Application of Gibbs–Markov random field and Hopfield-type neural networks for detecting moving objects from video sequences captured by static camera

详细信息    查看全文

• 作者：Badri Narayan Subudhi ; Susmita Ghosh ; Ashish Ghosh
• 关键词：Markov random field ; MAP estimation ; Hopfield neural network
• 刊名：Soft Computing - A Fusion of Foundations, Methodologies and Applications
• 出版年：2015
• 出版时间：October 2015
• 年：2015
• 卷：19
• 期：10
• 页码：2769-2781
• 全文大小：1,445 KB
• 参考文献：Besag J (1986) On the statistical analysis of dirty pictures. J R Stat Soc Ser B (Methodol) 48(3):259-02MATH MathSciNet
  Bovic AL (2000) Image and video processing. Academic Press, New York
  Brekke E, Hallingstad O, Glattetre J (2012) Improved target tracking in the presence of wakes. IEEE Trans Aerosp Electron Syst 48(2):1005-017CrossRef
  Brutzer S, Hoferlin B, Heidemann G (2011) Evaluation of background subtraction techniques for video surveillance. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR), pp 1937-944
  Durucan E, Ebrahimi T (2001) Change detection and background extraction by linear algebra. Proc IEEE (Spec Issue Adv Video Surveill) 89(10):1368-381
  Elgammal A, Duraiswami R, Harwood D, Anddavis L (2002) Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proc IEEE 90(7):1151-163CrossRef
  Ghosh A, Pal NR, Pal SK (1991) Image segmentation using a neural network. Biol Cybern 66:151-58MATH CrossRef
  Ghosh A, Subudhi BN, Ghosh S (2012) Object detection from videos captured by moving camera by fuzzy edge incorporated Markov random field and local histogram matching. IEEE Trans Circuits Syst Video Technol 22(8):1127-135CrossRef
  Ghosh S, Bruzzone L, Patra S, Bovolo F, Ghosh A (2007) A context-sensitive technique for unsupervised change detection based on Hopfield-type neural networks. IEEE Trans Geosci Remote Sens 45(3):778-89CrossRef
  Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two state neurons. Proc Natl Acad Sci USA 81:3088-092CrossRef
  Kim K, Chalidabhongse TH, Harwood D, Davis L (2005) Real-time foreground-background segmentation using codebook model. Real-Time Imaging 11(3):167-56CrossRef
  Lehmann EL, Romano JP (1997) Testing statistical hypotheses. Springer, New York
  Li SZ (2001) Markov random field modeling in image analysis. Springer, JapanMATH CrossRef
  Liu Z, Sarkar S (2005) Effect of silhouette quality on hard problems in gait recognition. IEEE Trans Syst Man Cybern Part B Cybern 35(2):170-83CrossRef
  Manjunath BS, Simchony T, Chellappa R (1990) Stochastic and deterministic networks for texture segmentation. IEEE Trans Acoust Speech Signal Process 38(6):1039-049CrossRef
  Monnet A, Mittal A, Paragios N, Ramesh V (2003) Background modeling and subtraction of dynamic scenes. In: Proceedings of IEEE international conference on computer vision (ICCV), pp 1305-312
  Pal S, Dutta Majumder D (1986) Fuzzy mathematical approach to pattern recognition. Wiley, New York
  Piccardi M, Jan T (2004) Mean-shift background image modelling. In: Proceedings of international conference on image processing, vol 5, pp 3399-402
  Poppe C, Martens G, De Bruyne S, Lambert P, Van de Walle R (2008) Robust spatio-temporal multimodal background subtraction for video surveillance. Opt Eng 47(10):107-03
  Portela-Sotelo MA, Desseree é, Moreau JM, Shariat B, Beuve M (2012) 3-D model-based multiple-object video tracking for treatment room supervision. IEEE Trans Biomed Eng 59(2):562-70CrossRef
  Potts RB (1952) Some generalized order-disorder transformations. Proc Camb Philos Soc 48:106-09MATH CrossRef MathSciNet
  Radke RJ, Al-Kofahi Andra S (2005) Image change detection algorithms: a systematic survey. IEEE Trans Image Process 14(3):294-07
  Rajgopalan AN, Chellapa R (2001) Higher order statistic based detection of people/vehicle in images. Proc Indian Natl Sci Acad 67A:157-66
  Rojas R (1996) Neural networks. Springer, Berlin
  Shanmugam KS, Breipohl AM (1988) Random signals detection, estimation and data analysis. Wiley, New York
  Shapiro A, Nemirovski A (2005) On complexity of stochastic programming problems. In: Jeyakumar V, Rubinov A (eds) Continuous optimization, applied optimization, vol 99. Springer, US, pp 111-46CrossRef
  Singh A (1989) Review article digital change detection techniques using remotely-sensed data. Int J Remote Sens 10(6):989-003
  Stauffer C, Grimson WEL (1999) Adaptive background mixture models for real-time tracking. In: Proceedings of international conference on computer vision and pattern recognition, pp 2246-252
  Stauffer C, Grimson WEL (2000) Learning patterns of activity using real time tracking. IEEE Trans Pattern Anal Mach Intell 22(8):747-67
  Subudhi BN, Ghosh S, Ghosh A (2013) Change detection for moving object segmentation with robust background construction under Wronskian framework. Mach Vis Appl 24(4):795-09
  Subudhi BN, Nanda PK, Ghosh A (2011) A change information based fast algorithm for video object detection and tracking. IEEE Trans Circuits Syst Video Technol 21(7):993-004CrossRef
  Szeliski R, Zabih R, Scharstein D, Veksler O, Kolmogorov V, Agarwala A, Tappen M, Rother C (2008) A comparative study of energy minimization methods for Markov random fields with smoothness-based priors. IEEE Trans Pattern Anal Mach Intell 30(6):1068-080Cross
• 作者单位：Badri Narayan Subudhi (1)
  Susmita Ghosh (2)
  Ashish Ghosh (3)
  
  1. Department of Electronics and Communication Engineering, National Institute of Technology, Farmagudi, Ponda, 403401, Goa, India
  2. Department of Computer Science and Engineering, Jadavpur University, Kolkata, 700032, India
  3. Machine Intelligence Unit, Indian Statistical Institute, Kolkata, 700108, India
  
• 刊物类别：Engineering
• 刊物主题：Numerical and Computational Methods in Engineering
  Theory of Computation
  Computing Methodologies
  Mathematical Logic and Foundations
  Control Engineering
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1433-7479

文摘

In this article, we propose a moving objects detection scheme using Gibbs–Markov random field(GMRF) and Hopfield-type neural network (HTNN) in expectation maximization (EM) framework for video sequences captured by static camera. In the considered technique, the background model is built by considering a running Gaussian average over few past frames. The change vector analysis (CVA) scheme is followed on the considered target frame and the constructed reference frame to generate a difference image. The moving objects in target frame are detected by segmenting the difference image into two classes: changed and unchanged, where the changed class represents moving object regions and the unchanged class the background regions. For segmentation, we have modeled the CVA generated difference image with GMRF and the segmentation problem is solved using the maximum a posteriori probability (MAP) estimation principle. The MAP estimator is found to be exponential in nature; and thus a modified HTNN is exploited for estimating the MAP. The parameters of the GMRF model are estimated using EM algorithm. Experiments are carried out on three video sequences. Results of the proposed change detection scheme are compared with those of the codebook-based background subtraction and GMRF model with graph-cut schemes. It is found that the proposed technique provides better results. Keywords Markov random field MAP estimation Hopfield neural network