News sports video shot classification with sports play field and motion features

Abstract

In this paper a novel sports news video shot classification method has been proposed. First two features based on motion and color are constructed and extracted from video shots: play field color ratio for specific types of sports, background motion and consistency ratio, then they are combined to generate an 11-dimension shot feature to feed into a C4.5 decision tree for shot classification. Based on our video data sets - the sports news video from the CNN Headline News video used in the TRECVID 2003, 7 predefined video shot classes were defined: 4 types of sports field video (basketball, baseball, ice hockey and golf), and sports news lead-in/lead-out, text, and others. Sports news video segments from 15 half-hour CNN News video were used for the training and testing. A performance of average precision and recall 88%, 82% has been achieved, respectively. The proposed method can be further developed and used to search news video for individual sports news and sports highlights. ©2004 IEEE.