Neural Network Approach to Background Modeling for Video Object Segmentation

This paper presents a novel background modeling and subtraction approach for video object segmentation. A neural network (NN) architecture is proposed to form an unsupervised Bayesian classifier for this application domain. The constructed classifier efficiently handles the segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed NN serve as a model of the background and are temporally updated to reflect the observed statistics of background. The segmentation performance of the proposed NN is qualitatively and quantitatively examined and compared to two extant probabilistic object segmentation algorithms, based on a previously published test pool containing diverse surveillance-related sequences. The proposed algorithm is parallelized on a subpixel level and designed to enable efficient hardware implementation.

[1]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[2]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[3]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Mohamad T. Musavi,et al.  On the Generalization Ability of Neural Network Classifiers , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  David S. Touretzky,et al.  Optical Chinese character recognition using probabilistic neural networks , 1997, Pattern Recognit..

[6]  Borko Furht,et al.  A neural network approach to bayesian background modeling for video object segmentation , 2006, VISAPP.

[7]  Gonzalo Pajares,et al.  A Hopfield Neural Network for Image Change Detection , 2006, IEEE Transactions on Neural Networks.

[8]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[9]  Tim Ellis,et al.  Object detection and tracking in an open and dynamic world , 2001 .

[10]  Mahmood R. Azimi-Sadjadi,et al.  Temporal updating scheme for probabilistic neural network with application to satellite cloud classification - further results , 2001, IEEE Trans. Neural Networks.

[11]  Qi Tian,et al.  Foreground object detection from videos containing complex background , 2003, MULTIMEDIA '03.

[12]  Xiaodong Gu,et al.  Image shadow removal using pulse coupled neural network , 2005, IEEE Transactions on Neural Networks.

[13]  Borko Furht,et al.  A Hybrid Color-Based Foreground Object Detection Method for Automated Marine Surveillance , 2005, ACIVS.

[14]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Anthony Zaknich.  General Regression Neural Network , 2003 .

[16]  Bayya Yegnanarayana,et al.  Supervised texture classification using a probabilistic neural network and constraint satisfaction model , 1998, IEEE Trans. Neural Networks.

[17]  Haizhou Ai,et al.  Moving object detection and tracking based on background subtraction , 2001, International Symposium on Multispectral Image Processing and Pattern Recognition.

[18]  K. P. Karmann,et al.  Moving object recognition using an adaptive background memory , 1990 .

[19]  Qi Tian,et al.  Statistical modeling of complex backgrounds for foreground object detection , 2004, IEEE Transactions on Image Processing.

[20]  Hon Keung Kwan.  One-layer feedforward neural network for fast maximum/minimum determination , 1992 .

[21]  Stefanos D. Kollias,et al.  An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture , 2003, IEEE Trans. Neural Networks.

[22]  Nikolas P. Galatsanos,et al.  A spatially constrained mixture model for image segmentation , 2005, IEEE Transactions on Neural Networks.

[23]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[24]  Liang-Gee Chen,et al.  Fast video segmentation algorithm with shadow cancellation, global motion compensation, and adaptive threshold techniques , 2004, IEEE Transactions on Multimedia.

[25]  Mahmood R. Azimi-Sadjadi,et al.  Temporal updating scheme for probabilistic neural network with application to satellite cloud classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[26]  J. Wolfowitz,et al.  An Introduction to the Theory of Statistics , 1951, Nature.

[27]  Paul L. Rosin.  Thresholding for change detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[28]  B. McKay,et al.  Probabilistic neural network array architecture for ECG classification , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[29]  Terrance E. Boult,et al.  Frame-rate omnidirectional surveillance and tracking of camouflaged and occluded targets , 1999, Proceedings Second IEEE Workshop on Visual Surveillance (VS'99) (Cat. No.98-89223).