vslam

Published: by Creative Commons Licence

Visual Simultaneous Localization and Mapping,

Visual SLAM

William Yu 2018.06.17 update

Simultaneous Localization and Mapping, also known as SLAM, is the computational problem of constructing or updating a map of an unknown environment while simultaneously keeping track of an agent's location within it.


News

Books

Courses, Lectures and Workshops

Papers

Researchers

United States

Europe

Australia

China

Datasets

  1. Intel Research Lab (Seattle)
  2. Malaga Dataset,一个西班牙的团队采集的Malaga城市数据:The Málaga Stereo and Laser Urban Data Set,覆盖了城市中汽车驾驶的各种情况(停车,加速,减速,行人,建筑,绿化带等),里面提供了双摄像头,Laser,IMU等数据以及GPS的ground truth trajectory。不过该版本因为是在市中心,所以GPS的ground truth并不可靠
  3. 另一个是慕尼黑工业大学Computer Vision Lab的RGB-D dataset https://vision.in.tum.de/data/datasets/rgbd-dataset,里面提供了大量的室内的RGBD数据集,以及非常方便好用的benchmark tools
  4. KITTI Dataset:The KITTI Vision Benchmark Suite

Code

  1. ORB-SLAM
  2. LSD-SLAM
  3. ORB-SLAM2
  4. DVO: Dense Visual Odometry
  5. SVO: Semi-Direct Monocular Visual Odometry
  6. G2O: General Graph Optimization
  7. RGBD-SLAM

Blogs

Miscellaneous

Contributing / Contact

Have anything in mind that you think is awesome and would fit in this list? Feel free to send a pull request.

Feel free to contact me anytime for anything.


License

CC0