Some questions about ORB-SLAM3 feature points.

[zhang-mu-zhi]

Hello,
according to the algorithm in your paper, the robot's navigation requires the combination of yolo's bounding_boxes and ORB-SLAM3's feature points.
But when I ran the ORB-SLAM3 code, I found that the distribution of feature points generated by ORB-SLAM3 was uneven, and many yolo's bounding_boxes did not have ORB-SLAM feature points.
As shown in the picture below, there are no feature points on the chair at all, but there are many feature points on the umbrella.
Therefore this algorithm cannot be run.
So how do you solve this problem?
I am very interested in the algorithm of your paper, so I have been trying to reproduce the robot navigation algorithm in your article . Thanks very much for your help.
thank you very much

[mmahdavian]

Hi zhang

Sorry for late reply. I've been on vacatioon. What you mention here is somehow true. It sometimes happens. But usually by moving the robot and giving it more time, ORB-SLAM finds other feature points too. Also I think I've seen other versions of ORB-SLAM that tries to find features more evenly. You can search for those. I didn't have that much trouble with my tests. So I didn't use them. Maybe putting a small paper on the top middle point of an object could help. So ORB features would be found there.

Good Luck