一种基于宏块信息的快速MPEG视频分割算法

Fast MPEG video segmentation algorithm based on macroblock

提出了一种基于宏块信息的快速MPEG压缩视频场景分割算法。该算法只需要通过直接抽取MPEG视频流中的B帧、P帧中的宏块类型信息,并对其进行计算就可以检测出视频中存在的镜头边界,从而对场景变换进行精确定位。这种方法无需对压缩视频进行解压,所以能够满足实时检测的速度要求。经过选用多个MPEG压缩视频进行实验分析证明,此方法能够精确有效地检测出视频流中存在的镜头边界。

A fast algorithm for MPEG video segmentation based on macroblock （MB） types was presented. The proposed method can detect scene boundaries through using various macroblock type of B-frame and P-frame in MPEG video flow in order to realize accurate scene change positioning. Those information can be extracted from the encoded bit-stream without decompression so that it can satisfies high speed detection requirement. Simulation results on different sequences show that the proposed algorithm is effective and accurate for the scene change boundaries detection in NPEG video.