Occlusion Robust Symbol Level Fusion for Multiple People Tracking

Nyan Bo Bo, Peter Veelaert, Wilfried Philips

2017

Abstract

In single view visual target tracking, an occlusion is one of the most challenging problems since target’s features are partially/fully covered by other targets as occlusion occurred. Instead of a limited single view, a target can be observed from multiple viewpoints using a network of cameras to mitigate the occlusion problem. However, information coming from different views must be fused by relying less on views with heavy occlusion and relying more on views with no/small occlusion. To address this need, we proposed a new fusion method which fuses the locally estimated positions of a person by the smart cameras observing from different viewpoints while taking into account the occlusion in each view. The genericity and scalability of the proposed fusion method is high since it needs only the position estimates from the smart cameras. Uncertainty for each local estimate is locally computed in a fusion center from the simulated occlusion assessment based on the camera’s projective geometry. These uncertainties together with the local estimates are used to model the probabilistic distributions required for the Bayesian fusion of the local estimates. The performance evaluation on three challenging video sequences shows that our method achieves higher accuracy than the local estimates as well as the tracking results using a classical triangulation method. Our method outperforms two state-ofthe-art trackers on a publicly available multi-camera video sequence.

References

  1. Andriyenko, A. and Schindler, K. (2010). Globally optimal multi-target tracking on a hexagonal lattice. In Proceedings of the 11th European Conference on Computer Vision: Part I, ECCV'10, pages 466-479.
  2. Andriyenko, A. and Schindler, K. (2011). Multi-target tracking by continuous energy minimization. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 1265-1272.
  3. Berclaz, J., Fleuret, F., Turetken, E., and Fua, P. (2011). Multiple object tracking using k-shortest paths optimization. IEEE Trans. on Pattern Analysis and Machine Intelligence, 33(9):1806-1819.
  4. Bernardin, K. and Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: the clear mot metrics. J. Image Video Process., 2008:1-10.
  5. Bo Bo, N., Deboeverie, F., Eldib, M., Guan, J., Xie, X., Nio, J., Van Haerenborgh, D., Slembrouck, M., Van de Velde, S., Steendam, H., Veelaert, P., Kleihorst, R., Aghajan, H., and Philips, W. (2014a). Human mobility monitoring in very low resolution visual sensor network. Sensors, 14(11):20800-20824.
  6. Bo Bo, N., Deboeverie, F., Veelaert, P., and Philips, W. (2015). Real-time multi-people tracking by greedy likelihood maximization. In Proceedings of the 9th International Conference on Distributed Smart Cameras, ICDSC 7815, pages 32-37, New York, NY, USA. ACM. [doi:10.1145/2789116.2789125].
  7. Bo Bo, N., Deboeverie, F., Veelaert, P., and Philips, W. (2016). Multiple people tracking in smart camera networks by greedy joint-likelihood maximization. In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pages 602-609.
  8. Bo Bo, N., Gruenwedel, S., Van Hese, P., Nin˜o Castan˜eda, J., Van Haerenborgh, D., Van Cauwelaert, D., Veelaert, P., and Philips, W. (2012). Phd forum: Illumination-robust foreground detection for multicamera occupancy mapping. In Proceedings of the Sixth International Conference on Distributed Smart Cameras (ICDSC).
  9. Bo Bo, N., Grünwedel, S., Van Hese, P., Guan, J., NioCastaeda, J., Van Haerenborgh, D., Van Cauwelaert, D., Veelaert, P., and Philips, W. (2014b). Illuminationrobust people tracking using a smart camera network. In PROCEEDINGS OF SPIE, Intelligent Robots and Computer Vision XXXI: Algorithms and Techniques, volume 9025, pages 90250G-90250G-10.
  10. Bredereck, M., Jiang, X., Korner, M., and Denzler, J. (2012). Data association for multi-object tracking-bydetection in multi-camera networks. In Distributed Smart Cameras (ICDSC), 2012 Sixth International Conference on, pages 1-6.
  11. Du, W. and Piater, J. (2006). Data fusion by belief propagation for multi-camera tracking. In 2006 9th International Conference on Information Fusion, pages 1-8.
  12. Du, W. and Piater, J. (2007). Multi-camera people tracking by collaborative particle filters and principal axis-based integration. In Proceedings of the 8th Asian Conference on Computer Vision - Volume Part I, ACCV'07, pages 365-374, Berlin, Heidelberg. Springer-Verlag.
  13. Fleuret, F., Berclaz, J., Lengagne, R., and Fua, P. (2008). Multicamera people tracking with a probabilistic occupancy map. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(2):267-282. [doi:10.1109/TPAMI.2007.1174].
  14. Gruenwedel, S., Jelac?a, V., Nin˜o Castan˜eda, J., Van Hese, P., Van Cauwelaert, D., Van Haerenborgh, D., Veelaert, P., and Philips, W. (2014). Low-complexity scalable distributed multi-camera tracking of humans. ACM Transactions on Sensor Networks, 10(2).
  15. Grünwedel, S., Jelaa, V., Nin˜o Castan˜eda, J., Van Hese, P., Van Cauwelaert, D., Veelaert, P., and Philips, W. (2012). Decentralized tracking of humans using a camera network. In Roning, J. and Casasent, D., editors, PROCEEDINGS OF SPIE, Intelligent Robots and Computer Vision XXIX: Algorithms and Techniques, volume 8301. SPIE.
  16. Henriques, J. F., Caseiro, R., and Batista, J. (2011). Globally optimal solution to multi-object tracking with merged measurements. In IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, November 6-13, 2011, pages 2470-2477.
  17. Khan, S. and Shah, M. (2000). Tracking people in presence of occlusion. In In Asian Conference on Computer Vision, pages 1132-1137.
  18. Luo, R. C. and Kay, M. G. (1990). A tutorial on multisensor integration and fusion. In Industrial Electronics Society, 1990. IECON 7890., 16th Annual Conference of IEEE, pages 707-722 vol.1.
  19. Mittal, A. and Davis, L. S. (2003). M2tracker: A multiview approach to segmenting and tracking people in a cluttered scene. Int. J. Comput. Vision, 51(3):189- 203.
  20. Mori, T., Matsumoto, T., Shimosaka, M., Noguchi, H., and Sato, T. (2008). Multiple Persons Tracking with Data Fusion of Multiple Cameras and Floor Sensors Using Particle Filters. In Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications - M2SFA2 2008, Marseille, France. Andrea Cavallaro and Hamid Aghajan.
  21. Munoz-Salinas, R., Medina-Carnicer, R., Madrid-Cuevas, F., and Carmona-Poyato, A. (2009). Multi-camera people tracking using evidential filters. International Journal of Approximate Reasoning, 50(5):732 - 749. [doi:10.1016/j.ijar.2009.02.001].
  22. Nin˜o-Castan˜eda, J., Frías-Vel ázquez, A., Bo, N. B., Slembrouck, M., Guan, J., Debard, G., Vanrumste, B., Tuytelaars, T., and Philips, W. (2016). Scalable semi-automatic annotation for multi-camera person tracking. IEEE Transactions on Image Processing, 25(5):2259-2274.
  23. Yang, J., Vela, P. A., Shi, Z., and Teizer, J. (2009). Probabilistic multiple people tracking through complex situations. In 11th IEEE International Workshop on PETS, pages 79-86.
Download


Paper Citation


in Harvard Style

Bo Bo N., Veelaert P. and Philips W. (2017). Occlusion Robust Symbol Level Fusion for Multiple People Tracking . 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 216-226. DOI: 10.5220/0006127602160226


in Bibtex Style

@conference{visapp17,
author={Nyan Bo Bo and Peter Veelaert and Wilfried Philips},
title={Occlusion Robust Symbol Level Fusion for Multiple People Tracking},
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={216-226},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006127602160226},
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 - Occlusion Robust Symbol Level Fusion for Multiple People Tracking
SN - 978-989-758-227-1
AU - Bo Bo N.
AU - Veelaert P.
AU - Philips W.
PY - 2017
SP - 216
EP - 226
DO - 10.5220/0006127602160226