Querying video contents by motion example

This paper presents a new conceptual model for representing visual information about moving objects in video data. Based on available automatic scene segmentation and object tracking algorithms, the proposed model calculates object motions at various levels of semantic granularity. It represents trajectory, color and dimensions of a single moving object and the directional and topological relations among multiple objects over a time interval. To facilitate query processing, there are two optimal approximate matching algorithms designed to match time-series visual features of moving objects. Experimental results indicate that the proposed algorithms outperform the conventional subsequence-matching methods substantially in the similarity between the two trajectories.

[1]  Masahito Hirakawa,et al.  VIOLONE: Video Retrieval by Motion Example , 1996, J. Vis. Lang. Comput..

[2]  Duane Szafron,et al.  Modeling of moving objects in a video database , 1997, Proceedings of IEEE International Conference on Multimedia Computing and Systems.

[3]  Shih-Fu Chang,et al.  A fully automated content-based video search engine supporting spatiotemporal queries , 1998, IEEE Trans. Circuits Syst. Video Technol..

[4]  Wei-Pang Yang,et al.  A New Content-Based Access Method for Video Databases , 1999, Inf. Sci..

[5]  Shi-Kuo Chang,et al.  Image sequence compression by iconic indexing , 1989, [Proceedings] 1989 IEEE Workshop on Visual Languages.

[6]  Svetha Venkatesh,et al.  Resequencing of Video using Spatial Indexing , 1997, J. Vis. Lang. Comput..

[7]  Suh-Yin Lee,et al.  A Video Information System for Sport Motion Analysis , 1997, J. Vis. Lang. Comput..

[8]  Avideh Zakhor,et al.  Motion indexing of video , 1997, Proceedings of International Conference on Image Processing.

[9]  Vijay V. Raghavan,et al.  Design and evaluation of algorithms for image retrieval by spatial similarity , 1995, TOIS.

[10]  Ahmed K. Elmagarmid,et al.  Scene change detection techniques for video database systems , 1998, Multimedia Systems.

[11]  Jonathan D. Courtney Automatic video indexing via object motion analysis , 1997, Pattern Recognit..

[12]  Jose A. Ventura,et al.  Optimal matching of general polygons based on the minimum zone error , 1995, Pattern Recognit. Lett..

[13]  Suh-Yin Lee,et al.  Video indexing: an approach based on moving object and track , 1993, Electronic Imaging.

[14]  Theodosios Pavlidis,et al.  Optimal Correspondence of String Subsequences , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Suh-Yin Lee,et al.  Video Data Indexing by 2D C-Trees , 1998, J. Vis. Lang. Comput..

[16]  Alberto Del Bimbo,et al.  Symbolic Description and Visual Querying of Image Sequences Using Spatio-Temporal Logic , 1995, IEEE Trans. Knowl. Data Eng..