基于H．264／AVC压缩域的实时视频镜头分割算法

Scene Change Detection Algorithms in H.264/AVC Compressed Domain

随着H．264／AVC压缩标准得到越来越广泛的应用，基于H．264／AVC压缩域的视频镜头分割技术成为视频检索领域的热点问题。根据镜头边缘处前后帧的相关性较低的特征，统计帧在总体上的宏蚺预测模式信息来获取视频的候选镜头边界集．然后利用局部特性对其进行筛选，得出了镜头边界，并通过实验进行验证，实验结果表明，本算法是快速有效的。

Along with widely using of H.264/AVC, the scene change detection in H.264/AVC compressed domain becomes a hot issue in Context-Based Video Retrieval field. Base on the character that there is less temporal correlation between frame＇ where scene change occurs, according to different macro-block prediction mode in the whole frame, the proposed algorithms obtain candidates of scene change frames. To find accurate scene changes, we use the part characteristic of the fame. The experimental results shows that the proposal algorithm is fast and efficient.