Dynamic Markov Random Field Model for Visual Tracking

  • Daehwan Kim
  • Ki-Hong Kim
  • Gil-Haeng Lee
  • Daijin Kim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7585)


We propose a new dynamic Markov random field (DMRF) model to track a heavily occluded object. The DMRF model is a bidirectional graph which consists of three random variables: hidden, observation, and validity. It temporally prunes invalid nodes and links edges among valid nodes by verifying validities of all nodes. In order to apply the proposed DMRF model to the object tracking framework, we use an image block lattice model exactly correspond to nodes and edges in the DMRF model and utilize the mean-shift belief propagation (MSBP). The proposed object tracking method using the DMRF surprisingly tracks a heavily occluded object even if the occluded region is more than 70~80%. Experimental results show that the proposed tracking method gives good tracking performance even on various tracking image sequences(ex. human and face) with heavy occlusion.


Markov random field Dynamic Markov random field Visual tracking 


  1. 1.
    Wu, B., Nevatia, R.: Detection and segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses. International Journal of Computer Vision 82, 185–204 (2009)CrossRefGoogle Scholar
  2. 2.
    Senior, A., Hampapur, A., Tian, Y., Brown, L.: Appearance models for occlusion handling. Image and Vision Computing 24, 1233–1243 (2006)CrossRefGoogle Scholar
  3. 3.
    Hu, W., Zhou, X., Hu, M., Maybank, S.: Occlusion reasoning for tracking multiple people. IEEE Transactions on Circuits and Systems for Video Technology 19, 114–121 (2009)CrossRefGoogle Scholar
  4. 4.
    Zhao, T., Nevatia, R.: Tracking multiple humans in complex situations. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 1208–1221 (2004)CrossRefGoogle Scholar
  5. 5.
    Mittal, A., Davis, L.S.: M2tracker: A multi-view approach to segmenting and tracking people in a cluttered scene using region-based stereo. International Journal of Computer Vision 51, 189–203 (2003)CrossRefGoogle Scholar
  6. 6.
    Lin, Z., Davis, L., Doermann, D., Dementhon, D.: An interactive approach to pose-assisted and appearance-based segmentation of humans. In: Proc. of IEEE International Conferenece on Computer Vision, pp. 1–8 (2007)Google Scholar
  7. 7.
    Ross, D., Lim, J., Lin, R.: Incremental learning for robust visual tracking. International Journal of Computer Vision 77, 125–141 (2008)CrossRefGoogle Scholar
  8. 8.
    Mei, X., Ling, H.: Beyond semi-supervised tracking: Tracking should be as simple as detection, but not simpler than recognition. In: Proc. of IEEE International Conferenece on Computer Vision Workshop, pp. 1409–1416 (2009)Google Scholar
  9. 9.
    Park, M., Liu, Y., Collins, R.: Efficient mean shift belief propagation for vision tracking. In: Proc. of IEEE Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  10. 10.
    Lin, W., Liu, Y.: A lattice-based mrf model for dynamic near-regular texture tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 777–792 (2007)CrossRefGoogle Scholar
  11. 11.
    Liu, J., Liu, Y.: Multi-target tracking of time-varying spatial patterns. In: Proc. of IEEE Computer Vision and Pattern Recognition, pp. 1839–1846 (2010)Google Scholar
  12. 12.
    Coughlan, J., Huiying, S.: Shape matching with belief propagation: Using dynamic quantization to accomodate occlusion and clutter. In: Proc. of IEEE Computer Vision and Pattern Recognition Workshop (2004)Google Scholar
  13. 13.
    Felzenszwalb, P., Huttenlocher, D.: Efficient belief propagation for early vision. International Journal of Computer Vision 70, 41–54 (2006)CrossRefGoogle Scholar
  14. 14.
    Yedidia, J., Freeman, W., Weiss, Y.: Understanding belief propagation and its generalizations. In: International Joint Conference on Artificial Intelligence (2001)Google Scholar
  15. 15.
    Park, M., Brocklehurst, K., Collins, R., Liu, Y.: Deformed lattice detection in real-world images using mean-shift belief propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence 31, 1804–1816 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Daehwan Kim
    • 1
  • Ki-Hong Kim
    • 1
  • Gil-Haeng Lee
    • 1
  • Daijin Kim
    • 2
  1. 1.Creative Content Research LaboratoryETRIDaejeonRepublic of Korea
  2. 2.Department of Computer Science and EngineeringPOSTECHPohangRepublic of Korea

Personalised recommendations