-
Notifications
You must be signed in to change notification settings - Fork 2
Description
Thank you for your excellent work!
I am trying to reproduce your work, but I am having difficulty in generating the memery, for two consecutive frames of images P0, P1, I first perform feature point matching. Then compute the homography matrix between them, next I try to map the contact points on P0 to P1. but in this process I found:
1, the accuracy of mapping is too low, many points will become less accurate after mapping to P1
2, the mapping effect is highly correlated with the correctness of the homography matrix, and homography matrix is correlated with the number of eigenpoints, different number of eigenpoints will bring about a big difference in the mapping result.
It is difficult for me to realize the contact point mapping from P0 to P1 through the single response matrix. I have followed your paper for fuzzy detection and window segmentation in my implementation, is there any mistake in my implementation, can you show your implementation process more specifically?

