Back to the work
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
FIFA Soccer DS previewYOLOv8 + ByteTrack
22 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

  1. Modular detect to track to graph pipeline: YOLOv8n detection, ByteTrack persistence with Kalman filtering, and a spatial-temporal graph built from tracklets.
  2. FastAPI service plus a live RTSP path, with ONNX and TensorRT export for deployment.
  3. 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.