一种快速的压缩域视频流场景分段算法

A Fast Algorithm for MPEG Compressed Video Segmentation Based on Scene Change

提出了一种快速的压缩域视频流场景分段算法,对视频流进行两次分析:第一次分析(粗略分析)只分析帧中宏块统计信息,检P-测出可能存在的镜头边界;第二次分析(精确分析)再对粗略分析找出的边界邻近的帧和帧的宏块类型进行分析,从而对场景变换进行B-P-精确分析和定位。实验结果表明,粗略分析可以满足实时检测的速度要求,帧定位误差控制在帧之内,精确分析可以进一步把帧定位误差10控制在帧之内。

This paper presents a fast algorithm for MPEG compressed video segmentation based on scene change. A rough scan over the P frames locates the potential scene change boundaries and the solution is then refined by a precise scan over the B frames of the respective neighborhoods. The advantages of this algorithm are its direct extraction from the MPEG bitstreams after VLC decoding, rule-based detection, frame-based detection accuracy and high detecting speed. ;;