Motion-based background subtraction using adaptive kernel density estimation

Background modeling is an important component of many vision systems. Existing work in the area has mostly addressed scenes that consist of static or quasi-static structures. When the scene exhibits a persistent dynamic behavior in time, such an assumption is violated and detection performance deteriorates. In this paper, we propose a new method for the modeling and subtraction of such scenes. Towards the modeling of the dynamic characteristics, optical flow is computed and utilized as a feature in a higher dimensional space. Inherent ambiguities in the computation of features are addressed by using a data-dependent bandwidth for density estimation using kernels. Extensive experiments demonstrate the utility and performance of the proposed approach.

[1]  L. Breiman,et al.  Variable Kernel Estimates of Multivariate Densities , 1977 .

[2]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[3]  Ian Abramson.  On Bandwidth Variation in Kernel Estimates-A Square Root Law , 1982 .

[4]  Jitendra Malik,et al.  Robust Multiple Car Tracking with Occlusion Reasoning , 1994, ECCV.

[5]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .

[6]  Lucia Ballerini,et al.  Time-Varying Image Processing and Moving Object Recognition , 1997 .

[7]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

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

[9]  W. Eric L. Grimson,et al.  Using adaptive tracking to classify and monitor activities in a site , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[10]  Eero P. Simoncelli.  Bayesian multi-scale differential optical flow , 1999 .

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

[12]  Alex Pentland,et al.  A Bayesian Computer Vision System for Modeling Human Interactions , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Heinrich Niemann,et al.  Statistical modeling and performance characterization of a real-time dual camera surveillance system , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[14]  Larry S. Davis,et al.  Non-parametric Model for Background Subtraction , 2000, ECCV.

[15]  Xiang Gao,et al.  Error analysis of background adaption , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[16]  Haifeng Chen,et al.  Robust Computer Vision through Kernel Density Estimation , 2002, ECCV.

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

[18]  Mubarak Shah,et al.  A hierarchical approach to robust background subtraction using color and gradient information , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[19]  Dorin Comaniciu,et al.  Nonparametric information fusion for motion estimation , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

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

[21]  Stan Sclaroff,et al.  Segmenting foreground objects from a dynamic textured background via a robust Kalman filter , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[22]  P. Anandan,et al.  A computational framework and an algorithm for the measurement of visual motion , 1987, International Journal of Computer Vision.

[23]  Stefano Soatto,et al.  Dynamic Textures , 2003, International Journal of Computer Vision.

[24]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.