摘要
视频时域分割指将视频序列分成若干镜头 ,是视频内容分析以及基于内容的视频浏览和检索的第一步 .该文首先对视频结构以及视频镜头种类进行了简要的描述 ,然后对为计算不连续性而采用的提取特征和建立测量准则的常用方法进行概述 .其后 ,文章介绍了检测镜头切变和渐变的算法及其优缺点 .在压缩域上检测镜头变换边界的问题也在文中予以分析 .在结论与展望中 ,提出了一些这一领域的难点和对今后工作的展望 .
Video temporal segmentation denotes partitioning a video sequence into shots which is the first step toward video content analysis and content-based video browsing and retrieval. A video shot is defined as a series of inter-related consecutive frames taken contiguously by a single camera. Video shots are also considered to be the primitives for higher level content analysis, indexing, and classification. Starting from a brief description of the structure of video and the classification of video shots, the paper generalize the common methods to extract features and build metrics for computing the discontinuity values. The characteristics of the features are presented in details and compared with each other. Afterwards the paper reviews the algorithms for detecting the cut and gradual shot changes and their advantages and drawbacks. The approaches to determine the adaptive threshold and the statistical methods are described respectively and a newly proposed inertia-based cut detection algorithm is also introduced here. Then the problems of finding shot boundaries in compressed domain are analyzed which include how to make use of the information of compressed video and how to eliminate the influences of sensitive factors.
出处
《计算机学报》
EI
CSCD
北大核心
2004年第8期1027-1035,共9页
Chinese Journal of Computers
基金
国家自然科学基金 ( 60 0 72 0 0 9)资助
关键词
视频时域分割
切变
渐变
特征提取
压缩域
Algorithms
Edge detection
Feature extraction
Image segmentation
Information analysis
Statistical methods
