MULTI-OBJECT TRACKING BASED ON SOFT ASSIGNMENT OF DETECTION RESPONSES

Sami Huttunen, Janne Heikkilä

Abstract

We introduce a new detection-based method that is able to track multiple objects from a single camera. The method is built upon an approach that combines Kalman filtering and the Expectation Maximization (EM) algorithm. The benefit of this approach is that soft assignment of the detections to corresponding objects can be performed automatically using their a posteriori probabilities. This is a general approach for detectionbased multi-object tracking, and there are various ways to detect the objects. In this paper, we demonstrate the applicability of the approach for tracking multiple pedestrians and faces using a basic cascade detector.

References

  1. Dempster, A., Laird, N., and Rubin, D. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, 39(1):1-38.
  2. Fortmann, T., Bar-Shalom, Y., and Scheffe, M. (1983). Sonar tracking of multiple targets using joint probabilistic data association. IEEE-JOE, 8(3):173-184.
  3. Gavrila, D. (2000). Pedestrian detection from a moving vehicle. In Proc. ECCV, volume 1843 of LNCS, pages 37-49.
  4. Hannuksela, J., Huttunen, S., Sangi, P., and Heikkilä, J. (2007). Motion-based finger tracking for user interaction with mobile devices. In Proc. CVMP.
  5. Huang, C., Wu, B., and Nevatia, R. (2008). Robust object tracking by hierarchical association of detection responses. In Proc. ECCV, volume 5303 of LNCS, pages 788-801.
  6. Huttunen, S. and Heikkilä, J. (2008). Multi-object tracking using binary masks. In Proc. ICIP, pages 2640-2643.
  7. Joo, S.-W. and Chellappa, R. (2007). A multiple-hypothesis approach for multiobject visual tracking. IEEE-TIP, 16:2849-2854.
  8. Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Trans. of the ASME-Journal of Basic Engineering, 82:35-45.
  9. Leibe, B., Schindler, K., and Van Gool, L. (2007). Coupled detection and trajectory estimation for multi-object tracking. In Proc. IEEE ICCV, pages 1-8.
  10. Lienhart, R. and Maydt, J. (2002). An extended set of haarlike features for rapid object detection. In Proc. ICIP, volume 1, pages 900-903.
  11. Mikolajczyk, K., Schmid, C., and Zisserman, A. (2004). Human detection based on a probabilistic assembly of robust part detectors. In Proc. ECCV, volume 3021 of LNCS, pages 69-82.
  12. Munder, S. and Gavrila, D. (2006). An experimental study on pedestrian classification. IEEE-TPAMI, 28(11):1863-1868.
  13. Reid, D. (1979). An algorithm for tracking multiple targets. IEEE-TAC, 24(6):843-854.
  14. Singh, V. K., Wu, B., and Nevatia, R. (2008). Pedestrian tracking by associating tracklets using detection residuals. In Proc. IEEE WMVC, pages 1-8.
  15. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proc. IEEE CVPR, volume 1, pages 511-518.
  16. Wu, B. and Nevatia, R. (2005). Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In Proc. IEEE ICCV, volume 1, pages 90-97.
Download


Paper Citation


in Harvard Style

Huttunen S. and Heikkilä J. (2010). MULTI-OBJECT TRACKING BASED ON SOFT ASSIGNMENT OF DETECTION RESPONSES . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 296-301. DOI: 10.5220/0002820602960301


in Bibtex Style

@conference{visapp10,
author={Sami Huttunen and Janne Heikkilä},
title={MULTI-OBJECT TRACKING BASED ON SOFT ASSIGNMENT OF DETECTION RESPONSES},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={296-301},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002820602960301},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - MULTI-OBJECT TRACKING BASED ON SOFT ASSIGNMENT OF DETECTION RESPONSES
SN - 978-989-674-028-3
AU - Huttunen S.
AU - Heikkilä J.
PY - 2010
SP - 296
EP - 301
DO - 10.5220/0002820602960301