Abstract：To implement the fast retrieval for compressed video data, a retrieval method based on the fluctuation of frame data counts is proposed. The data counts for each frame in compress domain are calculated to acquire the data counts curves of equal-length query segment and target video. Then, the query segment is slided on the target video after the alignment of frame data I, and the length of sliding window is the same as the length of a group of picture. The differences of data counts fluctuation between the query clip and the target video are measured. Finally, the similarity result is given according to the designated threshold. The extraction of high dimension feature vector for each frame is omitted in the proposed method, and a video clip is represented by a single vector instead of an array of high dimension vectors. The experimental results show that the video retrieval is speeded based on the proposed method. Meanwhile, a high accuracy is achieved. Therefore, the method can be used for fast retrieval on compressed video database and online video segment matching to find the target video.
高毫林，李弼程，张白愚. 基于帧数据量波动特性的压缩域视频快速检索方法[J]. 模式识别与人工智能, 2012, 25(3): 506-512.
GAO Hao-Lin, LI Bi-Cheng, ZHANG Bai-Yu. A Fast Compressed Video Retrieval Method Based on Fluctuation of Frame Data Counts. , 2012, 25(3): 506-512.
[1] Liu Z,Liu T,Gibbon D,et al.Effective and Scalable Video Copy Detection // Proc of the ACM SIGMM International Conference on Multimedia Information Retrieval.New York,USA,2010: 119-128 [2] Law-To J.Video Copy Detection: A Comparative Study // Proc of the ACM International Conference on Image and Video Retrieval.Amsterdam,Netherlands,2007: 371-378 [3] Douze M,Gaidon A,Jegou H.INRIA-LEARs Video Copy Detection System // Proc of the TREC Video Retrieval Evaluation Workshop.Gaithersburg,USA,2008: 1-8 [4] Hua Xiansheng,Chen Xian,Zhang Hongjiang.Robust Video Signature Based on Ordinal Measure // Proc of the IEEE International Conference on Image Processing.Singapore,Singapore,2004,I: 685-688 [5] Naturel X,Naturel P A.Fast Shot Matching Strategy for Detecting Duplicate Sequences in a Television Stream // Proc of the 2nd International Workshop on Computer Vision Meets Databases.Baltimore,USA,2005: 21-27 [6] Hampapur A,Hyun K H,Bolle R M.Comparison of Sequence Matching Techniques for Video Copy Detection // Proc of the SPIE Conference on Storage and Retrieval for Media Databases.San Jose,USA,2002: 194-201 [7] Jiang Y G,Ngo C.Visual Word Proximity and Linguistics for Semantic Video Indexing and Near-Duplicate Retrieval.Computer Vision and Image Understanding,2009,11(3): 405-414 [8] Tan H K,Ngo C,Hong R,et al.Scalable Detection of Partial Near-Duplicate Videos by Visual-Temporal Consistency // Proc of the ACM International Conference on Multimedia.Queensland,Australia,2009: 87-95 [9] Accustream Research[DB/OL].[2011-03-06].http://www.accustreamresearch.com [10] Chiu C Y,Wang H M,Chen C S.Fast Min-Hashing Indexing and Robust Spatiotemporal Matching for Detecting Video Copies.ACM Trans on Multimedia Computing,Communications and Applications,2010,6(2): 1-30 [11] Aslandogan Y A,Yu C T.Techniques and Systems for Image and Video Retrieval.IEEE Trans on Knowledge and Data Engineering,2002,11(1): 56-63 [12] Wu X,Hauptmann A G,Ngo C.Practical Elimination of Near-Duplicates from Web Video Search // Proc of the ACM International Conference on Multimedia.New York,USA,2007: 218-227 [13] Yuan Junsong,Duan Lingyu,Tian Qi.et al.Fast and Robust Short Video Clip Search Using an Index Structure // Proc of the 6th ACM SIGMM International Workshop on Multimedia Information Retrieval.New York,USA,2004: 61-68 [14] Bhat D N,Nayar S K.Ordinal Measures for Image Correspondence.IEEE Trans on Pattern Analysis and Machine Intelligence,1998,20(4): 415-423 [15] Mohan R.Video Sequence Matching // Proc of the IEEE International Conference on Acoustics,Speech and Signal Processing.Seattle,USA,1998: 3697-3700 [16] Datar M,Immorlica N,Indyk P.Locality-Sensitive Hashing Scheme Based on p-Stable Distributions // Proc of the 20th Annual Symposium on Computational Geometry.New York,USA,2004: 253-262 [17] Gionis A,Indyk P,Motwani R.Similarity Search in High Dimensions via Hashing // Proc of the International Conference on Very Large Data Bases.Edinburgh,Scotland,1999: 518-529 [18] Athitsos V,Potamias M,Papapetrou P.Nearest Neighbor Retrieval Using Distance-Based Hashing // Proc of the 24th IEEE International Conference on Data Engineering.Cancun,Mexico,2008: 327-336 [19] Zhang Yongdong,Zhang Dongming,Guo Junbo.Rapid Video Copy Detection on Compressed Domain.Journal on Communication,2009,30(3): 135-140 (in Chinese) (张勇东,张东明,郭俊波.压缩域快速视频拷贝检测算法.通信学报,2009,30(3): 135-140) [20] Zhang Zhihua,Zou Jianhua.A Relative Phases Algorithm of Key Edges for Detection Compressed Video Copies.Journal of Xian Jiaotong University,2010,44(10): 8-10 (in Chinese) (张志杰,邹建华.面向压缩域视频拷贝检测的主要边缘相对相位算法.西安交通大学学报,2010,44(10): 8-10) [21] Tang Zhifeng,Wang Shijun,Yang Shuyuan.A High Precision Compressed Domain Approach for Video Object Segmentation.Journal of Electronics Information Technology,2007,29(12): 2965-2968 (in Chinese) (唐志峰,王诗俊,杨树元.一种高精度的压缩域视频目标分割算法.电子与信息学报,2007,29(12): 2965-2968) [22] Xiao Youneng,Xue Xiangyang.A Fast Algorithm to Detect Dissolve Shot in Compression Domain.Journal of Computer Research and Development,2004,41(11): 1982-1989 (in Chinese) (肖友能,薛向阳.压缩域中叠化镜头的快速检测算法.计算机研究与发展,2004,41(11): 1982-1989)
2012, Vol. 25 
