Up to now, more and more video materials are stored and transmitted in the compression form, so it is practical to study the shot segmentation algorithms based on compressed video data.
从实用角度看，目前越来越多的动态视频资料都是以压缩形式存储和传输，所以，研究基于压缩视频流的算法更有实际意义。
The framework of video abstraction system in compressed domain is described, and main algorithms such as shot change detection, key-frame extraction and face detection are discussed.
给出了压缩域视频摘要系统的结构框架，并对其中的压缩域视频镜头变换检测、关键帧提取和压缩域人脸检测等主要算法进行了讨论。
With all three algorithms in effect, a 1-gb video file can be compressed to just 25 MB, without destroying any of the original video information.
三种算法都生效的情况下，一个1 - GB的视频文件可以被压缩到只有25 MB，并且不会破坏任何原始视频信息。
应用推荐