View source for SLAM: state of the art analysis

=Tested systems:=

Bundler [http://phototour.cs.washington.edu/bundler/]

PTAM (Parallel Tracking And Map) [http://www.robots.ox.ac.uk/~gk/PTAM/]

DWO (Double Window Optimization) [https://github.com/strasdat/ScaViSLAM]


=Datasets:=

RAWSEEDS [http://www.rawseeds.org/home/]

KITTI [http://www.cvlibs.net/datasets/kitti/index.php]

Computer Vision Group [http://vision.in.tum.de/data/datasets/rgbd-dataset/download]

The New College Dataset [http://www.robots.ox.ac.uk/NewCollegeData/]


=Open issues/questions=
These are the main open questions.
*initialization with EKF (TODO see [http://www.openslam.org/robotvision])
*BA advantages:
**accuracy
**density
*limits:
**computational cost;
**resouces

=To see/check=
Some useful tools to see or to check at least:
*g2o [http://openslam.org/g2o.html]
*MRPT [http://www.mrpt.org/]