A Framework for Feature Selection for Background Subtraction

Background subtraction is a widely used paradigm to detect moving objects in video taken from a static camera and is used for various important applications such as video surveillance, human motion analysis, etc. Various statistical approaches have been proposed for modeling a given scene background. However, there is no theoretical framework for choosing which features to use to model different regions of the scene background. In this paper we introduce a novel framework for feature selection for background modeling and subtraction. A boosting algorithm, namely RealBoost, is used to choose the best combination of features at each pixel. Given the probability estimates from a pool of features calculated by Kernel Density Estimate (KDE) over a certain time period, the algorithm selects the most useful ones to discriminate foreground objects from the scene background. The results show that the proposed framework successfully selects appropriate features for different parts of the image.

[1]  Nikos Paragios,et al.  Motion-based background subtraction using adaptive kernel density estimation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[2]  S. Varadhan,et al.  A probabilistic approach to , 1974 .

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

[4]  Robert Pless,et al.  Spatio-temporal Background Models for Outdoor Surveillance , 2005, EURASIP J. Adv. Signal Process..

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

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

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

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

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

[10]  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).

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

[12]  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..

[13]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[14]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

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

[16]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

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

[18]  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.

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

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