摘要
电子设备的普及,使得在互联网上每天有以数以百计的视频被创造出来。同时,盗版视频也在成倍的出现,这极大地侵害了版权所有者的利益了,并对视频用户的搜索结果造成影响。在这样的背景下,视频拷贝检测技术成为热点。
基于内容的视频拷贝检测是水印技术的有效补充,其基本思想是认为视频自身包含了足够多的能够用于检测拷贝的信息。通过测量从查询视频和测试视频中提取的能唯一标识视频内容的特征序列之间的距离来判断测试视频是否是查询视频的拷贝。它主要包含了镜头分割、关键帧检测、视频特征提取、特征值距离测量四部分内容。
本论文对镜头分割技术和关键帧特征提取技术进行了深入研究,对基于主颜色直方图的图像特征提取方法进行了改进,提出了一种新的HSV空间的分块主颜色直方图特征值的提取方法。在镜头边界检测中,使用新提出的方法作为镜头分割的主特征值,并结合帧图像主颜色像素比率改善算法结果;视频关键帧序列相似度检测采用和镜头分割相同的主特征值,而使用基于Canny算子的边缘特征值作为辅助特征,以提高准确性。最后,通过实验表明,使用本文提出的特征值提取方法能很好检测出同一内容的视频在不同分辨率和不同格式情况下的拷贝。
With the popular of electronic equipment, there are hundreds of videos and video copies are created in one day. These copies affect the video search result and against the interest of copyright holder. Video Copy Detection aims to find the copies.
The most popular technology in Video Copy Detection is Watermarking, and Content-based Video Copy Detection is a complementary approach to watermarking for detecting copies of media. The primary thesis of Content-based Copy Detection(CBCD) is "the media itself is the watermark", the media contains enough unique information that can be used for detecting copies. CBCD schemes measure the distance between signatures extracted from the original media and a possible copy, which contains shot boundary detection, key frames detection, video signatures extraction and distance measure.
A novel content-based video copy detection method was proposed. At first, this paper improves the domain color histogram in HSV space, and detects the shot boundary with the number of domain color pixels. Then use the same way to extract the character of sequence of key frames to detect the video copies, with the image boundary signature base on Canny detector. The result show the method can detect the video copies in different resolution and different format.
引文
[1]Cheung,SC.,Zakhor,A.Estimation of Web Video Multiplicity[J].In Proceedings of the SPIE -- Internet Imaging,pages 33-36,San Jose,California.January 2000.
[2]田乐、李宁.一种基于数字水印的媒体自动识别技术[J].计算机应用,2007年,27(10).
[3]Hsiao,Jen-Hao.2004 Digital Watermark Competition:The Technical Report,Technical Report,IIS Academia Sinica,2004 April.
[4]A.Hampapur and R.M.Bolle.Videogrep.Video copy detection using inverted file indices.Technical report,IBM research division,2002.
[5]E.Chang,J.Wang,C.Li and G.Wiederhold,RIME.A replicated image detector for the World Wide Web In PIE Multimedia Storage and Archiving Systems Ⅲ,Nov.1998.
[6]靳延安 基于内容的视频拷贝检测[J].计算机应用,2008年,28(8).
[7]A.Hampapur and R.M.Bolle.Comparison of Distance Measures for Video Copy Detection[C].In ICME 2001.
[8]R.Lienhart,C.Kuhmunch and W.Eelsberg.On the detection and recognition of television commercials[C].In Proc.of the IEEE Conf.on Multimedia Computing and Systems,1997.
[9]P.Indyk,G.Iyengar and N.Shivakumar.Finding pirated video sequences on the Internet.tech.rep.,Stanford Infolab,Feb.1999.
[10]J.M.Sanchez and X.Binefa.Color normalization for appearance based recognition of video key-frames[J].In Proc.of Int.Conf.on Pattern Recognition,Vol.Ⅰ,Aug.2000,pp.815-818.
[11]LIU Lu,LAI WEI,HUA XIAN-SHENG,et al.Video histogram:a novel video signatures for efficient Web video duplicate detection[C]Proceedings of 13~(th) International Multimedia Modeling Conference(MMM2007).Singapore:Springer,2006:94-103.
[12]S.O.Belkasim,M.Shridhar,andM.Ahmadi.Pattern Recognition with Moment Invariants:A comparative study and new results[J].In Pattern Recognition,Vol 24,No 12,1991.
[13]D.P.Huttenlocher,G.A.Klanderman and WJ.Rucklidge.Comparing images using the Hausdorff distance[J].IEEE Trans.on PAMI,Vol.15,No.9,Sept.1993.
[14]NAPHADE M,YEUNG M,YEO B.A novel scheme for fast and efficient video sequence matching using compact signatures[EB/OL].
[15]菅云峰、胡勇、李介谷.基于Hausdorff距离的图像匹配技术[J].红外线激光工程,1998年,27(4).
[16]N.K.Hu.Visual pattern recognition by moment invariance.IRE[J].Transactions on Information Theory,1962,pp.179-187.
[17]章毓晋.图像工程(第2版)[M].北京:清华大学出版社,2007.5
[18]Rafael C.Gonzalez,Richard E.Woods.Digital Image Processing Second Edition[M].阮秋琦、阮宇智.北京:电子工业出版社,2007年.
[19]Cull P,Larson S M.The Mobius cubes[C].IEEE Transactions on Computers,1995,44(5):647-659.
[20]卢汉清、孔维新..基于内容的视频信号与图像库检索中的图像技术[J].自动化学报,2001年,27(1):4-69.
[21]Naphad M,Mehrotra R.A high performance algorithm for shot boundary detection using multiple cues[C].In Proceedings of 1998 International Conference on Image Processing 1998.3-10
[22]朱兴全、薛向阳、吴立德.一种自动门限选取的视频Shot分割方法[J].计算机研究与发展,2000年,37(1):80-85.
[23]钱刚、曾贵华.典型视频镜头分割方法的比较[J].计算机工程与应用.2004,(32).
[24]M Yeung,B L Yeo,W Wolf et al.Video browsing using clustering and scene transitions on compressed sequences[C].IS&T/SPIE Multimedia Computing and Networking,1995:399-413
[25]Tonomura Y,Abe S.Content oriented visual interface using video icons for visual database systems[J].Journal of Visual Languages and Computing 1990:1(2):183-198.
[26]A Nagasaka,Y Tanaka.Automatic video indexing and full-motion search for object appearances[C].In:Proc IFIP TC2/WG2.6 Second Working Conf on Visual Database Syst,1991:112-127.
[27]F Arman,A Hsu,M Y Chiu.Image processing on compressed data for large video databases[C].In:SPIE Proc storage and Retrieval for Image and Video Databases,1993:267-272
[28]孙利涛,杨雷.视频镜头分割技术综述[J].山东轻工业学院学报(自然科学版),2007年.
[29]J Lee,Dickinson BW.Multiresolution.Video indexing for sub-band coded video databases.In:Proceedings of the SPIE Conference on Image and Video Processing Ⅱ.1994.162-173.
[30]B L Yeo,B Liu,A unified approach to temporal segmentation of motion JPEG and MPEG compressed videos[C].In:Proc of the International Conference of Multimedia Computing and Systems,1995:82-88.
[31]Zhang Y J,Lu H B.Hierarchical.Video organization based on compact representation of video units[C].Proc.Workshop on Very Low Bitrate Video 1999,67-70.1999.
[32]W Wolf.Key frame selection by motion analysis[C].In:Proc IEEE Int.Conf.Acoust.,Speech and Signal Proc,1996.
[33]陆其明.DirectShow开发指南[M].北京:清华大学出版社,2005.
[34]youken,http://www.vckbase.net/document/viewdoc/?id=976 VCKBASE.com Online Journal 第27期
[35]胡学龙,许开宇.数字图像处理[M].北京:电子工业出版社,2007.6 161-162.
[36]FERMAN A M,TEKALP AM.A fuzzy framework for unsupervised video content characterization and shot classification[J].Journal of Electronic imaging,2001,10(4):917-929.
[37]于俊清、周洞汝、刘军、蔡波.基于文字和图像信息提取视频关键帧.计算机工程与应用.2002,(09):83-85
[38]潘磊、吴小俊、尤媛媛.基于聚类的视频镜头分割和关键帧提取.红外与激光工程.2005,34(3):341-344
[39]Zhao L,Qi W.,Li S.Z.,Yang S.Q.,and Zhang H.J.,Key-frame extraction and shot retrieval using Nearest Feature Line(NFL),International Workshop on Multimedia Information Retrieval,n conjunction with ACM Multimedia Conference 2000,LosAngeles,USA,2000.
[40]戴锋.Visual C++程序设计基础[M].清华大学出版社.2001.4.
[41]KIM C,VASUDEV B.Spatiotemporal sequence matching for efficient video copy detection [J].IEEE Transactions on Circuits and Systems for Video Technology,2005,15(1):127-132.
[42]CHEUNG S C S,ZAKHOR A.Efficient video similarity measurement with video signature [C].IEEE Transactions on Circuits and Systems for Video Technology,2003,13(1):59-73.
[43]CHEUNG S C S,ZAKHOR A.Fast similarity search and clustering of video sequences on the World Wide Web[C].IEEE Transactions on Multimedia,2005,7(3):523-537.
[44]朱映映、周洞汝.一种从压缩视频流中提取关键帧的方法[J].计算机工程与应用.2003.
[45]Hanjalic A,Zhang HongJiang.An integrated scheme for automated video abstraction based on unsupervised cluster-validity analysis[C].IEEE Transactions on Circuits and Systems for Video Technology.Dec.1999,9(8):1280-1289
[46]Yueting Zhang,Yong Rui et al.Adaptive Key Frame Extraction using unsupervised clustering [C].Proceedings of International Conference on image processing,1998.10.3-7:886-870