JonathonLuiten/TrackEval

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1255 stars · 310 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

TrackEval is a Python library for evaluating multi-object tracking (MOT) algorithms, implementing metrics such as HOTA, CLEARMOT, IDF1, VACE, and Track mAP. It serves as the official evaluation code for several tracking benchmarks including MOTChallenge, KITTI Tracking, and RobMOTS.

Use cases

• evaluate multi-object tracking results with HOTA metrics
• compute MOTA and MOTP scores for MOTChallenge submissions
• compare tracker performance across KITTI and other benchmarks
• run official evaluation for a tracking challenge submission
• plot and analyze tracking metric results
• evaluate segmentation masks for video object tracking

When to choose

• you need standardized, benchmark-official MOT evaluation metrics
• you want HOTA, CLEARMOT, IDF1, or Track mAP computed consistently
• you are submitting to a benchmark like MOTChallenge or KITTI that uses TrackEval

When to avoid

• you need real-time tracking rather than offline evaluation
• your task is single-object tracking or image-level detection only
• you need a non-Python evaluation pipeline

Facets

library · maturity stable

computer-vision machine-learning benchmarking data-science computer-vision machine-learning artificial-intelligence python cross-platform multi-object-tracking mot hota evaluation-metrics tracking-benchmarks clearmot idf1 algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="JonathonLuiten/TrackEval")