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 HOTA

Tracking 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