Computer Vision · Builder
FIFA Soccer DS.
Production-shaped computer-vision pipeline for soccer video: YOLOv8n detection, ByteTrack tracking, and a GraphSAGE tactical-graph scaffold, served via FastAPI with MLflow + DVC.
- Role
- Builder
- When
- 2024
- Stack
- Python, YOLOv8, ByteTrack, PyTorch Geometric
- Scale
- 22 FPS real-time inference
YOLOv8 + ByteTrack22 FPSreal-time inference
3-stagedetect to track to graph
max_age 20occlusion recovery
ONNX + TRTexport targets
The problem
Take raw soccer video (YouTube highlights, FIFA gameplay, or a live RTSP stream) and turn it into tracked players and tactical interaction graphs, wrapped in real MLOps for experiment tracking, data versioning, and deployment.
What it does
- Modular detect to track to graph pipeline: YOLOv8n detection, ByteTrack persistence with Kalman filtering, and a spatial-temporal graph built from tracklets.
- FastAPI service plus a live RTSP path, with ONNX and TensorRT export for deployment.
- MLflow experiment tracking and a DVC-versioned pipeline so runs are reproducible end to end.
Impact
- Detection and tracking run on real La Liga footage at 22 FPS on an RTX 3070-class 8GB GPU.
- GraphSAGE role classifier is scaffolded and inference-wired (trained weights pending), feeding off the tracklet graph.
- Each stage logs to MLflow and runs standalone or as one unified pipeline; Dockerized.