search

xinshuoweng / AB3DMOT

(IROS 2020, ECCVW 2020) Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics"
http://www.xinshuoweng.com/
Other
1.68k stars 403 forks source link

Evaluation on Custom Tracking #103

Open YCAyca opened 2 years ago

YCAyca commented 2 years ago

Hello, I use another tool to make my detections + tracking and save the results in kitti format. I didnt well understand if its exactly the same format needed to use evaluate.py for 3d evaluation on kitti dataset. Here are my structure:

Screenshot from 2022-05-14 14-19-56 Screenshot from 2022-05-14 14-21-12 Screenshot from 2022-05-14 14-21-19

But I take the following error: "The uploaded results could not be evaluated. Check for format errors."

What should I change in mt format exactly? I thought it was the correct one for kitti benchmark format?

sharifinjf commented 2 years ago

I have the same problem. Does anyone find a solution?

zyg234 commented 1 year ago

I have the same problem. Does anyone find a solution?