基于视频区域特征及HMM的体育视频分类研究  

Video Classification Based on Region Features and HMM

作　　者：宋刚[1] 肖国强[1] 代毅[1] 李占闯[1] 

机构地区：[1]西南大学计算机与信息科学学院,重庆400715

出　　处：《西南师范大学学报（自然科学版）》2010年第2期180-184,共5页Journal of Southwest China Normal University(Natural Science Edition)

基　　金：重庆市科委自然科学基金资助项目(CSTC2008BB2252)

摘　　要：提出了一种基于视频区域特征的体育视频分类方法.首先将帧分块,对块亮度均值大小进行比较得到块亮度比较编码信息BICC,以及对视频帧各块的颜色分量进行统计得到块颜色直方图;再利用这些特征通过SVM对体育视频进行分类;最后利用一阶HMM对SVM的输出结果进行后处理,得到视频的最终分类结果.实验结果表明,方法对于体育视频分类的效果较好.Considering that the average intensity and color are different in regions of video frame, the authors propose a video classification method based on region features. First, divide the frame into blocks, then according to comparison of the average intensity among different blocks to get the feature block intensity comparison code （BICC）, and get the block color histogram through the statistics of color components in each blocks of frame. Then the authors classify the video frames using SVM with extracted features. Finally, a hidden Markov model is employed to process the data getting from SVM to enhance the performance of video classification. The experimental results show that the approach proposed in the paper outperforms other methods based on features such as only BICC, edge and Mathematical Morphology.

关 键 词：块亮度比较编码 块区域颜色直方图 支持向量机 隐马尔可夫模型 

分 类 号：TN911.73[电子电信—通信与信息系统]