Spiideo/soccersegcal
Soccer pitch segmentation and camera calibration in two steps. Step 1, pixelwise segmentation of an broacast image of a soccer game into six different clases defined by the line markings. Step 2, a differential-rendering optimizer that tries to estimate camera parameters from such segementations.Trained on SoccerNet.
This project helps sports analysts and broadcasters automatically understand camera angles and player positions from soccer match footage. It takes broadcast video frames as input and outputs a pixel-level breakdown of the pitch markings, followed by precise camera calibration parameters. It's designed for professionals working with sports analytics, referee assistance systems, or augmented reality overlays in soccer.
No commits in the last 6 months.
Use this if you need to precisely calibrate broadcast soccer camera feeds for advanced sports analysis or graphical overlays.
Not ideal if you're looking for player tracking or general object recognition within the soccer footage, as its focus is strictly on pitch segmentation and camera parameters.
Stars
37
Forks
7
Language
Python
License
MIT
Category
Last pushed
Aug 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Spiideo/soccersegcal"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ArtLabss/tennis-tracking
Open-source Monocular Python HawkEye for Tennis
shukkkur/VolleyVision
Applying Deep Learning Approaches to Volleyball Data
OwlTing/AI_basketball_games_video_editor
AI Basketball Games Video Editor is a program to get basketball highlight video by PyTorch...
vcg-uvic/sportsfield_release
Code release for WACV 2020, "Optimizing Through Learned Errors for Accurate Sports Field Registration"
Basket-Analytics/BasketTracking
Basketball 🏀 action tracking and understanding using classical computer vision approaches and...