基于行列块编码的视频查询方法

A New Video Inquiry Technology Based on Row-column Coding

基于内容的视频分析方法是多媒体检索领域内最近兴起的研究课题 ,多数研究集中在视频序列结构化、索引、识别和浏览等技术上 ,而对用户常用的视频查询却研究较少 .为此讨论了基于“窗口对”查询方法存在的不足 ,并根据视频编码制式的特点、视频本身特性和常用的视频分析方法 ,提出了一种可处理多种视频格式的方法 .该法基于视频帧行列块编码 ,采用了一种逐帧匹配的流式查询方法 .该方法可用少量的字节来表征视频帧的颜色和位置信息 ,其占用内存少 ,简单易得 ,计算量小 ,而且对于移位和亮度的变化均不敏感 ,使得查全率和准确率大为提高 。

The technology of content based video analysis is a new research task in the multimedia retrieval field, but the most research is centralized in structurizing video sequence, indexing recognizing and browsing,and video inquiry is seldom focused. This paper analyses the shortcoming of the 'window pairs' technology proposed by Nevenka. The way of selecting window pairs is arbitrary in that method, so it is inappropriate sometimes. This paper suggests a new method about row and column coding based on the video coding characteristics, video peculiarities and normal technology of video analysis. The character this method used describes the color and position information of video frame. Most video about different formats could be processed using the frame by frame matching and streaming inquiry technology by this method. This method needs a few bytes to figure a picture, occupying fewer memory, and using less computing. The experiment improved that this technology is robust to frame shift and luminance variable, achieved better experiment results that the Recall and Precision are highly improved.