Player classification algorithm based on digraph in soccer video

Player classification method based on the tradition histograms lacks color spatial information, which leads to low classification performance, and, in addition, it needs priori template information. According to this, a novel player classification algorithm based on digraph was proposed in this paper. Firstly, the candidate players were extracted through the main color under the HSV Model Space of Color and equal-area rectangle partitioning strategy was adopted to partition the image. Secondly, HSV color space was quantified in each block and color histogram was extracted as color features. Thirdly, the distance among images was calculated according to the color features and the digraph was generated based on the distance matrix. Finally, the player classification was implemented by classifying the vertexes of digraph. Experimental results show that the proposed method, without priori template information, is an effective way of classifying the players positioned around the classification boundary with an average classification accuracy of 98.82%. Compared with traditional method, the proposed method has a remarkable promotion on classification effect.