Advertisement

Inter-camera Association of Multi-target Tracks by On-Line Learned Appearance Affinity Models

  • Cheng-Hao Kuo
  • Chang Huang
  • Ram Nevatia
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6311)

Abstract

We propose a novel system for associating multi-target tracks across multiple non-overlapping cameras by an on-line learned discriminative appearance affinity model. Collecting reliable training samples is a major challenge in on-line learning since supervised correspondence is not available at runtime. To alleviate the inevitable ambiguities in these samples, Multiple Instance Learning (MIL) is applied to learn an appearance affinity model which effectively combines three complementary image descriptors and their corresponding similarity measurements. Based on the spatial-temporal information and the proposed appearance affinity model, we present an improved inter-camera track association framework to solve the “target handover” problem across cameras. Our evaluations indicate that our method have higher discrimination between different targets than previous methods.

Keywords

Training Sample Color Histogram Appearance Model Equal Error Rate Multiple Instance Learn 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Porikli, F.: Inter-camera color calibration by correlation model function. In: ICIP (2003)Google Scholar
  2. 2.
    Javed, O., Shafique, K., Shah, M.: Appearance modeling for tracking in multiple non-overlapping cameras. In: CVPR (2005)Google Scholar
  3. 3.
    Chen, K.W., Lai, C.C., Hung, Y.P., Chen, C.S.: An adaptive learning method for target tracking across multiple cameras. In: CVPR (2008)Google Scholar
  4. 4.
    Dietterich, T.G., Lathrop, R.H., Lozano-Perez, T., Pharmaceutical, A.: Solving the multiple-instance problem with axis-parallel rectangles. Artificial Intelligence 89, 31–71 (1997)zbMATHCrossRefGoogle Scholar
  5. 5.
    Viola, P., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. In: NIPS (2005)Google Scholar
  6. 6.
    Babenko, B., Yang, M.H., Belongie, S.: Visual Tracking with Online Multiple Instance Learning. In: CVPR (2009)Google Scholar
  7. 7.
    Cai, Q., Aggarwal, J.: Tracking human motion in structured environments using a distributed-camera system. IEEE Tran. on PAMI 21, 1241–1247 (1999)Google Scholar
  8. 8.
    Collins, R., Lipton, A., Fujiyoshi, H., Kanade, T.: Algorithms for cooperative multisensor surveillance. Proceedings of the IEEE 89, 1456–1477 (2001)CrossRefGoogle Scholar
  9. 9.
    Khan, S., Shah, M.: Consistent labeling of tracked objects in multiple cameras with overlapping fields of view. IEEE Tran. on PAMI 25, 1355–1360 (2003)Google Scholar
  10. 10.
    Huang, T., Russell, S.: Object identification in a bayesian context. In: IJCAI (1997)Google Scholar
  11. 11.
    Pasula, H., Russell, S., Ostl, M., Ritov, Y.: Tracking many objects with many sensors. In: IJCAI (1999)Google Scholar
  12. 12.
    Kettnaker, V., Zabih, R.: Bayesian multi-camera surveillance. In: CVPR (1999)Google Scholar
  13. 13.
    Javed, O., Rasheed, Z., Shafique, K., Shah, M.: Tracking across multiple cameraswith disjoint views. In: ICCV (2003)Google Scholar
  14. 14.
    Dick, A.R., Brooks, M.J.: A stochastic approach to tracking objects across multiple cameras. In: Australian Conference on Artificial Intelligence (2004)Google Scholar
  15. 15.
    Makris, D., Ellis, T., Black, J.: Bridging the gaps between cameras. In: CVPR (2004)Google Scholar
  16. 16.
    Gilbert, A., Bowden, R.: Tracking objects across cameras by incrementally learning inter-camera colour calibration and patterns of activity. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 125–136. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  17. 17.
    Sturges, J., Whitfield, T.: Locating basic colour in the munsell space. Color Research and Application 20, 364–376 (1995)CrossRefGoogle Scholar
  18. 18.
    Song, B., Roy-Chowdhury, A.: Robust tracking in a camera network: A multi-objective optimization framework. IEEE Journal of Selected Topics in Signal Processing 2, 582–596 (2008)CrossRefGoogle Scholar
  19. 19.
    Song, B., Roy-Chowdhury, A.K.: Stochastic adaptive tracking in a camera network. In: ICCV (2007)Google Scholar
  20. 20.
    Huang, C., Wu, B., Nevatia, R.: Robust object tracking by hierarchical association of detection responses. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 788–801. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  21. 21.
    Tuzel, O., Porikli, F., Meer, P.: Region covariance: A fast descriptor for detection and classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 589–600. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  22. 22.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  23. 23.
    Mason, L., Baxter, J., Bartlett, P., Frean, M.: Boosting algorithms as gradient descent in function space (1999)Google Scholar
  24. 24.
    Kuo, C.H., Huang, C., Nevatia, R.: Multi-target tracking by on-line learned discriminative appearance models. In: CVPR (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Cheng-Hao Kuo
    • 1
  • Chang Huang
    • 1
  • Ram Nevatia
    • 1
  1. 1.University of Southern CaliforniaLos AngelesUSA

Personalised recommendations