Title :
News sports video shot classification with sports play field and motion features
Author :
Wang, De-Hong ; Tian, Qi ; Gao, Sheng ; Sung, Wing-Kin
Author_Institution :
Inst. for Infocomm Res., Singapore, Singapore
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.
Keywords :
decision trees; feature extraction; image classification; image colour analysis; image motion analysis; image segmentation; sport; video signal processing; 11-dimension shot feature; C4.5 decision tree; CNN headline news; TRECVID; consistency ratio; motion feature; motion-color construction; motion-color extraction; play field color ratio; sports video shot classification; video data set; video segment; Cameras; Cellular neural networks; Classification tree analysis; Computer science; Data mining; Decision trees; Histograms; Ice; Indexing; Testing;
Conference_Titel :
Image Processing, 2004. ICIP '04. 2004 International Conference on
Print_ISBN :
0-7803-8554-3
DOI :
10.1109/ICIP.2004.1421545
