Shot view classification for playfield-based sports video

摘要

In this paper, we propose a technique for classifying shots of playfield-based sports video into their respective view classes. Based on common broadcasting style, a shot can be classified as a far-view or a closeup-view. The technique considers the frame-wise color values of each pixel in the HSV color space, while at the same time calculating the assumed object size within the segmented playfield region. Based on our experiments, it is shown that this technique can greatly reduce the number of misclassified shots, while at the same time maintain a good level of accuracy. At the moment, we have tested our approach on soccer videos but believe that it can be applied to other playfield-based sports as well.