hku-mars / btc_descriptor Goto Github PK

I would like to express my gratitude for your excellent work. May I kindly inquire as to when the code will be updated?🎉

Great work!!!

When I tried to replicate this work, I found that I consistently failed to obtain an accurate transformation whenever loop closure was detected. I noticed that the influence of the reference planes is significant;

When I select one reference plane, the accuracy of plane fitting greatly affect the final transformation by P3P. Could it be that I misunderstood something here?

By the way, I test it outdoor.

Dear auther,
I have read some paper related to binary descriptor in LiDAR sensor area, such as, https://ieeexplore.ieee.org/document/10187686. In their works, the binary descriptor is extracted from the local submap like NDT. However, refer to your introduction, the binary descriptor is belong to each keypoint forming the triangle. In your STD paper, the process of selecting keypoints create a binary map looks like the corner point in camera SLAM, as following picture shows.

Can I suppose the way to construct binary descriptor is similar with the BRIEF feature in ORB-SLAM?

Thanks for your reply!