# JonathonLuiten/TrackEval

HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).

Repository: https://github.com/JonathonLuiten/TrackEval
Canonical: https://ross.abutalabs.com/products/trackeval
Language: Python
License: MIT
License Family: permissive
Last push: 2024-07-03T06:21:21+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2177, "days_push": 791, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1255, forks 310 (observed 2026-08-28T04:04:08.854710+00:00)

## What it is
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
- artifact type: library
- maturity: stable
- function: computer-vision, machine-learning, benchmarking, data-science
- domain: computer-vision, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: multi-object-tracking, mot, hota, evaluation-metrics, tracking-benchmarks, clearmot, idf1, algorithms

## Member repositories
- JonathonLuiten/TrackEval (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:08.854710+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:07:18.480768+00:00, confidence not recorded.
  - readme: https://github.com/JonathonLuiten/TrackEval (fetched 2026-08-28T04:04:08.854710+00:00, sha 3f7d557d469a)
- Data as of 2026-08-30T08:39:29.467469+00:00.