基于组合相似性的视频检索

邓丽; 金立左; 费树岷

doi:10.3724/SP.J.1146.2006.00165

基于组合相似性的视频检索

doi: 10.3724/SP.J.1146.2006.00165

计量
- 文章访问数: 3094
- HTML全文浏览量: 111
- PDF下载量: 1566
- 被引次数: 0
出版历程
- 收稿日期: 2006-02-20
- 修回日期: 2006-09-27
- 刊出日期: 2007-05-19

Ensemble Similarity-Blased Video Retrieval

摘要

摘要: 该文研究基于镜头的视频检索问题，提出了一种新的基于组合相似性的镜头相似性度量方法。首先把镜头看成由帧序列组成的一个组合，镜头的相似性通过帧组合的相似性来度量。其次通过用一个非线性映射，把帧组合所在的空间映射到一个高维空间，在这个空间中，假设帧组合服从正态分布，利用核方法，抽取出关键帧序列，并计算出两个正态分布之间的概率距离，这个距离表明了帧组合的相似程度，从而得到两个镜头之间的相似性。最后将这种方法应用于基于镜头的视频检索中，实验表明在相同条件下，基于该方法的检索效果明显优于传统的欧式距离和直方图交方法。
- 镜头相似性;组合相似性;核方法;概率距离;视频检索
Abstract: In this paper, a novel method is proposed to determine the similarity between shots. Firstly, a shot is treated as an ensemble that consists of a sequence of video frames. Shot similarity can be measured by ensemble similarity. Secondly, the original space is mapped to a high dimension space by a nonlinear mapping. In this space, distribution of the ensemble can be assumed as a normal distribution. Finally, by kernel method, the probability distance is computed directly. This distance is equivalent to the ensemble similarity. So, the shot similarity is also obtained. Experimental results show that this method achieves superior performance than the traditional Euclidean distance and histogram intersection methods.

HTML全文

参考文献(1)

Jain A K, Vailaya A, and Wei X. Query by video clip[J].Multimedia System.1999, 7(5):369-384[2]Shan M K and Lee S Y. Content-based video retrieval based on similarity of frame sequence. In Proceedings of the IEEE Conference on Multimedia Computing and Systems, Austin, Texas, 5-7 Aug, 1998: 90-97.[3]林通, 张宏江, 封举富等. 镜头内容分析及其在视频检索中的应用. 软件学报, 2002, 13(8): 1577-1585. Lin T, Zhang H J, and Feng J F, et al. Shot content analysis for video retrieval application. Journal of Software, 2002, 13(8): 1577-1585.[4]赵黎, 祁卫, 李子青等. 基于关键帧提取的最近特征线 (NFL) 聚类算法的镜头检索方法. 计算机学报, 2000, 23 (12): 1292- 1298. Zhao Li, Qi Wei, and Li Zi-qin. Key-Frame Extraction Based Improved Nearest Feature Line(NFL) Classification Algorithm. Journal of Computers, 2000, 23(12): 1292-1298.[5]Zhou S K and Chellappa R. From sample similarity to ensemble similarity: Probabilistic distance measure in reproducing kernel Hilbert space[J].IEEE Trans. on Pattern Analysis and Machine Intelligence.2006, 28(6):917-929[6]Missaoui R, Sarifuddin M, and Vaillancout J. Similarity measures for efficient content-based image retrieval[J].IEE Proceedings Vision, Image and Signal Process.2005, 152(6):875-887[7]Devijver P and Kitter J. Pattern Recognition: A statistical Approach. UK: Prentice Hall International, 1982: 120-146.[8]Bach F and Jordan M I. Learning graphical models with Mercer kernels. In Advances in Neural Information Processing Systems15, Cambridge, MA, 2003, MIT Press.Kondor R and Jebara T. A kernel between sets of vectors. In Proceedings of the Twentieth International Conference on Machine Learning, Washington, DC, USA. , August 21-24, 2003: 361-368.[9]张莉, 周伟达, 焦李成. 核聚类算法. 计算机学报, 2002, 25(6): 587-590. Zhang Li, Zhou Wei-da, and Jiao Li-cheng. Kernel clustering algorithm. Journal of Computers, 2002, 25(6): 587-590.[10]Swain M J and Ballard D H. Color indexing[J].International Journal of Computer Vision.1991, 7(1):11-32

施引文献

资源附件(0)

访问统计