An Improved Approach for Moving Object Detection Based on Markov Random Field

  • Buyu Xu
  • Hao Tang
  • Lei Zhou
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 113)


Due to utilization of the relativity of every pixel of an image, the Markov random field (MRF) model is effective in solving the problem of detecting moving objects under a complex background. In this paper, the bits-segmentation of inter-frame difference images is used as the label field of MRF, and the compatibility function related to such labels and the hidden states is provided, so that an improved detection method for moving objects is proposed based on MRF. Compared with the traditional MRF method, the proposed approach can avoid the threshold selection process for obtaining the label field, which is a sensitive issue that may affect the detection negatively. The experiment results show that this approach is more effective and has a better adaptability than traditional methods.


Markov random filed Inter-frame difference images Moving object detecting Belief propagation 


  1. 1.
    Lipton A, Fujiyoshi H, Patil R (1998) Moving target classification and tracking from real-time video[C]. IEEE workshop on applications of computer vision, pp 8–14Google Scholar
  2. 2.
    Wang L-L, Li W, Gao X-R (2010) The research of moving object detection algorithm in video images. J Microcomput Inf 16(6):147–149Google Scholar
  3. 3.
    Yin Z, Collins R (2007) Belief propagation in a 3D spatio-temporal MRF for moving object detection[C]. In: IEEE conference on computer vision and pattern recognition, pp 1–8Google Scholar
  4. 4.
    Linghu Y-F, Guo X-M, Wang S-T (2007) Research on motion segmentation based on Markov random field models. J Comput Eng Appl 43(14):56–59Google Scholar
  5. 5.
    Long M, Wang L-P, Shen Z-K (2010) A slow-moving-object segmentation technology based on MRF under complex background. J Signal Process 26(6):911–916Google Scholar
  6. 6.
    Yedidia JS, Freeman WT, Weiss Y (2003) Understanding belief propagation and its generalizations[C]. In: Exploring artificial intelligence in the new millennium. Morgan Kaufmann Publishers, USA, pp 239–269Google Scholar
  7. 7.
    Boykov Y, Veksler O, Zabih R (2001) Fast approximate energy minimization via graph cuts. J IEEE Trans Pattern Analysis Mach Intell 23(11):1222–1239CrossRefGoogle Scholar
  8. 8.
    Tappen M, Freeman W (2003) Comparison of graph cuts with belief propagation for stereo using identical MRF parameters[C], In: ICCV, pp 900–907Google Scholar
  9. 9.
    Gonzalez C, Woods E (2003) Digital image processing[M], Electronic Industry Press, Beijing pp 485–486Google Scholar
  10. 10.
    Zhan J.-F, Qi F.-H, Wang H.-L (2000) Moving object segmentation technology based on spatial-temporal Markov random field[J]. J of China Inst Commun 21(11):63–68Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2012

Authors and Affiliations

  1. 1.School of Computer and InformationHefei University of TechnologyHefeiChina
  2. 2.Engineering Research Center of Safety Critical Industry Measure and Control TechnologyMinistry of EducationHefeiChina

Personalised recommendations