MartyG-RealSense
commented
1 year ago Hi @Pshcer OpenCV is not typically used with RealSense for wall following applications that take account of left and right walls. Navigation and obstacle avoidance with RealSense cameras is more commonly performed with ROS.
My research of your question indicated that OpenCV wall following applications tended to use a technique called Hough Transform, like in the maze-solving paper at the link below.
https://campus-rover.gitbook.io/lab-notebook/gen4-reports/cvmaze
Leads to further resources can be found by googling for the term opencv "wall-following" hough (include the quotation marks to help to find search results relevant to wall-following).
In regard to a ROS based approach, an example of wall following with ROS and Python is here:
https://github.com/nimbekarnd/Wall-follower-in-ROS-using-Python
Pshcer
Before opening a new issue, we wanted to provide you with some useful suggestions (Click "Preview" above for a better view):
All users are welcomed to report bugs, ask questions, suggest or request enhancements and generally feel free to open new issue, even if they haven't followed any of the suggestions above :)
Issue Description
I want to use the intel realsense camera to build an autonomous bot that detects the wall on both sides and moves through the middle of the wall.
are there any readily available scripts or what are the possibilities of accomplishing this task using OpenCV computer vision incorporating with dept data