vcg-uvic/sportsfield_release

Code release for WACV 2020, "Optimizing Through Learned Errors for Accurate Sports Field Registration"

45
/ 100
Emerging

This project helps sports analysts and researchers accurately overlay a standard soccer field template onto real-world images or video footage. You input an image or video of a soccer game, and it outputs a highly precise 'registered' image with the template perfectly aligned, even in challenging conditions. It's designed for academic researchers studying sports analytics or computer vision applications in sports.

No commits in the last 6 months.

Use this if you need to precisely map game events or player positions onto a standardized field representation from diverse visual inputs for non-commercial academic research.

Not ideal if you need a commercial solution, as this project is patent-protected and strictly for non-commercial academic research use.

sports-analytics soccer-analysis sports-research video-analysis game-event-tracking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

77

Forks

25

Language

Jupyter Notebook

License

Last pushed

Mar 28, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/vcg-uvic/sportsfield_release"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.