# roboflow/sports

computer vision and sports

Repository: https://github.com/roboflow/sports
Canonical: https://ross.abutalabs.com/products/sports
Language: Python
License: MIT
License Family: permissive
Topics: computer-vision, deep-learning, deep-neural-networks, image-embeddings, keypoint-detection, object-detection, tutorial, football, soccer, sports, soccer-analytics, soccer-data, sports-analytics, sports-data, visualization, football-data
Last push: 2026-07-22T16:33:40+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 60, longevity 60
- inputs: {"age_days": 842, "days_push": 42, "days_rel": 58, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5320, forks 656 (observed 2026-08-28T04:09:15.575518+00:00)

## What it is
A Python library from Roboflow providing reusable computer vision tools for sports analytics, including ball tracking, player tracking and re-identification, jersey number reading, and camera calibration. It ships with datasets and examples focused on soccer but is applicable to sports and beyond.

## Use cases
- track a soccer ball in match footage
- detect and track players in a football video
- re-identify players across camera cuts
- read jersey numbers from video frames
- calibrate a camera view to a pitch for speed and distance stats
- detect pitch keypoints for soccer analytics

## When to choose
- you need open-source computer vision tools for soccer or sports video analysis
- you want pretrained datasets for player, ball, and pitch keypoint detection
- you are building sports analytics on top of Roboflow's detection models

## When to avoid
- you need a stable pip-installable package with versioned releases
- you need non-sports or general-purpose video analytics out of the box
- you need production-grade tracking with no custom tuning

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, object-storage, data-visualization, machine-learning
- domain: computer-vision, sports, machine-learning, data-science
- platform: python, cross-platform
- tags: sports-analytics, soccer, ball-tracking, player-tracking, keypoint-detection, camera-calibration, jersey-number-ocr, football

## Member repositories
- roboflow/sports (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:15.575518+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 2026-08-29T17:58:55.511476+00:00, confidence not recorded.
  - readme: https://github.com/roboflow/sports (fetched 2026-08-28T04:09:15.575518+00:00, sha aff8f1a88548)
- Data as of 2026-08-30T08:39:29.467469+00:00.