摘要
镜头切换检测是视频检索研究领域中一项基本的、重要的技术,对于数字视频镜头突变切换的检测,一般有模板匹配法、直方图法等基本算法,但这些算法在实际检测中通常达不到较高的检测精度。因此,提出了一种特征融合的镜头边界检测方法。HSV色彩直方图进行镜头边界检测是一种常用、有效的方法,该文通过小波变换得到视频帧的纹理特征,并将其与色彩直方图特征相融合,采用滑动窗口技术对视频镜头进行检测。实验表明,该方法能够有效地检测镜头突变,对镜头的渐变也能有较好地检测。
The shot change detection is a basic and important technology in video retrieval. There are some basic algorithms for detecting abrupt shot change in digital video, including the template-matching algorithm, the histogram algorithm, etc. , but they cannot always attain high precision in practical detecting. Hence, an approach of shot-boundary detection by fusing feature was proposed. HSV histogram is a common and effective method for shot boundary detection. In this paper, texture analysis was obtained by wavelet transformation and then was integrated with the HSV histogram. Finally, the shots were detected by the technology of a sliding window. Experimental result shows that this proposed approach can detect abrupt shot effectively and has a satisfied result in gradual shot transition detection
出处
《重庆邮电大学学报（自然科学版）》
北大核心
2009年第1期100-104,共5页
Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)
基金
重庆市自然科学基金(CSTC
20072386)
重庆市教委应用基础研究项目(KJ070504)
关键词
镜头边界检测
小波变换
特征融合
突变
渐变
shot boundary detection
wavelet transform
feature fusion
hard cut
gradual transition
