⚽ Advanced Football Video Analyzer
Complete Pipeline Implementation
This application:
- Player Detection - Collect player crops using Roboflow
- Team Classification - Train SigLIP-based team classifier
- Persistent Tracking - ByteTrack with stable ID assignment
- Field Transformation - Project players onto pitch coordinates
- Ball Trajectory - Track and clean ball path with outlier removal
- Performance Analytics - Heatmaps, stats, possession, and event detection
Upload a football match video to get comprehensive performance analytics!
Full video with player tracking, team colors, ball detection, and events overlay
Interactive charts comparing player performance metrics
Combined activity heatmaps showing team positioning
Top 6 players with detailed activity analysis
Game-style tactical view with ball trail
Per-player totals: distance, speeds, zones, possession
Detected passes, tackles, interceptions, shots, clearances
🔧 Technical Details:
Detection Models:
- Player/Ball/Referee Detection:
football-players-detection-3zvbc/11 - Field Keypoint Detection:
football-field-detection-f07vi/14
Tracking & Classification:
- ByteTrack for persistent player IDs
- SigLIP embeddings for team classification
- Majority voting for stable team assignments
Performance Metrics:
- Distance covered (meters)
- Average & maximum speed (km/h)
- Zone activity (defensive/middle/attacking thirds)
- Position heatmaps with Gaussian smoothing
- Possession per player & per team
Ball Tracking:
- Field homography transformation
- Outlier removal (500 cm threshold)
- Transformation matrix smoothing (5-frame window)
Events:
- Passes, tackles, interceptions, shots, clearances
- Event banner overlay in video
- Full event list downloadable as JSON