AIRWiki - User contributions [en]

User:MarcoUberti

2008-06-16T15:44:06Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|advisor=AlessandroGiusti
|projectpage=Long Exposure Images for Resource-constrained video surveillance
|photo=Fulminilecco.jpg
}}

User:MarcoUberti

2008-06-16T15:43:31Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|advisor=AlessandroGiusti|Alessandro Giusti
|projectpage=Long Exposure Images for Resource-constrained video surveillance
|photo=Fulminilecco.jpg
}}

User:MarcoUberti

2008-06-16T15:43:04Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|advisor= User:AlessandroGiusti
|projectpage=Long Exposure Images for Resource-constrained video surveillance
|photo=Fulminilecco.jpg
}}

User:MarcoUberti

2008-06-16T15:42:35Z

MarcoUberti:

User:MarcoUberti

2008-06-16T15:36:31Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|advisor=AlessandroGiusti
|projectpage=Long_Exposure_Images_for_Resource-constrained_video_surveillance
|photo=Fulminilecco.jpg
}}

User:MarcoUberti

2008-06-16T15:36:12Z

MarcoUberti:

File:Fulminilecco.jpg

2008-06-16T15:35:48Z

MarcoUberti:

User:MarcoUberti

2008-06-16T15:33:14Z

MarcoUberti:

User:MarcoUberti

2008-06-16T15:32:39Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|advisor=AlessandroGiusti
|projectpage=Computer Vision and Image Analysis
|photo=Nophoto.png
}}

User:MarcoUberti

2008-06-16T15:32:15Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|advisor=[[User:AlessandroGiusti|Alessandro Giusti]]
|projectpage=Computer Vision and Image Analysis
|photo=Nophoto.png
}}

User:MarcoUberti

2008-06-16T15:31:31Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|advisor=VincenzoCaglioti
|projectpage=Computer Vision and Image Analysis
|photo=Nophoto.png
}}

User:MarcoUberti

2008-06-16T15:30:59Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|photo=Nophoto.png
}}

User:MarcoUberti

2008-06-16T15:30:20Z

MarcoUberti:

{{User
|firstname=Marco
|lastname=Uberti
|email=marcouberti84(at)gmail(dot)com
|projectpage=Computer Vision and Image Analysis
|photo=Nophoto.png
}}

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:28:11Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec) taken with a Canon EOS 350D digital camera|300px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

{|
| [[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|300px]] ||
[[Image:ottosec.JPG|center|thumb|Motion detection of the photo on the left|300px]]
|-
| [[Image:rampa.JPG|center|thumb|5 seconds exposure with a person walking|300px]] ||
[[Image:Cinquesec.JPG|center|thumb|Motion detection of the photo on the left|300px]]
|}

=== Documentation and useful files ===

* [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]
* [[Media:CodeUbertiRiva.zip | Matlab source code]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:27:54Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec) taken with a Canon EOS 350D digital camera|300px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

{|
| [[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|300px]] ||
[[Image:ottosec.JPG|center|thumb|Motion detection off the photo on the left|300px]]
|-
| [[Image:rampa.JPG|center|thumb|5 seconds exposure with a person walking|300px]] ||
[[Image:Cinquesec.JPG|center|thumb|Motion detection off the photo on the left|300px]]
|}

=== Documentation and useful files ===

* [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]
* [[Media:CodeUbertiRiva.zip | Matlab source code]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:25:40Z

MarcoUberti: /* Project short description */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec) taken with a Canon EOS 350D digital camera|300px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

{|
| [[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|300px]] ||
[[Image:ottosec.JPG|center|thumb|Motion detection on the photo on the left|300px]]
|-
| [[Image:rampa.JPG|center|thumb|5 seconds exposure with a person walking|300px]] ||
[[Image:Cinquesec.JPG|center|thumb|Motion detection on the photo on the left|300px]]
|}

=== Documentation and useful files ===

* [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]
* [[Media:CodeUbertiRiva.zip | Matlab source code]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:25:26Z

MarcoUberti: /* Project short description */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec) taken with a Canon EOS 350D|300px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

{|
| [[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|300px]] ||
[[Image:ottosec.JPG|center|thumb|Motion detection on the photo on the left|300px]]
|-
| [[Image:rampa.JPG|center|thumb|5 seconds exposure with a person walking|300px]] ||
[[Image:Cinquesec.JPG|center|thumb|Motion detection on the photo on the left|300px]]
|}

=== Documentation and useful files ===

* [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]
* [[Media:CodeUbertiRiva.zip | Matlab source code]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:16:06Z

MarcoUberti: /* Project short description */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec) taken with a Canon EOS 350D camera|400px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]

<gallery>
Image:magazzino.JPG|8 seconds exposure with a person walking
Image:ottosec.JPG|8 seconds exposure with a person walking
Image:rampa.JPG|8 seconds exposure with a person walking
Image:Cinquesec.JPG|8 seconds exposure with a person walking
</gallery>

=== Documentation and useful files ===

* [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]
* [[Media:CodeUbertiRiva.zip | Matlab source code]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:15:02Z

MarcoUberti: /* Documentation and useful files */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec)|400px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]

=== Documentation and useful files ===

* [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]
* [[Media:CodeUbertiRiva.zip | Matlab source code]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:14:30Z

MarcoUberti: /* Documentation and useful files */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec)|400px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]

=== Documentation and useful files ===

[[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]
[[Media:CodeUbertiRiva.zip | Matlab source code]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

File:CodeUbertiRiva.zip

2008-06-16T15:13:43Z

MarcoUberti:

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:11:38Z

MarcoUberti: /* Project short description */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec)|400px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]

=== Documentation and useful files ===

[[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:09:20Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec)|300px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]

=== Documentation and useful files ===

[[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | Documentation]]

=== Useful link ===

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

File:Longexp.JPG

2008-06-16T15:07:58Z

MarcoUberti:

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:07:37Z

MarcoUberti: /* Project short description */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:Longexp.JPG|center|thumb|An example of long exposure image (1 sec)|300px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:Cinquesec.JPG|left|thumb|8 seconds exposure with a person walking|300px]]

=== Documentation and useful files ===

Documentation aviable [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | here]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:07:12Z

MarcoUberti: /* Project short description */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

[[Image:longexp.JPG|left|thumb|An example of long exposure image (1 sec)|300px]]

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:Cinquesec.JPG|left|thumb|8 seconds exposure with a person walking|300px]]

=== Documentation and useful files ===

Documentation aviable [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | here]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:05:02Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:Cinquesec.JPG|left|thumb|8 seconds exposure with a person walking|300px]]

=== Documentation and useful files ===

Documentation aviable [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | here]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:04:04Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|left|thumb|8 seconds exposure with a person walking|400px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]

=== Documentation and useful files ===

Documentation aviable [[Media:Long_Exposure_Images_for_Resource-constrained_video_surveillance.pdf | here]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:03:30Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|right|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|left|thumb|8 seconds exposure with a person walking|400px]]
[[Image:Cinquesec.JPG|right|thumb|8 seconds exposure with a person walking|400px]]

=== Documentation and useful files ===

[[Documentation]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Image retargeting by k-seam removal

2008-06-16T15:03:06Z

MarcoUberti: /* '''Conclusion''' */

== '''Part 1: project profile''' ==

=== Project name ===

Image retargeting by k-seam removal.

=== Project short description ===

This project presents a methodology for content aware image resizing based on seam removal. In this work four different approaches were implemented in order to retarget an image:
* removing a 8-connected path of pixels (1-seam) minimizing an energy function
* removing a not connected path of pixels (k-seam) minimizing an energy function
* removing a 8-connected path of pixels (1-seam) minimizing the energy variation in the image
* removing a not connected path of pixels (k-seam) minimizing the energy variation in the image
where k is the maximum disconnect allowed.

The work ends with a comparison on several test pictures among these algorithms considering the one which gives the best results.

=== Dates ===
Start date: 2008/01/01

End date: 2008/06/24

=== People involved ===

===== Project head(s) =====

* V. Caglioti - Vincenzo (dot) Caglioti (at) polimi (dot) it

===== Other Politecnico di Milano people =====

* P. Taddei - pierluigi (dot) taddei (at) polimi (dot) it

===== Students currently working on the project =====

* Luigi Cardamone - luigi (dot) cardamone (at) mail (dot) polimi (dot) it

* [[User:PamelaGotti|Pamela Gotti]]

=== Laboratory work and risk analysis ===

This project does not include laboratory activities.

== '''Part 2: project description''' ==

==='''State of the art'''===

This project is based on the article ''Seam carving for content-aware image resizing, Avidan, S. and Shamir, A.,International Conference on Computer Graphics and Interactive Techniques, 2007'', in which the author describes content aware image resizing by removal of 8-connected path of pixels.

==='''The problem'''===

The normal way of resizing a picture doesn’t take in account it’s content and differs from the resizing of a web page where each object is modified on the basis of its content. So, there is the need for an image resizing that is content aware.

==='''The Idea'''===

The idea behind content aware resizing is to treat in a different way the important regions of the image respect to those regions with less information. To achieve this goal it’s possible to remove from the picture the seam with low energy.
A seam is a path of pixel from top to bottom or from left to right, as it’s possible to see in the following picture:

[[Image:Paesaggioconseam.JPG|center|thumb|An example of vertical connected seam|400px]]

==='''The Algorithm'''===

The implemented algorithms use different kind of seam and minimize different measure:
* removing a 8-connected path of pixels (1-seam) minimizing an energy function
* removing a not connected path of pixels (k-seam) minimizing an energy function
* removing a 8-connected path of pixels (1-seam) minimizing the total energy variation in the image
* removing a not connected path of pixels (k-seam) minimizing the total energy variation in the image

Where k seam are those seam with a maximum disconnection of k pixel. This disconnection is important when in the picture there are many object and it’s important to don’t cut their edges.

All these algorithms were implemented in Matlab and tested on several pictures (source code is available here: [[Media:Carving.zip|Carving source code]]
). The project follows with a comparative analysis of strength and weakness of each method.

==='''Report'''===

The report about this project is available here: [[Media:Relazione.pdf|Report]]

==='''Conclusion'''===

From results emerge that the best algorithm is that one working with 1-seam with minimum energy.

In the following pictures it is possible to see the difference between the result of the retargeting using the best algorithm and the normal resize method (stretching).

[[Image:ImageContentResizeDelfino.jpg|left|thumb|Original image|325px]]

[[Image:Delfino22.JPG|left|thumb|Resized image with streching|250px]]

[[Image:Delfino2 original connected.JPG|left|thumb|Resized image with 1-seam with minumum energy|250px]]

[[Image:Delfino2 original notconnected.JPG|left|thumb|Resized image with k-seam with minumum energy|250px]]

[[Image:Delfino2 final connected.JPG|left|thumb|Resized image with 1-seam with minumum energy variation|250px]]

[[Image:Delfino2 final notconnected.JPG|left|thumb|Resized image with k-seam with minumum energy variation|250px]]

Image retargeting by k-seam removal

2008-06-16T15:02:41Z

MarcoUberti: /* '''Conclusion''' */

== '''Part 1: project profile''' ==

=== Project name ===

Image retargeting by k-seam removal.

=== Project short description ===

This project presents a methodology for content aware image resizing based on seam removal. In this work four different approaches were implemented in order to retarget an image:
* removing a 8-connected path of pixels (1-seam) minimizing an energy function
* removing a not connected path of pixels (k-seam) minimizing an energy function
* removing a 8-connected path of pixels (1-seam) minimizing the energy variation in the image
* removing a not connected path of pixels (k-seam) minimizing the energy variation in the image
where k is the maximum disconnect allowed.

The work ends with a comparison on several test pictures among these algorithms considering the one which gives the best results.

=== Dates ===
Start date: 2008/01/01

End date: 2008/06/24

=== People involved ===

===== Project head(s) =====

* V. Caglioti - Vincenzo (dot) Caglioti (at) polimi (dot) it

===== Other Politecnico di Milano people =====

* P. Taddei - pierluigi (dot) taddei (at) polimi (dot) it

===== Students currently working on the project =====

* Luigi Cardamone - luigi (dot) cardamone (at) mail (dot) polimi (dot) it

* [[User:PamelaGotti|Pamela Gotti]]

=== Laboratory work and risk analysis ===

This project does not include laboratory activities.

== '''Part 2: project description''' ==

==='''State of the art'''===

This project is based on the article ''Seam carving for content-aware image resizing, Avidan, S. and Shamir, A.,International Conference on Computer Graphics and Interactive Techniques, 2007'', in which the author describes content aware image resizing by removal of 8-connected path of pixels.

==='''The problem'''===

The normal way of resizing a picture doesn’t take in account it’s content and differs from the resizing of a web page where each object is modified on the basis of its content. So, there is the need for an image resizing that is content aware.

==='''The Idea'''===

The idea behind content aware resizing is to treat in a different way the important regions of the image respect to those regions with less information. To achieve this goal it’s possible to remove from the picture the seam with low energy.
A seam is a path of pixel from top to bottom or from left to right, as it’s possible to see in the following picture:

[[Image:Paesaggioconseam.JPG|center|thumb|An example of vertical connected seam|400px]]

==='''The Algorithm'''===

The implemented algorithms use different kind of seam and minimize different measure:
* removing a 8-connected path of pixels (1-seam) minimizing an energy function
* removing a not connected path of pixels (k-seam) minimizing an energy function
* removing a 8-connected path of pixels (1-seam) minimizing the total energy variation in the image
* removing a not connected path of pixels (k-seam) minimizing the total energy variation in the image

Where k seam are those seam with a maximum disconnection of k pixel. This disconnection is important when in the picture there are many object and it’s important to don’t cut their edges.

All these algorithms were implemented in Matlab and tested on several pictures (source code is available here: [[Media:Carving.zip|Carving source code]]
). The project follows with a comparative analysis of strength and weakness of each method.

==='''Report'''===

The report about this project is available here: [[Media:Relazione.pdf|Report]]

==='''Conclusion'''===

From results emerge that the best algorithm is that one working with 1-seam with minimum energy.

In the following pictures it is possible to see the difference between the result of the retargeting using the best algorithm and the normal resize method (stretching).

[[Image:ImageContentResizeDelfino.jpg|left|thumb|Original image|325px]]

[[Image:Delfino22.JPG|right|thumb|Resized image with streching|250px]]

[[Image:Delfino2 original connected.JPG|left|thumb|Resized image with 1-seam with minumum energy|250px]]

[[Image:Delfino2 original notconnected.JPG|left|thumb|Resized image with k-seam with minumum energy|250px]]

[[Image:Delfino2 final connected.JPG|left|thumb|Resized image with 1-seam with minumum energy variation|250px]]

[[Image:Delfino2 final notconnected.JPG|left|thumb|Resized image with k-seam with minumum energy variation|250px]]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:02:18Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:ottosec.JPG|left|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:01:17Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|300px]] [[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|300px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|400px]] [[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:00:56Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|400px]] [[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|400px]] [[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:00:36Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:ottosec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

File:Ottosec.JPG

2008-06-16T15:00:17Z

MarcoUberti:

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T15:00:02Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:8sec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:Cinquesec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

File:Cinquesec.JPG

2008-06-16T14:59:35Z

MarcoUberti:

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T14:58:31Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:8sec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:rampa.JPG|center|thumb|8 seconds exposure with a person walking|400px]]
[[Image:5sec.JPG|center|thumb|8 seconds exposure with a person walking|400px]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

File:8sec.jpg

2008-06-16T14:57:44Z

MarcoUberti: 8 seconds motion detection (difference of two images)

8 seconds motion detection (difference of two images)

File:5sec.jpg

2008-06-16T14:57:06Z

MarcoUberti: 5 seconds motion detection (difference of two images)

5 seconds motion detection (difference of two images)

File:Longexp.jpg

2008-06-16T14:56:16Z

MarcoUberti: An example of long expousure image (1 sec)

An example of long expousure image (1 sec)

File:Rampa.JPG

2008-06-16T14:55:08Z

MarcoUberti: 5 seconds exposure with a person walking

5 seconds exposure with a person walking

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T14:48:43Z

MarcoUberti: /* Results and problems */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

* Long exposure photograpy technique
* Simulation of a long exposure photo using the mean of video frames
* Median filtering
* Motion detection using images difference
* Modelling images as signal plus gaussian noise
* Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
* the feet of a walking person are detected very well, despite the rest of the body
* in some cases shadows can help detect motion, in other case no

[[Image:magazzino.JPG|center|thumb|8 seconds exposure with a person walking|400px]]

=== Useful link ===

link to project documents and files (you can upload them using the [[Special:Upload]] page);

PETS, Performance Evaluation of Tracking and Surveillance [http://www.cvg.rdg.ac.uk/slides/pets.html]

File:Magazzino.JPG

2008-06-16T14:47:36Z

MarcoUberti:

8 sec expousure with a person walking

File:Magazzino.JPG

2008-06-16T14:46:13Z

MarcoUberti: 5 sec expousure with a person walking

5 sec expousure with a person walking

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T14:28:37Z

MarcoUberti: /* Students who worked on the project in the past */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

[[User:AndreaRiva|Andrea Riva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

[[User:MarcoUberti|Marco Uberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

=== The Problem ===

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

=== Preliminary studies ===

This concept and preliminary studies have been used to elaborate the solution:

- Long exposure photograpy technique
- Simulation of a long exposure photo using the mean of video frames
- Median filtering
- Motion detection using images difference
- Modelling images as signal plus gaussian noise
- Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

=== Adopted solution ===

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

=== Results and problems ===

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
- the feet of a walking person are detected very well, despite the rest of the body
- in some cases shadows can help detect motion, in other case no

link to project documents and files (you can upload them using the [[Special:Upload]] page);

link a PETS (dataset ecc...)

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T14:27:28Z

MarcoUberti: /* Project Advisor */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

[[User:AlessandroGiusti|Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

Andrea Riva - [[AndreaRiva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

Marco Uberti - [[MarcoUberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

'''The Problem'''

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

'''Preliminary studies'''

This concept and preliminary studies have been used to elaborate the solution:

- Long exposure photograpy technique
- Simulation of a long exposure photo using the mean of video frames
- Median filtering
- Motion detection using images difference
- Modelling images as signal plus gaussian noise
- Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

'''Adopted solution'''

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

'''Results and problems'''

The results vary very much for different exposures, movements, colors and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
- the feet of a walking person are detected very well, despite the rest of the body
- in some cases shadows can help detect motion, in other case no

link to project documents and files (you can upload them using the [[Special:Upload]] page);

link a PETS (dataset ecc...)

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T14:26:25Z

MarcoUberti: /* Project Advisor */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

A. Giusti - [[AlessandroGiusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

Andrea Riva - [[AndreaRiva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

Marco Uberti - [[MarcoUberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

The Problem

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

Preliminary studies

This concept and preliminary studies have been used to elaborate the solution:

- Long exposure photograpy technique
- Simulatiion of a long exposure photo using the mean of video frames
- Median filtering
- Motion detection using images difference
- Modelling images as signal plus gaussian noise
- Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

Adopted solution

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

Results and problems

The results vary very much for different exposures, for different movements and for different color and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
- the feet of a walking person are detected very well, despite the rest of the body
- in some cases shadows can help detect motion, in other case no

link to project documents and files (you can upload them using the [[Special:Upload]] page);

link a PETS (dataset ecc...)

Long Exposure Images for Resource-constrained video surveillance

2008-06-16T14:26:13Z

MarcoUberti: /* Project Advisor */

== '''Part 1: project profile''' ==

=== Project name ===

Long Exposure Images for Resource-constrained video surveillance

=== Project short description ===

The aim of the project is to create a simple system for detecting movements in long exposure images, looking at the differences between them.
The work consists in taking some movement-detection tests using images taken in different situation and with an exposure varying between 1 and 30 seconds, seeking for satisfable results and parameters that can be used in a wide range of situations.

=== Dates ===
Start date: 2008/02/01

End date: ongoing

=== People involved ===

===== Project Advisor =====

A. Giusti - [[User:Alessandro Giusti]]

===== Students currently working on the project =====

===== Students who worked on the project in the past =====

Andrea Riva - [[AndreaRiva]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

Marco Uberti - [[MarcoUberti]] - as a project for the courses Image Analysis and Synthesis and
Advanced Topics of Image Analysis, prof. Caglioti

== '''Part 2: project description''' ==

The Problem

In some situations (e.g. wireless sensor networks), it may be useful to perform video surveillance tasks using long exposure images.
In long exposure images, moving objects appear blurred and often they are barely visible, depending on movement direction and speed and on the colour and contrast of the object.

Preliminary studies

This concept and preliminary studies have been used to elaborate the solution:

- Long exposure photograpy technique
- Simulatiion of a long exposure photo using the mean of video frames
- Median filtering
- Motion detection using images difference
- Modelling images as signal plus gaussian noise
- Datasets for videosurveillance

The principal problem in detecting movement in long exposure images is the blur of the subject in movement, that grows up with the exposure time.
Also other facts influences the detection, such as movement direction and speed,colours and contrast of the subject, and in particular the variation of the brightness of the scene.

Adopted solution

The simplest way to detect motion is making the difference between two images of the same scene with an appropriate threshold to avoid noise disturb. For better result, however, the threshold is automatically detected by compute the variance between more poses of the same scene without any motion. There are more than one method for compute the threshold: by avaraging the variance of all the pixels or by taking a different variance for each pixel.

Results and problems

The results vary very much for different exposures, for different movements and for different color and contrast between the background and the moving object.
The principal problems encountered during motion detection are the variation of the brightness of the scene and the presence of shadows. The solution to the first problem is quite simple for some cases, but the second problem is very difficult to solve.
There are also some interesting aspects like:
- the feet of a walking person are detected very well, despite the rest of the body
- in some cases shadows can help detect motion, in other case no

link to project documents and files (you can upload them using the [[Special:Upload]] page);

link a PETS (dataset ecc...)