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

Question about convex hull of the keyframe set #50

Open
Wuqiqi123 opened this issue May 27, 2024 · 2 comments
Open

Question about convex hull of the keyframe set #50

Wuqiqi123 opened this issue May 27, 2024 · 2 comments

Comments

@Wuqiqi123
Copy link

Wuqiqi123 commented May 27, 2024

2024-10-08_13-29.png
Hi, author. Thanks for you great works.

I have a question about convex hull in your paper:
As the image above, the convex hull of the keyframe set are the L nearest neighbor convex hull scans of all keyframes, why the left-up corner keyframes are been selected?

@kennyjchen
Copy link
Collaborator

Hi @Wuqiqi123 -- great question. Those top-left ones are keyframes that are in the set of all keyframes which construct the convex hull of the keyframes. We use those to retrieve boundary points for the submap during scan-to-map matching.

@Wuqiqi123
Copy link
Author

Hi @Wuqiqi123 -- great question. Those top-left ones are keyframes that are in the set of all keyframes which construct the convex hull of the keyframes. We use those to retrieve boundary points for the submap during scan-to-map matching.

Given a set of all keyframes(coordinate system) and to choose some of them to construct the convex hull, but I don't known why only the green spheres are selected. The frames with green spheres doesn't look like a convex hull boundary of all keyframes.

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

2 participants