Real-Time sports analysis with AI on the edge
Real-Time sports analysis with AI on the edge
About the service
A client in the sports technology sector, operating across football, rugby, and hockey, required a real-time sports video analysis solution capable of running multiple AI models in parallel for tasks such as object detection, player tracking, and camera calibration. The system needed to deliver high-performance processing and improved accuracy while maintaining low latency.
What We Achieved
A complete sports video analysis application was developed, integrating multiple AI models and functionalities across various domains, including object detection, multi-object tracking, and camera calibration. Model accuracy was improved through synthetic data generation, enabling robust performance in a wide range of sports scenarios.
The system featured a hardware-accelerated graphics environment tailored to the customer’s requirements, along with a custom, high-performance video player capable of reproducing synthetic video streams. All AI models were optimized for real-time execution on edge devices, providing a responsive and field-ready sports technology solution.
