Multiple Target, Multiple Type Visual Tracking using a Tri-GM-PHD Filter

Nathanael L. Baisa, Andrew Wallace

2017

Abstract

We propose a new framework that extends the standard Probability Hypothesis Density (PHD) filter for multiple targets having three different types, taking into account not only background false positives (clutter), but also confusion between detections of different target types, which are in general different in character from background clutter. Our framework extends the existing Gaussian Mixture (GM) implementation of the PHD filter to create a tri-GM-PHD filter based on Random Finite Set (RFS) theory. The methodology is applied to real video sequences containing three types of multiple targets in the same scene, two football teams and a referee, using separate detections. Subsequently, Munkres’s variant of the Hungarian assignment algorithm is used to associate tracked target identities between frames. This approach is evaluated and compared to both raw detections and independent GM-PHD filters using the Optimal Sub-pattern Assignment (OSPA) metric and discrimination rate. This shows the improved performance of our strategy on real video sequences.

References

  1. Ahmed, E., Jones, M., and Marks, T. K. (2015). An improved deep learning architecture for person reidentification. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3908- 3916.
  2. Appel, R., Fuchs, T., Dollar, P., and Perona, P. (2013). Quickly boosting decision trees - pruning underachieving features early. In ICML, volume 28, pages 594-602.
  3. Bernardin, K. and Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: The CLEAR MOT metrics. J. Image Video Process., pages 1:1-1:10.
  4. Bourgeois, F. and Lassalle, J.-C. (1971). An extension of the munkres algorithm for the assignment problem to rectangular matrices. Commun. ACM, 14(12):802- 804.
  5. Cai, Y., de Freitas, N., and JJ, L. (2006). Robust visual tracking for multiple targets. In IN ECCV, pages 107- 118.
  6. Cham, T.-J. and Rehg, J. M. (1999). A multiple hypothesis approach to figure tracking. In CVPR, pages 2239- 2245. IEEE Computer Society.
  7. Choi, W. (2015). Near-online multi-target tracking with aggregated local flow descriptor. In The IEEE International Conference on Computer Vision (ICCV).
  8. Dollar, P., Appel, R., Perona, P., and Belongie, S. (2014). Fast feature pyramids for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 99:14.
  9. Liu, J. and Carr, P. (2014). Detecting and tracking sports players with random forests and context-conditioned motion models. In Computer Vision in Sports, pages 113-132. Springer.
  10. Maggio, E., Taj, M., and Cavallaro, A. (2008). Efficient multi-target visual tracking using random finite sets. IEEE Transactions On Circuits And Systems For Video Technology, pages 1016-1027.
  11. Mahler, R. P. (2003). Multitarget bayes filtering via firstorder multitarget moments. IEEE Trans. on Aerospace and Electronic Systems, 39(4):1152-1178.
  12. Matzka, P., Wallace, A., and Petillot, Y. (2012). Efficient resource allocation for automotive attentive vision systems. IEEE Trans. on Intelligent Transportation Systems, 13(2):859-872.
  13. Pasha, S., Vo, B.-N., Tuan, H. D., and Ma, W.-K. (2009). A gaussian mixture PHD filter for jump markov system models. Aerospace and Electronic Systems, IEEE Transactions on, 45(3):919-936.
  14. Rasmussen, C. and Hager, G. D. (2001). Probabilistic data association methods for tracking complex visual objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23:560-576.
  15. Ristic, B., Clark, D., and Vo, B.-N. (2010). Improved SMC implementation of the PHD filter. In Information Fusion (FUSION), 2010 13th Conference on, pages 1-8.
  16. Ristic, B., Clark, D. E., Vo, B.-N., and Vo, B.-T. (2012). Adaptive target birth intensity for PHD and CPHD filters. IEEE Transactions on Aerospace and Electronic Systems, 48(2):1656-1668.
  17. Schumacher, D., Vo, B.-T., and Vo, B.-N. (2008). A consistent metric for performance evaluation of multiobject filters. Signal Processing, IEEE Transactions on, 56(8):3447-3457.
  18. Vo, B.-N. and Ma, W.-K. (2006). The gaussian mixture probability hypothesis density filter. Signal Processing, IEEE Transactions on, 54(11):4091-4104.
  19. Vo, B.-N., Singh, S., and Doucet, A. (2005). Sequential monte carlo methods for multitarget filtering with random finite sets. IEEE Transactions on Aerospace and Electronic Systems, 41(4):1224-1245.
  20. Wei, Y., Yaowen, F., Jianqian, L., and Xiang, L. (2012). Joint detection, tracking, and classification of multiple targets in clutter using the PHD filter. Aerospace and Electronic Systems, IEEE Transactions on, 48(4):3594-3609.
  21. Yang, W., Fu, Y., and Li, X. (2014). Joint target tracking and classification via RFS-based multiple model filtering. Information Fusion, 18:101-106.
  22. Yoon, J. H., Lee, C.-R., Yang, M.-H., and Yoon, K.-J. (2016). Online multi-object tracking via structural constraint event aggregation. In CVPR.
  23. Zhou, X., Li, Y., He, B., and Bai, T. (2014). GM-PHDbased multi-target visual tracking using entropy distribution and game theory. Industrial Informatics, IEEE Transactions on, 10(2):1064-1076.
Download


Paper Citation


in Harvard Style

L. Baisa N. and Wallace A. (2017). Multiple Target, Multiple Type Visual Tracking using a Tri-GM-PHD Filter . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 467-477. DOI: 10.5220/0006145704670477


in Bibtex Style

@conference{visapp17,
author={Nathanael L. Baisa and Andrew Wallace},
title={Multiple Target, Multiple Type Visual Tracking using a Tri-GM-PHD Filter},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={467-477},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006145704670477},
isbn={978-989-758-227-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - Multiple Target, Multiple Type Visual Tracking using a Tri-GM-PHD Filter
SN - 978-989-758-227-1
AU - L. Baisa N.
AU - Wallace A.
PY - 2017
SP - 467
EP - 477
DO - 10.5220/0006145704670477