MULTIPLE OBJECT TRACKING WITH RELATIONS

Luca Cattelani, Cristina Manfredotti, Enza Messina

Abstract

Dealing with multi-object tracking raises several issues; an essential point is to model possible interactions between objects. Indeed, while reliable algorithms for tracking multiple non-interacting objects in constrained scenarios exist, tracking of multiple interacting objects in uncontrolled scenarios is still a challenge. The multiple-object tracking problem can be broken down into two subtasks: the detection of target objects, and the association between objects along time. Interaction between objects can yield erroneous associations that cause the interchange of object identities, therefore, the explicit recognition of the relationships between interacting objects in the scene can be useful to better detect the targets and understand their dynamics, making tracking more accurate. To make inference in relational domains we have developed an extension of particle filter, called relational particle filter, able to track simultaneously the objects in the domain and the evolution of their relationships. Experimental results show that our method can follow the targets’ path more closely than standard methods, being able to better predict their behaviours while decreasing the complexity of the tracking.

References

  1. Brambilla M., Cattelani L., 2009. Mobility analysis inside buildings using Distrimobs simulator: A case study. In Building and Environment, Volume 44, Issue 3, March 2009, 595-604.
  2. Copsey K., Webb A., 2002. Bayesian networks for incorporation of contextual information in target recognition systems. In SSPR/SPR, 709-717.
  3. Fleuret F., Berclaz J., Lengagne R., Fua P., 2008. MultiCamera People Tracking With a Probabilistic Occupancy Map. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 30, no. 2, February 2008, 267-282.
  4. Getoor L., Friedman N., Koller D., Pfeffer A., 2001. Learning probabilistic relational models. In S. Dzeroski S. and Lavrac N. (Eds.), Relational Data Mining, Springer-Verlag, Kluwer, 2001, 307-335.
  5. Giebel J., Gavrila D., Schnorr C., 2004. A Bayesian Framework for Multi-Cue 3D Object Tracking. In European Conference on Computer Vision.
  6. Gning A., Mihaylova L., Maskell S., Pang S. K., Godsill S., 2011. Group Object Structure and State Estimation With Evolving Networks and Monte Carlo Methods, IEEE Transactions on Signal Processing, Vol. 59, No. 4, April 2011, 1383-1396.
  7. Khan Z., Balch T. R., Dellaert F., 2004. An mcmc-based particle filter for tracking multiple interacting targets. In ECCV (4), 279-290.
  8. Liu, J. S., Chen, R., 1998. Sequential Monte Carlo methods for dynamic systems. In Journal of the American Statistical Association, Volume 93, 1032- 1044.
  9. Manfredotti C., Messina E., Fleet D. J., 2009. Relations to improve multi-target tracking in an activity recognition system. In 3rd International Conference on Imaging for Crime Detection and Prevention, (ICDP09), London, December 2009.
  10. Manfredotti C., Messina E., 2009. Relational Dynamic Bayesian Networks to Improve Multi-Target Tracking, In Lecture Notes in Computer Sciences ACIVS 2009, Volume 5807, 528-539.
  11. Manfredotti C. E., Fleet D. J., Hamilton H. J., Zilles S., 2011. Simultaneous Tracking and Activity Recognition with Relational Dynamic Bayesian Networks, Technical Report CS 2011-1, March 2011.
  12. Pang S. K., Li J., Godsill S. J., 2008. Models and Algorithms for Detection and Tracking of Coordinated Groups, In Aerospace Conference, 2008 IEEE, March 2008, 1-17.
  13. Perera A., Srinivas C., Hoogs A., Brooksby G., Wensheng H., 2006. Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions. in Conference on Computer Vision and Pattern Recognition, June 2006, 666-673.
  14. Reynolds C. W., 1987. Flocks, herds and schools: A distributed behavioral model. In Proceedings of the 14th annual conference on Computer graphics and interactive techniques (SIGGRAPH 7887), Maureen C. Stone (Ed.), ACM, New York, NY, USA, 25-34.
Download


Paper Citation


in Harvard Style

Cattelani L., Manfredotti C. and Messina E. (2012). MULTIPLE OBJECT TRACKING WITH RELATIONS . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: IATMLRP, (ICPRAM 2012) ISBN 978-989-8425-98-0, pages 459-466. DOI: 10.5220/0003856004590466


in Bibtex Style

@conference{iatmlrp12,
author={Luca Cattelani and Cristina Manfredotti and Enza Messina},
title={MULTIPLE OBJECT TRACKING WITH RELATIONS},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: IATMLRP, (ICPRAM 2012)},
year={2012},
pages={459-466},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003856004590466},
isbn={978-989-8425-98-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: IATMLRP, (ICPRAM 2012)
TI - MULTIPLE OBJECT TRACKING WITH RELATIONS
SN - 978-989-8425-98-0
AU - Cattelani L.
AU - Manfredotti C.
AU - Messina E.
PY - 2012
SP - 459
EP - 466
DO - 10.5220/0003856004590466