8000 About memery generation · Issue #3 · TEA-Lab/Robo-ABC · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

About memery generation #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
huamo555 opened this issue Nov 18, 2024 · 1 comment
Open

About memery generation #3

huamo555 opened this issue Nov 18, 2024 · 1 comment

Comments

@huamo555
Copy link

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?

image1
image2

@huamo555
Copy link
Author
huamo555 commented Nov 18, 2024

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?

image1 image2

Above is P0, I mapped one of the red points(Red dots simulate contact points) to P1, but now the error is huge.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant
0