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: Is it possible to mask out image regions? #122

Open
themightyoarfish opened this issue Oct 28, 2024 · 1 comment
Open

Question: Is it possible to mask out image regions? #122

themightyoarfish opened this issue Oct 28, 2024 · 1 comment

Comments

@themightyoarfish
Copy link

themightyoarfish commented Oct 28, 2024

I would like to run this software in a scenario where some fixed or less fixed object is showing up in the camera and LIDAR data, which should be ignored for calibration purposes, e.g. camera an LIDAR are mounted on large machinery which moves them around, or stuff is hanging into the image/lidar FOV.

Where would I add logic to filter out pixels or points so they do not participate in the optimization?

@koide3
Copy link
Owner

koide3 commented Oct 29, 2024

I think such a mask can be implemented by modifying the NIDCost class that measures the normalized information distance between a point cloud and an image.

BTW, I suppose just filling masked regions with a uniform color (e.g., black or white) should work in most cases because the NID effectively ignores such outliers (at least in theory).

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