基于码流分析和边缘检测的视频镜头分割算法

A Video Shot Segmentation Algorithm Based on Video Stream Analysis and Edge Detection

针对视频镜头的快速有效分割问题,提出一种结合视频帧码流分析与边缘检测的镜头分割算法。算法首先提取并分析视频码流中的每个宏块编码类型和运动向量信息,根据码流分析结果确定部分镜头切换帧及候选镜头切换帧,然后对候选切换帧再进行边缘检测,分析边缘纹理特征,排除非镜头切换帧,保留镜头切换帧。试验结果表明,算法对不同类型视频的镜头突变和渐变检测都有较好的效果。

To segment video shot quickly and efficiently, a video shot segmentation algorithm which combine frame stream analysis with edge detection was proposed in this paper. Firstly, the coding type and motion vector of each macrobolck were extracted and analyzed to determine a portion of shot boundary frames and candidate shot boundary frames; Secondly, the edge texture features of candidate frames was detected to exclude non - shot boundary frame and retain shot boundary frames. The experiments indicate that this algorithm performs well on both abrupt and gradual shot boundary.