Video Copy Detection Based on Fusion of Spatio-Temporal Features

Abstract:

A video copy detection method based on fusion of spatio-temporal features is proposed in this paper. Firstly, trajectories are built and lens boundaries are detected by SURF features analyzing, then normalized histogram is used to describe spatio-temporal behavior of trajectories, the bag of visual words is constructed by trajectories behavior clustering, word frequency vectors and SURF features with behavior labels are extracted to express spatio-temporal content of lens, finally, duplicates are detected efficiently based on grade-match. The experimental results show the performance of this method is improved greatly compared with other similar methods.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 3653-3661
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.3653
• Online since: August 2013
• Authors: Wei Bao, Li Xin Ji, Shi Lin Gao, Xing Li, Li Xiong Liu
• Keywords: Bag of Visual Words, Grade-Match, Spatio-Temporal Behavior of Trajectories, Speeded-Up Robust Feature, Video Copy Detection

References

[1] Guidelines for the TRECVID 2011CD task Evaluation[OL]. http: /www-nlpir. nist. gov/projects/tv2011/tv2011. html.

[2] Law-To J, Buisson O, Gouet-Brunet V, et al. Robust Voting Algorithm based on Labels of Behavior for Video Copy Detection[C]. In ACM Multimedia, (2006).

DOI: 10.1145/1180639.1180826

[3] Law-To J, Li Chen, Alexis Joly, et al. Video Copy Detection: A Comparative Study[C]. In Proc of ACM International Conference on Image and Video Retrieval, 2007. 371-378.

DOI: 10.1145/1282280.1282336

[4] Shi Chen, Jinqiao Wang, Yi Ouyang, et al. Multi-Level Trajectory Modeling for Video Copy Detection[C]. In Proc of IEEE International Conference on Acoustics Speech and Signal Processing, 2010, 2378-2381.

DOI: 10.1109/icassp.2010.5496165

[5] Guo Junbo, Li Jintao, Zhang Yongdong, et al. Video Copy Detection Based on Trajectory Behavior Pattern [J]. Journal of computer-aided design & computer graphics, 2010, 22, 943-948.

DOI: 10.3724/sp.j.1089.2010.10842

[6] Wu Xiao, Li Jintao, Tang Sheng, Guo Junbo. Video Copy Detection Based on Spatio-Temporal Trajectory Behavior Feature [J]. Journal of computer research and development, 2010, 47, 1871-1877.

DOI: 10.1049/cp:20080349

[7] The origin of the video database is MUSCLE-VCD-2007[EB/OL]. http: /wwwrocq. inria. fr/imedia/civr-bench/index. html.

[8] Bay H, Ess A, Gool L., etc. SURF: Speeded Up Robust Features[J]. Computer Vision and Image Understanding, 110, 346-359.

DOI: 10.1016/j.cviu.2007.09.014

[9] Bauer . J, Sünderhauf . N, Protzel .P. Comparing Several Implementations of Two Recently Published Feature Detectors[C]. In Proc. of the International Conference on Intelligent and Autonomous Systems, Toulouse, France, (2007).

DOI: 10.3182/20070903-3-fr-2921.00027

[10] Luo Juan, Oubong Gwun. A Comparison of SIFT, PCA-SIFT and SURF[J]. International Journal of Image Processing, 3, 143-152.

[11] Frey . J, Dueck .D. Clustering by Passing Messages between Data Points[J]. Science, 2007, 315, 972-976.

DOI: 10.1126/science.1136800

[12] Wang Kaijun, Zheng Jie. Fast Algorithm of Affinity Propagation Clustering under Given Number of Clusters [J]. applications of the computer systems, 2010, 19, 207-209.