What are best Visual SLAM algorithms in a dynamic environment?

asked 2019-08-19 05:58:25 -0500

ashwinsushil gravatar image

Hello everyone,

I have been doing some research on the Visual SLAM algorithms that are out there and there seems to be a lot. Some of the algorithms that I came across are ORB-SLAM, RTAB, LSD SLAM, etc.

I have an intel real sense D415 camera and a very dynamic environment. My aim is to localize my robot in this dynamic environment. (The D415 is a USB-powered depth camera and consists of a pair of depth sensors, RGB sensor, and infrared projector.)

Can someone please suggest me some of the best algorithms that I can use with ROS for this setup? Any help will be much appreciated :)

There is a similar question posted but not about dynamic environment: https://answers.ros.org/question/2418...


edit retag flag offensive close merge delete



Best ones out there are orb-slam2 and rtabmap, and both have ros implementations available.

Choco93 gravatar image Choco93  ( 2019-08-19 08:06:43 -0500 )edit