A framework for vision-based swimmer tracking

Abstract

Swimmer tracking in swimming pools is a challenging vision task due to its varying complex background. Most moving object detection methods are developed for static or partial static backgrounds, and thus can not be applied in swimmer detection problems. This work presents an approach combining mean-shift clustering and cascaded boosting learning algorithm for swimmer detection. There are three main steps in the proposed framework: background modeling, swimmer detection, and swimmer tracking. A recorded image sequences from a practical indoor swimming pool was used to verify the proposed approach. Experimental results showed that the proposed approach is feasible and able to detect the swimmers in complex backgrounds.