A complex system for football player detection in broadcasted video

In this paper a novel segmentation system for football player detection in broadcasted video is presented. The system is based on the combination of Histogram of Oriented Gradients (HOG) descriptors and linear Support Vector Machine (SVM) classification. Although recently HOG-based methods were successfully used for pedestrian detection, experimental results presented in this paper show that combination of HOG and SVM seems to be a promising technique for locating and segmenting players in broadcasted video. Proposed detection system is a complex solution incorporating a dominant color based segmentation technique of a football playfield, a 3D playfield modeling algorithm based on Hough transform and a dedicated algorithm for player tracking. Evaluation of the system is carried out using SD (720×576) and HD (1280×720) resolution test material. Additionally, performance of the proposed system is tested with different lighting conditions (including non-uniform pith lightning and multiple player shadows) and various camera positions.