ArtLabss/tennis-tracking
Open-source Monocular Python HawkEye for Tennis
Combines TrackNet deep learning for ball tracking with ResNet50 player detection and court line identification, processing single-camera video feeds into annotated output with optional bounce-point prediction via sktime's TimeSeriesForestClassifier. Generates dynamic mini-maps overlaying detected players and ball positions on court coordinates, while supporting GPU acceleration through TensorFlow for real-time analysis of rally footage.
649 stars. No commits in the last 6 months.
Stars
649
Forks
150
Language
Python
License
Unlicense
Category
Last pushed
Feb 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ArtLabss/tennis-tracking"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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...
bnww/dart-sense
Dart Sense is an automatic dart scoring application. It uses a sophisticated deep learning-based...