Abstract
Maintaining the stability of tracks on multiple targets in video over extended time periods remains a challenging problem. A few methods which have recently shown encouraging results in this direction rely on learning context models or the availability of training data. However, this may not be feasible in many application scenarios. Moreover, tracking methods should be able to work across different scenarios (e.g. multiple resolutions of the video) making such context models hard to obtain. In this paper, we consider the problem of long-term tracking in video in application domains where context information is not available a priori, nor can it be learned online. We build our solution on the hypothesis that most existing trackers can obtain reasonable short-term tracks (tracklets). By analyzing the statistical properties of these tracklets, we develop associations between them so as to come up with longer tracks. This is achieved through a stochastic graph evolution step that considers the statistical properties of individual tracklets, as well as the statistics of the targets along each proposed long-term track. On multiple real-life video sequences spanning low and high resolution data, we show the ability to accurately track over extended time periods (results are shown on many minutes of continuous video).
Keywords
- Markov Chain Monte Carlo
- Color Histogram
- Data Association
- Proposal Distribution
- Multiple Object Tracking
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.
This work was supported in part by NSF grant IIS-0712253 and subcontract from Mayachitra Inc., through a DARPA STTR award (#W31P4Q-08-C-0464).
Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Babenko, B., Yang, M., Belongie, S.: Visual Tracking with Online Multiple Instance Learning. In: IEEE CVPR (2009)
Bar-Shalom, Y., Fortmann, T.: Tracking and Data Association. Academic Press, London (1988)
Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based Object Tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence (May 2003)
Duda, R., Hart, P., Stork, D.: Pattern Classification. Wiley Interscience, Hoboken (2001)
Ge, W., Collins, R.: Multi-target Data Association by Tracklets with Unsupervised Parameter Estimation. In: British Machine Vision Conference (2008)
Hoiem, D., Efros, A., Hebert, M.: Geometric Context from a Single Image. In: IEEE ICCV (2005)
Hue, C., Cadre, J.L., Prez, P.: Sequential Monte Carlo Methods for Multiple Target Tracking and Data Fusion. IEEE Trans. on Signal Processing (2002)
Isard, M., Blake, A.: Condensation - Conditional Density Propagation for Visual Tracking. International Journal of Computer Vision (1998)
Jiang, H., Fels, S., Little, J.: A Linear Programming Approach for Multiple Object Tracking. In: IEEE CVPR (2007)
Leibe, B., Schindler, K., Gool, L.V.: Coupled Detection and Trajectory Estimation for Multi-Object Tracking. In: IEEE ICCV (2007)
Li, Y., Huang, C., Nevatia, R.: Learning to Associate: HybridBoosted Multi-Target Tracker for Crowded Scene. In: IEEE CVPR (2009)
Perera, A., Srinivas, C., Hoogs, A., Brooksby, G., Hu, W.: Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions. In: IEEE CVPR (2006)
Reid, D.: An Algorithm for Tracking Multiple Targets. IEEE Trans. Automatic Control 24(6), 843–854 (1979)
Song, B., Roy-Chowdhury, A.: Stochastic Adaptive Tracking in a Camera Network. In: IEEE ICCV (2007)
Stauffer, C., Grimson, W.: Adaptive Background Mixture Models for Real-time Tracking. In: IEEE CVPR (1998)
Yang, M., Wu, Y., Hua, G.: Context-Aware Visual Tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence (July 2009)
Yu, Q., Medioni, G., Cohen, I.: Multiple Target Tracking Using Spatio-Temporal Markov Chain Monte Carlo Data Association. In: IEEE CVPR (2007)
Zhang, L., Li, Y., Nevatia, R.: Global Data Association for Multi-Object Tracking Using Network Flows. In: IEEE CVPR (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
1 Electronic Supplementary Material
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Song, B., Jeng, TY., Staudt, E., Roy-Chowdhury, A.K. (2010). A Stochastic Graph Evolution Framework for Robust Multi-target Tracking. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6311. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15549-9_44
Download citation
DOI: https://doi.org/10.1007/978-3-642-15549-9_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15548-2
Online ISBN: 978-3-642-15549-9
eBook Packages: Computer ScienceComputer Science (R0)