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

some question to ask #14

Open
lonlonago opened this issue Nov 20, 2024 · 1 comment
Open

some question to ask #14

lonlonago opened this issue Nov 20, 2024 · 1 comment

Comments

@lonlonago
Copy link

lonlonago commented Nov 20, 2024

img_v3_02gq_4411d33a-3686-4af4-91ac-dfe809663c1g

question one: if I have a very large pointcloud ,and I replace one of the point clouds with a large point cloud data, an error will be reported as shown in the figure

The second question: Is there no such function as icp. hasConverted() or icp. getFitnessScore()? How can I judge whether the registration is successful?

Third, I want to use it for initialization positioning based on PCD big map. Do you have any suggestions and how to operate?
can I give a init guess pose to the registration first ?

Thank you very much for your excellent work!

@LimHyungTae
Copy link
Member

A1. I guess, feature extraction is only allowed for a single scan.
A2. Once you check the # of final inliers, we can guess whether the registration succeeded or not.
A3. In that case, I'd recommend not using this repository, but please refer to the original TEASER++ repository. And please read my recent paper: https://arxiv.org/abs/2409.15615

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