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 on output format #90

Open
gcaldarulo7 opened this issue Jan 26, 2022 · 2 comments
Open

Question on output format #90

gcaldarulo7 opened this issue Jan 26, 2022 · 2 comments

Comments

@gcaldarulo7
Copy link

Hi WeijingShi,
I was looking at your code for my master thesis work on obstacle tracking in autonomous vehicles and wanted to ask what format is the output presented in? i.e. when I see the line
Car -1 -1 0 720.9023535498856 173.59484562011147 919.0134679995857 318.15647610376465 1.5824964 1.6578441 3.52217 2.5813196 1.5942556 9.684726 1.5792502 103.05632911317069
what are the values referred to?
thanks in advance

@WeijingShi
Copy link
Owner

Hi @gcaldarulo7

Thanks for your interest in our work. The output follows KITTI format:
name truncation occlusion alpha xmin ymin xmax ymax height width length x3d y3d z3d heading

In our main evaluation, truncation occlusion alpha are not used, so we use placeholder -1 -1 0.
xmin ymin xmax ymax are image coordinates for the 2D bounding box's upper-left and lower-right corners.
height width length are the object dimensions.
x3d y3d z3d are the 3D coordinates (camera coordinate frame) of the object's center (e.g. lower center of the car).
heading: object's yaw in the same 3D coordinate frame.

I hope this helps. Thanks,
Weijing

@gcaldarulo7
Copy link
Author

Thank you very much!

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