Real-Time Football Match Perception System

Overview

Led the end-to-end development of a real-time computer vision system for football match analytics, combining OCR, object detection, tracking, classification, and classical CV techniques into a unified production pipeline.

Achievements

• Built a low-latency multi-module perception system operating in real time • Successfully combined deep learning and classical CV methods in a single pipeline • Reduced processing delay while maintaining high detection accuracy • Enabled automated extraction of structured match data from live video streams

Responsibilities

• Developed object detection and player tracking models
• Implemented OCR for scoreboard and broadcast overlays
• Designed a modular perception architecture for real-time inference
• Built and maintained the data labeling and validation pipeline
• Optimized system performance for stable real-time execution