Ask Your Question
1

Which is the best Visual Slam algorithm to implement using stereo vision? Are there any source code available?

asked 2016-08-17 08:19:29 -0600

Vijeet gravatar image

I want to implement visual SLAM using stereo camera in C/C++. I found papers on SLAM using Laser scanners and also cameras, but they are for robots. I need it for cars.Please let me know which algo to implement or are there any source code available?I know programming in C/C++ and also OpenCV. Suggest me how to start.

edit retag flag offensive close merge delete

3 Answers

Sort by ยป oldest newest most voted
2

answered 2016-10-14 17:15:20 -0600

There are many open source algorithms using visual SLAM. Use this link to check for a few implementation. I am not sure what you mean by applying it for cars, theoretically they should work if you are using stereo vision to get data, be it robots or cars.

I would suggest starting with ORB-SLAM, Open RatSLAM and OKVIS since they seem to provide better results in most cases. You can of course try other algorithms for comparing the performance. Some of the algorithms may be for monocular camera but later might release a version for stereo camera, so look out for that. Other algorithms that may be interesting based on your question would be LSD SLAM, LibViso, PTAM to list a few. You also mentioned finding some papers on the related topic, it is quite likely that they already have some kind of implementation in place to take a look at.

Also if you are looking for data with cars, KITTI dataset seems to be quite popular.

With my limited experience I would say there is not yet best algorithm which can be identified.

edit flag offensive delete link more

Comments

Thanks for the information. Its really helpful.

Vijeet gravatar image Vijeet  ( 2017-05-23 06:22:35 -0600 )edit

Could you please tell me how to run openratslam in ubuntu16.04 with ROSkinetic and opencv3.4 ?

sunt40 gravatar image sunt40  ( 2019-02-23 01:32:38 -0600 )edit
1

answered 2017-05-23 04:21:32 -0600

sihe gravatar image

Another very interesting algorithm is RTAB: https://introlab.github.io/rtabmap/ . It is available as a ROS package, wtih an active developer and seems to produce quite impressive dense maps.

edit flag offensive delete link more
0

answered 2017-05-24 06:50:02 -0600

The state of the Art and Open Source SLAM Algorithm for Visual SLAM and in your case Stereo SLAM to get the correct scale of the scene is in my opinion ORB-SLAM2. It can be used without ROS but there are also little ROS Wrappers for it available. It is based on ORB (Oriented FAST and Rotated BRIEF) Features, operates on Realtime, provides loop closures and relocalization. Depending on how fast is your system the poses and mappoints are optimized pretty good. The sparse reconstruction of the environment makes it possible to map even large areas. For more information check the papers which are linked in the git repository.

edit flag offensive delete link more

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

Stats

Asked: 2016-08-17 08:19:29 -0600

Seen: 4,008 times

Last updated: May 24 '17