Skip to content
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

ComputeDistance in descriptor matching is never been called? #65

Open
glennliu opened this issue Sep 9, 2024 · 0 comments
Open

ComputeDistance in descriptor matching is never been called? #65

glennliu opened this issue Sep 9, 2024 · 0 comments

Comments

@glennliu
Copy link

glennliu commented Sep 9, 2024

Hi

Thanks for your interesting work.

I have questions regarding the ComputeDistance function. If I understand correct, the function compute the similarity beteen the two hybrid descriptor, which is a key step in the top-down loop closure detection introduced in the paper.

Then,

  1. I can not find the function compute the similarity between place descirptors. Do you implement it different from the paper?
  2. This function seems have never been recalled in the program. I can only find it in its .h and .cpp file. Do you use it in the experiment?

The reason I ask is that I want to evaluate the loop closure detection module separately. So, I can avoid deploying the entire SLAM system and prepare light-weighted data. But I need to know how does the front-end works. Since the key loop closure detection function has not been recalled, I don't what it actually reads from the front-end and how does each descriptor been constructed.

Thanks
Chuhao

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