Skip to content
This repository has been archived by the owner on Sep 2, 2024. It is now read-only.

Does the Input must be one-to-one? #10

Open
DeliKeng opened this issue Feb 23, 2018 · 3 comments
Open

Does the Input must be one-to-one? #10

DeliKeng opened this issue Feb 23, 2018 · 3 comments

Comments

@DeliKeng
Copy link

If the cloud's number are difference, Should I do the matching work?

@syncle
Copy link
Collaborator

syncle commented Feb 23, 2018

Technically yes. You can check the data we used in this repo. Check out here

@DeliKeng
Copy link
Author

Above all, I feel appreciate to your answer, and I have some question about the Initial of data?

How can I pick up match-point from two different cloud? I try this by curvature, But the result is not good. Dose this algorithm can adapt to different cloud? Could you give me some direction. Thank you!

@syncle
Copy link
Collaborator

syncle commented Feb 24, 2018

I am not sure whether I completely understood your question, but let me try one by one.

How can I pick up match-point from two different cloud? I try this by curvature, But the result is not good.

You don't have to match points by yourself. As shown in README.md, all you need to do is put xyz+geometric feature for the pipeline.

Dose this algorithm can adapt to different cloud?

Depends on the cases. FGR is tested on the noisy point clouds as well, but If the two point clouds are quite different (captured by different sensors, almost no overlapping, or density is not the same) it can suffer. See the discussion #5 #6.

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

No branches or pull requests

2 participants