cheind/py-motmetrics

Health v2 · maintenance only

Adoption not part of the score

1487 stars · 261 forks observed · 2026-08-28

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

py-motmetrics is a Python library for evaluating multiple object tracking (MOT) results with MOTChallenge-aligned CLEAR MOT, Identity, and HOTA metrics such as MOTA, MOTP, and IDF1. It offers both a Python API and a command-line evaluator that can automatically detect common tracking file formats.

Use cases

• evaluate multiple object tracker results against ground truth
• compute MOTA MOTP IDF1 metrics for MOTChallenge
• benchmark object tracking algorithms in Python
• compare predicted tracking files to ground truth annotations
• compute HOTA metrics for tracking
• evaluate tracker output from VATIC or UA-DETRAC formats

When to choose

• you need standardized MOTChallenge-compatible tracking metrics
• you want a maintained Python library with both API and CLI evaluation
• you need to parse multiple tracking annotation formats automatically
• you want frame-level matching events for custom metric analysis

When to avoid

• you need real-time tracking rather than offline evaluation
• you work with single-object tracking only
• you need metrics for other vision tasks like detection or segmentation

Facets

library · maturity active

benchmarking computer-vision data-science analytics computer-vision machine-learning data-science testing python cli cross-platform multiple-object-tracking motchallenge clear-mot hota idf1 mota tracker-evaluation metrics

Member repositories

For agents

markdown · JSON · MCP: product_card(name="cheind/py-motmetrics")