Scene structure analysis for sprint sports

Abstract

This work proposes a robust model to analyse the structure of horse races based on 2D velocity vector information. This model is capable of detecting scene breaks, classifying the view of the contenders and extracting the trajectory of the contenders throughout the race. The performance of the system is tested over six video clips from two different broadcast sources. The performance analysis shows the model achieves a high accuracy of view classification with the lowest value of 83%, all in real time.

Tracking Jockeys in a Cluttered Environment with Group Dynamics

“…To have a fully automated system, first, we need to extract the frame sequences around the turning points (turning segment), then detect jockeys at each segment and finally track and extract their trajectory. The approach for extracting turning segments is reported in our earlier work [15]. The detection of jockeys is accomplished by locating of the jockey's cap with using well-known histogram of gradient (HOG) object detection framework [6].…”