计算机科学 ›› 2018, Vol. 45 ›› Issue (2): 84-89.doi: 10.11896/j.issn.1002-137X.2018.02.014
• 2017年中国计算机学会人工智能会议 • 上一篇 下一篇
于晓,聂秀山,马林元,尹义龙
YU Xiao, NIE Xiu-shan, MA Lin-yuan and YIN Yi-long
摘要: 针对互联网相似视频内容检测问题,提出了基于短空时变化的鲁棒视频哈希算法。特征提取和特征量化是该算法的两个关键步骤。在特征提取中,与现有基于时空信息融合的特征提取方法相比,该算法的创新性在于充分利用相邻帧之间 局部空域信息的短时变化(简称“短空时变化”)来提取特征。该算法首先构造视频内接球,并以球心为起点对内接球进行划分,获取一系列内接球环,从而捕捉相邻帧的空域信息的短时变化,然后将球环非负矩阵分解系数作为视频内容进行特征表示;在特征量化中,该算法采用改进的曼哈顿量化策略将视频特征映射成二进制的哈希序列,更好地保留了原空间中的近邻关系,提高了量化的准确度。实验结果表明,该算法具有良好的性能。
[1] TAN H K,NGO C W,HONG R,et al.Scalable detection of partial near-duplicate videos by visual-temporal consistency[C]∥Proceedings of the 17th ACM International Conference on Multimedia.ACM,2009:145-154. [2] WU X,HAUPTMANN A G,NGO C W.Practical elimination ofnear-duplicates from web video search[C]∥Proceedings of the 15th ACM International Conference on Multimedia.ACM,2007:218-227. [3] CHERUBINI M,OLIVEIRA R D,OLIVER N.Understanding near-duplicate videos:a user-centric approach[C]∥Proceedings of the 17th ACM International Conference on Multimedia.ACM,2009:35-44. [4] HUANG Z,SHEN H T,SHAO J,et al.Practical online near-duplicate subsequence detection for continuous video streams[J].IEEE Transactions on Multimedia,2010,12(5):386-398. [5] SHEN H T,ZHOU X F,HUANG Z,et al.UQLIPS:a real-time near-duplicate video clip detection system[C]∥Proceedings of the 33rd International Conference on Very Large Data Bases.VLDB Endowment,2007:1374-1377. [6] WU X,HAUPTMANN A G,NGO C W.Practical elimination of near-duplicates from web video search[C]∥Proceedings of the 15th ACM International Conference on Multimedia.ACM,2007:218-227. [7] LIU J J,HUANG Z,CAI H Y,et al.Near-duplicate video retrieval[J].ACM Computing Surveys,2013,45(4):1-23. [8] KONG W H,LI W J,GUO M Y.Manhattan hashing for large-scale image retrieval[C]∥Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2012:45-54. [9] LEE S,YOO C D.Robust video fingerprinting for content-based video identification[J].IEEE Transactions on Circuits and Systems for Video Technology,2008,18(7):983-988. [10] ROOVER C D,VLEESCHOUWER C D,LEFèBVRE F,et al.Robust video hashing based on radial projections of key frames[J].IEEE Transactions on Signal Processing,2005,53(10):4020-4037. [11] LEE S,YOO C D.Video fingerprinting based on centroids ofgradient orientations[C]∥2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.IEEE,2006,2:II. [12] LEE S,YOO C D,KALKER T.Robust video fingerprintingbased on symmetric pairwise boosting[J].IEEE Transactions on Circuits and Systems for Video Technology,2009,19(9):1379-1388. [13] CHEN L,STENTIFORD F W M.Video sequence matchingbased on temporal ordinal measurement[J].Pattern Recognition Letters,2008,29(13):1824-1831. [14] COSKUN B,SANKUR B,MEMON N.Spatio-temporal transform based video hashing[J].IEEE Transactions on Multimedia,2006,8(6):1190-1208. [15] ESMAEILI M M,WARD R K.Robust video hashing based on temporally informative representative images[C]∥Proceedings of the 32nd International Conference on Coastal Engineering Consumer Electronics (ICCE 2010).Shanghai,China,2010:179-180. [16] ESMAEILI M M,FATOURECHI M,WARD R K.A robust and fast video copy detection system using content-based fingerprinting[J].IEEE Transactions on Information Forensics and Security,2011,6(1):213-226. [17] LI M,MONGA V.Robust video hashing via multilinear sub-space projections[J].IEEE Transactions on Image Processing,2012,21(10):4397-4409. [18] LI M,MONGA V.Twofold video hashing with automatic synchronization[J].IEEE Transactions on Information Forensics and Security,2015,10(8):1727-1738. [19] SONG J K,YANG Y,HUANG Z,et al.Effective multiple feature hashing for large-scale near-duplicate video retrieval[J].IEEE Transactions on Multimedia,2013,15(8):1997-2008. [20] LI W J,ZHOU Z H.Learning to hash for big data:current status and future trends[J].Chinese Science Bulletin,2015,60(5/6):485-490.(in Chinese) 李武军,周志华.大数据哈希学习:现状与趋势[J].科学通报,2015,60(5/6):485-490. [21] NIE X S,CHAI Y E,LIU J,et al.Spherical torus-based video hashing for near-duplicate video detection[J].Science China Information Sciences,2016,59(5):1-3. |
No related articles found! |
|