Abstract
We present an object detection and tracking algorithm that addresses the problem of multiple simultaneous targets tracking in real-world surveillance scenarios. The algorithm is based on color change detection and multi-feature graph matching. The change detector uses statistical information from each color channel to discriminate between foreground and background. Changes of global illumination, dark scenes, and cast shadows are dealt with a pre-processing and post-processing stage. Graph theory is used to find the best object paths across multiple frames using a set of weighted object features, namely color, position, direction and size. The effectiveness of the proposed algorithm and the improvements in accuracy and precision introduced by the use of multiple features are evaluated on the VACE dataset.
This is a preview of subscription content, log in via an institution to check access.
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
Chang, C., Hu, W., Hsieh, J., Chen, Y.: Shadow elimination for effective moving object detection with gaussian models. In: Proc. of IEEE Conf. on Pattern Recog., vol. 2, pp. 540–543 (2002)
Porikli, F., Thornton, J.: Shadow flow: A recursive method to learn moving cast shadows. In: Proc. of IEEE International Conference on Computer Vision, vol. 1, pp. 891–898 (2005)
Martel-Brisson, N., Zaccarin, A.: Moving cast shadow detection from a gaussian mixture shadow model. In: Proc. of IEEE Conf. on Comp. Vis. and Pattern Recog., vol. 2, pp. 643–648 (2005)
Javed, O., Shah, M.: Tracking and object classification for automated surveillance. In: Proc. of the European Conference on Computer Vision, Copenhagen (2002)
Fung, G., Yung, N., Pang, G., Lai, A.: Effective moving cast shadow detection for monocular color image sequences. In: Proc. of IEEE International Conf. on Image Analysis and Processing, pp. 404–409. IEEE Computer Society Press, Los Alamitos (2001)
Xu, D., Liu, J., Liu, Z., Tang, X.: Indoor shadow detection for video segmentation. In: IEEE Fifth World Congress on Intelligent Control and Automation (WCICA), vol. 4 (2004)
Huang, J., Xie, W., Tang, L.: Detection of and compensation for shadows in colored urban aerial images. In: IEEE Fifth World Congress on Intelligent Control and Automation (WCICA), vol. 4, pp. 3098–3100. IEEE, Los Alamitos (2004)
Salvador, E., Cavallaro, A., Ebrahimi, T.: Shadow identification and classification using invariant color models. In: Proc. of IEEE International Conf. on Acoustics, Speech, and Signal Processing, vol. 3, pp. 1545–1548. IEEE, Los Alamitos (2001)
Hsieh, J., Yu, S., Chen, Y., Hu, W.: A shadow elimination method for vehicle analysis. In: Proc. of IEEE Conf. on Pattern Recog., vol. 4, pp. 372–375. IEEE, Los Alamitos (2004)
Fortman, T., Bar-Shalom, Y., Scheffe, M.: Sonar tracking of multiple targets using joint probabilistic data association. IEEE J. Oceanic Eng. 8(3), 173–184 (1983)
Reid, D.: An algorithm for tracking multiple targets. IEEE Trans. Automat. Contr. AC-24, 843–854 (1979)
Shafique, K., Shah, M.: A noniterative greedy algorithm for multiframe point correspondence. IEEE Trans. Pattern Anal. Machine Intell. 27, 51–65 (2005)
Veenman, C., Reinders, M., Backer, E.: Resolving motion correspondence for densely moving points. IEEE Trans. Pattern Anal. Machine Intell. 23(1), 54–72 (2001)
Rowan, M., Maire, F.: An efficient multiple object vision tracking system using bipartite graph matching. In: FIRA (2004)
Chen, H., Lin, H., Liu, T.: Multi-object tracking using dynamical graph matching. In: Proc. of IEEE Conf. on Comp. Vis. and Pattern Recog., vol. 2, pp. II–210–I–217 (2001)
Mathes, T., Piater, J.: Robust non-rigid object tracking using point distribution models. In: British Machine Vision Conference, Oxford (2005)
Javed, O., Rasheed, Z., Shafique, K., Shah, M.: Tracking across multiple cameras with disjoint views. In: The Ninth IEEE International Conference on Computer Vision, Nice, France (2003)
Cohen, I., Medioni, G.G.: Detecting and tracking moving objects for video surveillance. In: CVPR, pp. 2319–2325. IEEE Computer Society Press, Los Alamitos (1999)
Kasturi, R.: Performance evaluation protocol for face, person and vehicle detection & tracking in video analysis and content extraction (VACE-II). Computer Science & Engineering University of South Florida, Tampa (2006)
Cavallaro, A., Ebrahimi, T.: Interaction between high-level and low-level image analysis for semantic video object extraction. EURASIP Journal on Applied Signal Processing 6, 786–797 (2004)
Hopcroft, J., Karp, R.: An n2.5 algorithm for maximum matchings in bipartite graphs. SIAM J. Computing 2(4), 225–230 (1973)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Taj, M., Maggio, E., Cavallaro, A. (2007). Multi-feature Graph-Based Object Tracking. In: Stiefelhagen, R., Garofolo, J. (eds) Multimodal Technologies for Perception of Humans. CLEAR 2006. Lecture Notes in Computer Science, vol 4122. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69568-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-540-69568-4_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69567-7
Online ISBN: 978-3-540-69568-4
eBook Packages: Computer ScienceComputer Science (R0)