Abstract
This paper proposes a video retrieval system from compressed outdoor video surveillance databases. The aim is to extract moving objects from frames provided by MPEG video stream in order to classify them into predefined categories according to image-based properties, and then robustly index them. The principal idea is to combine between useful properties of metrical classification and the notion of temporal consistency. Fuzzy geometry classification is used in order to provide an efficient method to classify motion regions into three generic categories: pedestrian, vehicle and no identified object. The temporal consistency provides a robust classification to changes of objects appearance and occlusion of object motion. The classified motion regions are used as templates for metrical training algorithms and as keys for tree indexing technique.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bart, K.: Neural Networks and fuzzy Systems. Prentice-Hall, Englewood Cliffs (1992)
Bezdek, J.C.: On the relationship between neural networks, pattern recognition and intelligence. Intenational Journal of Approximate Reasonning 6, 85–107 (1992)
Bregler, C.: Learning and recognizing human dynamics in video sequences. In: Proceeding of IEEE CVPR 1997, pp. 568–574 (1997)
Brunelli, R., Mich, O., Modena, C.M.: A survey on the automatic indexing of video data. Jal. of visual communication and image representation 10, 78–112 (1999)
Pham, D.L.: Spatial models for fuzzy clustering. Jal. Computer vision and image understanding 84, 285–297 (2001)
Ferman, A.M., Murat Tekalp, A.: Efficient filtering and clustering methods for temporal video segmentation and visual summarization. Jal. of visual communication and image representation 99(4), 336–351 (1998)
Gudivada, V.N., Raghvan, V.V.: Content-based image systems. IEEE Comput 28(9), 18–22 (1995)
Habed, A.: Content-based access image and video libraries, Math-info department, Sherbrooke University (1999)
Idris, F., Pandranathan, S.: ‘Review of image and video indexing techniques’. Jal. of visual communication and image representation 8(2), 146–166 (1997)
Iketani, A., Nagai, A., Kuno, Y., Shirai, Y.: ‘Real time surveillance system detecting persons in complex scenes’. Jal. of Real time imaging 7, 433–446 (2001)
Khelifi, S., Boudihir, M.E., Nourine, R.: Fuzzy Classification System for outdoor Video Databases Retrieval. In: Proceeding of AICSSA 2003. IEEE Int. Conf. on Computer Systems and Applications, Gammart. Tunisia, July 14-18 (2003)
Khelifi, S., Boudihir, M.E., Nourine, R.: Content-Based Video Database Retrieval Using Fuzzy Classification System. In: Proceeding of MediaNet 2004. 2ndInternational Conference on Intelligent Access of Multimedia Documents on Internet, Tozeur, Tunisia, November 25-28 (2004)
Khelifi, S., Boudihir, M.E., Nourine, R.: Video Database Indexing: an Approach using Fuzzy Classification of Moving Objects in Outdoor Videos. In: Proc. of MCSEAI 2004. 8thMaghrebian Conference on Software Engineering and Artificial Intelligence, Sousse, Tinisia, May 9-12, pp. 555–566 (2004)
Khelifi, S., Boudihir, M.E., Nourine, R.: Fuzzy Classification System for Telesurveillance Databases Retrieval and Indexing. In: Proceeding of International IEEE/APS Conference on Mechatronics and Robotics, Aachen, Germany, September 13-15, pp. 20–25 (2004)
Krüger, S.: Motion analysis and estimation using multi-resolution affine models, Thesis submitted at the university of Bristol (July 1998)
Lipton, A.J., Fujiyoshi, H., Patil, R.S.: Moving target classification and tracking from real-time video, Submitted to IEEE WACV 1998 (1998)
Niblack, W.: The QBIC project: querying images by content using colour, texture, and shape. In: Proceedings of the SPIE Storage and Retrieval for Image and Video Databases, San Jose, California, Bellingham, SPIE, vol. 1908, pp. 173–187 (February 1993)
Ng, R., Sedighian, A.: Evaluating multi-dimensional indexing structures for images transformed by principals component analysis. In: Proc. SPIE Storage and retrieval for image and video databases (1996)
Rudolf, K., Gebhardt, J., Klowonn, F.: Fundations of fuzzy systems. John Wiley and Sons Ltd., Chichester (1994)
Smoliar, S.W., Zhang, H.J.: Content-based video indexing and retrieval. In: Proceeding of IEEE Multimedia, vol. 1(2), pp. 62–72 (Summer 1994)
Schonfeld, D., Lescu, D.: VORTEX: video retrieval and tracking from compressed multimedia databases- multiple object tracking from MPEG-2 bit stream. Jal. of visual communication and image representation 11, 154–182 (2000)
Shneier, M., Abdel, M.M.: ‘Exploiting the JPEG compression scheme for image retrieval’. Proceeding in IEEE Trans. Patt. Anal. Mach. Intell. 18(8), 849–853 (1996)
Tizhoosh, H.: Fuzzy image processing. Springer, Heidelberg (1997)
Yeo, B.-L., Liu, B.: A unifiedapproach to temporal segmentation of motion JPEG and MPEG compressed videos. In: Proceeding of the International Conference on Multimedia Computing and Systems, May 1995, pp. 81–88 (1995)
Yeo, B.-L., Liu, B.: Efficient processing of compressed images and video, Ph.D. thesis, Dept. Of Electrical Engineering, Princeton University (January 1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Khelifi, S.F., Boudihir, M.E., Nourine, R. (2005). Compressed Telesurveillance Video Database Retrieval Using Fuzzy Classification System. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2005. Lecture Notes in Computer Science, vol 3656. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11559573_71
Download citation
DOI: https://doi.org/10.1007/11559573_71
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29069-8
Online ISBN: 978-3-540-31938-2
eBook Packages: Computer ScienceComputer Science (R0)