MOTA, IDF1 and HOTA
Steppers for the counts behind MOTA and IDF1, and sliders for the detection and association halves of HOTA. The three disagree about what a tracking failure costs, and here they disagree on your numbers.
Try this
Add identity switches without adding misses. MOTA shrugs; IDF1 does not.
MOTA detection-centric
1 − (FN + FP + IDSW) / GT
IDF1 identity-centric
2·IDTP / (2·IDTP + IDFP + IDFN)
HOTA balanced
√(DetA · AssA)
Where this lab comes from
Object Tracking Metrics: MOTA, MOTP, IDF1, and HOTATracking adds identity over time, so its metrics score two things at once: detecting objects and keeping their IDs consistent. MOTA, MOTP, ID switches, IDF1, and the modern HOTA that balances detection against association, on one running door-cam example, with the equations and motmetrics.
More in metrics
- Precision, recall and the threshold — Edit the four counts, or drag a threshold and trace the PR and ROC curves.
- IoU and Dice, by dragging boxes — Two draggable boxes; intersection, union and both scores update live.
- Macro, micro and weighted, side by side — An editable C×C confusion matrix with per-class F1 drawn as bars.