基于小波变换及熵的视频镜头分割检测方法

戴小文; 蔡志平; 钟桂英

基于小波变换及熵的视频镜头分割检测方法

基金项目:

信息产业部电子发展基金资助项目((2005)No.555)

详细信息

作者简介:
戴小文(1967- ),男,副教授,博士,研究方向为模式识别,E-mail:xwdai678@yahoo.com.cn

计量
- 文章访问数: 1685
- HTML全文浏览量: 76
- PDF下载量: 473
- 被引次数: 0
出版历程
- 收稿日期: 2007-09-05
- 刊出日期: 2008-06-25

Video Shot Detection Method Based on Wavelet Transform and Wavelet Entropy

摘要

摘要: 提出了基于小波变换及熵的视频镜头分割检测方法.用图像低频信号的小波系数的均值和标准差检测剪切镜头转换边界.分别计算图像小波分解后水平、垂直和对角方向细节信号的小波熵分量,以此3个小波熵分量作为特征量,计算相邻视频帧间特征量的欧氏距离.在检测窗内欧氏距离两次以上大于设定的阈值时即可判定镜头发生渐变转换.实验结果表明,剪切镜头查准率为95%,查全率为96%;渐变镜头查准率为87.5%,查全率83.8%.
- 视频镜头 /
- 检测 /
- 小波变换 /
- 小波熵 /
- 直方图
Abstract: A detection method for video shot transitions based on wavelet transform and wavelet entropy was presented.The mean and standard deviation of the low frequency components of an image is used to detect cut transitions.To detect gradual transitions,the wavelet entropies of the image in horizontal,vertical and diagonal directions are used as characteristic values,and these values are taken as inputs to calculate the Euclidean distances between neighboring images.A gradual transition is determined if at least two Euclidean distances are larger than a preset threshold in the detection window.Experiment results indicate that using the proposed method the ratio of correct detection is 95% and the detected ratio is 96% respectively for cut transitions,and 87.5% and 83.8% respectively for gradual transitions.
- video shot /
- detection /
- wavelet transform /
- wavelet entropy /
- histogram

HTML全文

参考文献(1)

COTSACES C,NIKOLAIDIS N,PLTAS L.Video shot detection and condensed representation[J].IEEE Signal Processing Magazine,2006,23 (2):28-37.[2] LIENHART R.Reliable transition detection in videos:a survey and pratitioner's guide[J].International Journal of Image Graphics,2001,1(3):469-486.[3] HEATHERYU H.A hierarchical multiresolution video shot transition detection scheme[J].Computer Vision and Image Understanding,1999,75(1/2):196-213.[4] HANJALIC A.Shot-boundary detection:unraveled and resolved[J].IEEE Trans.on Circuits Systems for Video Technology,2002,12(2):90-105.[5] CERNEKOVA Z,PITAS I,NIKOU C.Information theory-based shot cut/fade detection and video summarization[J].IEEE Trans.on Circuits and Systems for Video Technology,2006,16(1):82-91.[6] BOCCIGNONE G,CHIANESE A,MOSCATO V,et al.Foveated shot detection for video segmentation[J].IEEE Trans.on Circuits and Systems for Video Technology,2005,15(3):365-377.[7] LELESCU D,SCHONFELD D.Statistical sequential analysis for real-time video scene change detection on compressed multimedia bitstream[J].IEEE Trans.on Multimedia,2003,5 (1):106-117.[8] 耿玉亮,须德.视频镜头边界检测的统一策略[J].中国图象图形学报,2005,10(5):650-655.GENG YUliang,XU De.A unified framework for shot boundary detection[J].Journal of Image and Graphics,2005,10(5):650-655.[9] 韩冰,高新波,姬红兵.基于模糊粗糙集的新闻视频镜头边界检测方法[J].电子学报,2006,34(6):1 085-1 089.HAN Bing,GAO Xinbo,JI Hongbing.A shot boundary detection method for news video based on rough fuzzy sets[J].Acta Electronica Sinica,2006,34(6):1 085-1 089.[10] BLANCO S,FIGLIOSA A,QUIAN Q R,et al.Time-frequency analysis of electroencephalogram series(Ⅲ):information transfer function and wavelets packets[J].Physical Review E,1998,57(1):930-940.[11] DAUBECHIES I.Ten lectures on wavelets[M].2nd ed.Philadelphia:SIAM,1992.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 1685
HTML全文浏览量: 76
PDF下载量: 473
被引次数: 0

基于小波变换及熵的视频镜头分割检测方法

作者简介: 戴小文(1967- ),男,副教授,博士,研究方向为模式识别,E-mail:xwdai678@yahoo.com.cn

计量

出版历程

Video Shot Detection Method Based on Wavelet Transform and Wavelet Entropy

计量

出版历程

目录

作者简介:
戴小文(1967- ),男,副教授,博士,研究方向为模式识别,E-mail:xwdai678@yahoo.com.cn