A Graph-based MAP Solution for Multi-person Tracking using Multi-camera Systems

Xiaoyan Jiang, Marco Körner, Daniel Haase, Joachim Denzler

Abstract

Accurate multi-person tracking under complex conditions is an important topic in computer vision with various application scenarios such as visual surveillance. Taking into account the difficulties caused by 2D occlusions, missing detections, and false positives, we propose a two-stage graph-based object tracking-by-detection approach using multiple calibrated cameras. Firstly, data association is formulated into a maximum a posteriori (MAP) problem. After transformation, we show that this single MAP problem is equivalent of finding min-cost paths in a two-stage directed acyclic graph. The first graph aims to extract an optimal set of tracklets based on the hypotheses on the ground plane by using both 2D appearance feature and 3D spatial distances. Subsequently, the tracklets are linked into complete tracks in the second graph utilizing spatial and temporal distances. This results in a global optimization over all the 2D detections obtained from multiple cameras. Finally, the experimental results on three difficult sequences of the PETS’09 dataset with comparison to the state-of-the-art methods show the precision and consistency of our approach.

References

  1. Andriyenko, A. and Schindler, K. (2011). Multi-target tracking by continuous energy minimization. In CVPR, pages 1265-1272.
  2. Berclaz, J., Fleuret, F., Turetken, E., and Fua, P. (2011). Multiple object tracking using k-shortest paths optimization. TPAMI, 33:1806-1819.
  3. Bernardin, K. and Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: The clear mot metrics. EJIVP, 246309.
  4. Bredereck, M., Jiang, X., Körner, M., and Denzler, J. (2012). Data association for multi-object tracking-by-detection in multi-camera networks. In ICDSC.
  5. Breitenstein, M. D., Reichlin, F., Leibe, B., Koller-Meier, E., and Gool, L. V. (2011). Online muti-person trackingby-detection from a single, uncalibrated camera. PAMI, 33:1820 - 1833.
  6. Collins, R. T. (2012). Multitarget data association with higher-order motion models. In CVPR.
  7. Dijkstra, E. W. (1959). A note on two problems in connexion with graphs. NUMERISCHE MATHEMATIK, 1:269- 271.
  8. Felzenszwalb, P., Girshick, R., and McAllester, D. (2010). Cascade object detection with deformable part models. In CVPR.
  9. Ferryman, J. and Shahrokni, A. (2009). Pets2009: Dataset and challenge. In 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS-Winter).
  10. Fleuret, F., Berclaz, J., Lengagne, R., and Fua, P. (2008). Multi-camera people tracking with a probabilistic occupancy map. TPAMI, 30:267-282.
  11. Henriques, J. F., Caseiro, R., and Batista, J. (2011). Globally optimal solution to multi-object tracking with merged measurements. In ICCV.
  12. Hofmann, M., Wolf, D., and Rigoll, G. (2013). Hypergraphs for joint multi-view reconstruction and multi-object tracking. In CVPR.
  13. Huang, C., Wu, B., and Nevatia, R. (2008). Robust object tracking by hierarchical association of detection responses. In ECCV, pages 788-801.
  14. J. Yang, Z. Shi, P. V. and Teizer, J. (2009). Probabilistic multiple people tracking through complex situations. In IEEE Workshop Performance Evaluation of Tracking and Surveillance.
  15. Jiang, X., Haase, D., K örner, M., Bothe, W., and Denzler, J. (2013). Accurate 3d multi-marker tracking in x-ray cardiac sequences using a two-stage graph modeling approach. In the 15th Conference on Computer Analysis of Images and Patterns (CAIP).
  16. Jiang, X., Rodner, E., and Denzler, J. (2012). Multiperson tracking-by-detection based on calibrated multicamera systems. In ICCVG, pages 743-751.
  17. Leal-Taixé, L., Pons-Moll, G., and Rosenhahn, B. (2012). Branch-and-price global optimization for multi-view multi-target tracking. In CVPR, pages 1987-1994.
  18. Satoh, Y., Okatani, T., and Deguchi, K. (2004). A colorbased tracking by kalman particle filter. In ICPR, pages 502-505.
  19. Wu, Z., Kunz, T. H., and Betke, M. (2011). Efficient track linking methods for track graphs using network-flow and set-cover techniques. In CVPR, pages 1185-1192.
  20. Wu, Z., Thangali, A., Sclaroff, S., and Betke, M. (2012). Coupling detection and data association for multiple object tracking. In CVPR.
  21. Xing, J., Ai, H., and Lao, S. (2009). Multi-object tracking through occlusions by local tracklets filtering and global tracklets association with detection responses. In CVPR.
  22. Zhang, L., Li, Y., and Nevatia, R. (2008). Global data association for multi-object tracking using network flows. In CVPR.
Download


Paper Citation


in Harvard Style

Jiang X., Körner M., Haase D. and Denzler J. (2014). A Graph-based MAP Solution for Multi-person Tracking using Multi-camera Systems . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 343-350. DOI: 10.5220/0004690103430350


in Bibtex Style

@conference{visapp14,
author={Xiaoyan Jiang and Marco Körner and Daniel Haase and Joachim Denzler},
title={A Graph-based MAP Solution for Multi-person Tracking using Multi-camera Systems},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={343-350},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004690103430350},
isbn={978-989-758-009-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - A Graph-based MAP Solution for Multi-person Tracking using Multi-camera Systems
SN - 978-989-758-009-3
AU - Jiang X.
AU - Körner M.
AU - Haase D.
AU - Denzler J.
PY - 2014
SP - 343
EP - 350
DO - 10.5220/0004690103430350