Abstract
This paper describes a real-time system for multi-target tracking and classification in image sequences from a single stationary camera. Several targets can be tracked simultaneously in spite of splits and merges amongst the foreground objects and presence of clutter in the segmentation results. In results we show tracking of upto 17 targets simultaneously. The algorithm combines Kalman filter-based motion and shape tracking with an efficient pattern matching algorithm. The latter facilitates the use of a dynamic programming strategy to efficiently solve the data association problem in presence of multiple splits and merges. The system is fully automatic and requires no manual input of any kind for initialization of tracking. The initialization for tracking is done using attributed graphs. The algorithm gives stable and noise free track initialization. The image based tracking results are used as inputs to a Bayesian network based classifier to classify the targets into different categories. After classification a simple 3D model for each class is used along with camera calibration to obtain 3D tracking results for the targets. We present results on a large number of real world image sequences, and accurate 3D tracking results compared with the readings from the speedometer of the vehicle. The complete tracking system including segmentation of moving targets works at about 25Hz for 352×288 resolution color images on a 2.8 GHz pentium-4 desktop.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Bar-Shalom, Y.: Tracking methods in a multitarget environment. IEEE Transactions on Automatic Control AC-23(4), 618–626 (1978)
Blackman, S.: Multiple-Target Tracking with Radar Application. Artech House, Norwood (1986)
Paragios, N., Deriche, R.: Geodesic active regions for motion estimation and tracking. IEEE Transactins on Pattern Analysis and Machine Intelligence 22(3), 266–280 (2000)
McKenna, S.J., Jabri, S., Duric, Z., Rosenfeld, A., Wechsler, H.: Tracking groups of people. Computer Vision and Image Understanding 80, 42–56 (2000)
Javed, O., Shah, M.: Tracking and object classification for automated surveillance. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 343–357. Springer, Heidelberg (2002)
Haritaoglu, I., Harwood, D., Davis, L.: W4: Who, when, where, what: A real time system for detecting and tracking people. In: Proceedings of the Third International Conference on Automatic Face and Gesture Recognition (FG 1998), April 1998, pp. 222–227 (1998)
Haritaoglu, I., Harwood, D., Davis, L.: W4S: A real-time system for detecting and tracking people in \(2\frac{1}{2}D\). In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 877–892. Springer, Heidelberg (1998)
Medioni, G., Cohen, I., Bremond, F., Hongeng, S., Nevatia, R.: Event detection and analysis from video streams. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 873–889 (2001)
Reid, D.B.: An algorithm for tracking multiple targets. IEEE Transactions on utomatic Control AC-24(6), 843–854 (1979)
Cox, I., Miller, M.: On finding rank assignments with application to multitarget tracking and motion correspondence. Aerosys 32, 486–489 (1996)
Tao, H., Sawhney, H.S., Kumar, R.: Object tracking with bayesian estimation of dynamic layer representations. IEEE Transactions on Pattern Analysis and 24(1), 75–89 (2002)
Kumar, P., Ranganath, S., Huang, W.: Queue based fast background modelling and fast hysteresis thresholding for better foreground segmentation. In: Proccedings of The 2003 Joint Conference of the Fourth ICICS and PCM, Singapore, p. 2A2.5 (December 2003)
Li, L., Huang, W., Irene, Y.G., Tian, Q.: Foreground object detection from videos containing complex background. In: Proccedings of ACM Multimedia, pp. 2– 10 (November 2003)
Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct least square fitting of ellipses. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(5), 476–480 (1999)
Mazor, E., Averbuch, A., Bar-Shalom, Y., Dayan, J.: Interacting multiple model methods in target tracking: A survey. IEEE Transactions on Aerospace and Electronic Systems 34(4), 103–123 (1998)
Cipolla, R., Blake, A.: Surface orientation and time to contact from image divergence and deformation. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 187–202. Springer, Heidelberg (1992)
Zheng, Q., Chellappa, R.: Automatic feature point extraction and tracking in image sequences for unknown camera motion. In: Proccedings of International Conference on Computer Vision, Berlin, Germany, pp. 335–339 (May 1993)
Kumar, P.: Multi-body tracking and behavior analysis. Ph.D. Thesis, National University of Singapre
Wolf, J.K., Viterbi, A.M., Dixon, G.S.: Finding the best set of k-paths through a trellis with application to multitarget tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 287–295 (1989)
Mittal, A., Fah, C.L.: Characterizing content using perceptual level features and context cues through dynamic bayesian framework. IEEE Transactions on Circuits and Systems for Video Technology, Special Issue on Conceptual and Dynamical Aspects of Multimedia Content Description (under submission)
Matsui, K., Iwase, M., Agata, M., Tanaka, T., Onishi, N.: Soccer image sequence computed by a virtual camera. In: Proc. Conf. on Computer Vision and Pattern Recognition, pp. 860–865 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kumar, P., Ranganath, S., Sengupta, K., Weimin, H. (2004). Co-operative Multi-target Tracking and Classification. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3021. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24670-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-540-24670-1_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21984-2
Online ISBN: 978-3-540-24670-1
eBook Packages: Springer Book Archive