Metrics for oriented/rotated bounding boxes

rafaelpadilla / review_object_detection_metrics

Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.

Other

1.08k stars 215 forks source link

Metrics for oriented/rotated bounding boxes #148

Closed Petros626 closed 2 months ago

Petros626 commented 3 months ago

Hey,

I would like to know, if this tool supports not only axis aligned bounding boxes for the evaluation. Is it planned in the future to implement this feature?

Thanks in advance

rafaelpadilla commented 2 months ago

It does not support oriented (rotated) bounding box. If you need to evaluate your detections in sick datasets, such as DOTA and UCAS, you need to adapt our code. I believe you just need to modify the IOU part. If you want to collaborate, please open a PR and tag me as a reviewer. 🙏

github-actions[bot] commented 2 months ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.