Segmentation of Football Video Broadcast

In this paper a novel segmentation system for football player detection in broadcasted video is presented. 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, player detection system based on the combination of Histogram of Oriented Gradients (HOG) descriptors with Principal Component Analysis (PCA) and linear Support Vector Machine (SVM) classification. For the shot classification the several classification technique SVM, artificial neural network and Linear Discriminant Analysis (LDA) are used. Evaluation of the system is carried out using 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. Experimental results presented in this paper show that combination of these techniques seems to be a promising solution for locating and segmenting objects in a broadcasted video.