Towards AI Enabled Automated Tracking Of Multiple Boxers
In this work, we introduce a vision-based system that relies on economic video capture system (single fixed viewpoint). Specifically, we propose modified algorithms for automatic transition detection system and person re-identification systems that shows significant improvements over state-of-the-art techniques.
Towards AI Enabled Automated Tracking Of Multiple Boxers
Photo: Multiple Boxers
Towards AI Enabled Automated Tracking Of Multiple Boxers
Photo: Multiple Boxers
-
Previous Story
Olympic Weightlifters’ Performance Assessment Module Using Computer Vision -
Next Story
Punch Types And Range Estimation In Boxing Bouts Using IMU Sensors
