Spatiotemporal Gaussian mixture model to detect moving objects in dynamic scenes

The Gaussian mixture model (GMM) is an important metric for moving objects segmentation and is fit to deal with the gradual changes of illumination and the repetitive motions of scene elements. However, the performance of the GMM may be plagued by the complex motion of the dynamic background such as waving trees and flags fluttering. A spatiotemporal Gaussian mixture model (STGMM) is proposed to handle the complex motion of the background by considering every background pixel to be fluctuating both in intensity and in its neighboring region. A new matching rule is defined to incorporate the spatial information. Experimental results on typical scenes show that STGMM can segment the moving objects correctly in complex scenes. Quantitative evaluations demonstrate that the proposed STGMM performs better than GMM.

[1]  Y. Sun,et al.  Hierarchical GMM to handle sharp changes in moving object detection , 2004 .

[2]  Joachim M. Buhmann,et al.  Topology Free Hidden Markov Models: Application to Background Modeling , 2001, ICCV.

[3]  Til Aach,et al.  Detection and recognition of moving objects using statistical motion detection and Fourier descriptors , 2003, 12th International Conference on Image Analysis and Processing, 2003.Proceedings..

[4]  Reinhard Klette,et al.  Robust background subtraction and maintenance , 2004, ICPR 2004.

[5]  Michael Harville,et al.  A Framework for High-Level Feedback to Adaptive, Per-Pixel, Mixture-of-Gaussian Background Models , 2002, ECCV.

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

[7]  Dongxiang Zhou,et al.  Modified GMM background modeling and optical flow for detection of moving objects , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[8]  Stuart J. Russell,et al.  Image Segmentation in Video Sequences: A Probabilistic Approach , 1997, UAI.

[9]  Qiuming Zhu,et al.  Median model for background subtraction in intelligent transportation system , 2004, IS&T/SPIE Electronic Imaging.

[10]  Nikos Paragios,et al.  Background modeling and subtraction of dynamic scenes , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[11]  Luigi di Stefano,et al.  A change-detection algorithm based on structure and colour , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[12]  Naoya Ohta,et al.  A statistical approach to background subtraction for surveillance systems , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[13]  Richard Bowden,et al.  A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes , 2003, Image Vis. Comput..

[14]  I. Haritaoglu,et al.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance , 2002 .

[15]  Robert Pless,et al.  Evaluation of local models of dynamic backgrounds , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[16]  Zoran Zivkovic,et al.  Improved adaptive Gaussian mixture model for background subtraction , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[17]  Kyu-Won Lee,et al.  Moving object segmentation based on statistical motion model , 1999 .

[18]  Kazuhiko Sumi,et al.  Background subtraction based on cooccurrence of image variations , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

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

[20]  Wei Zhang,et al.  Moving vehicles segmentation based on Bayesian framework for Gaussian motion model , 2006, Pattern Recognit. Lett..

[21]  Luca Lombardi,et al.  Multi-module switching and fusion for robust video surveillance , 2003, 12th International Conference on Image Analysis and Processing, 2003.Proceedings..

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

[23]  Sylvain Ballandras,et al.  Experimental measurements of velocities and temperature effects for SAWs on Y-rotated cuts of langasite , 1999 .