Statistical background subtraction based on imbalanced learning

In this paper, we study the class imbalance problem in statistical background subtraction. Firstly, we discuss the imbalance essence in background subtraction, and conclude that foreground and background are inherently imbalanced. Secondly, following the imbalanced learning strategy in machine learning, we present a spatio-temporal over-sampling method to resolve the class imbalance in background subtraction. Our method densely generate synthesized foreground samples in compact 3D spatio-temporal domain. Those generated samples could reduce the imbalance level between foreground and background from both quantity and quality, and therefore contribute to improvement of detection performance. We also define a new index to measure the change of imbalance level during over-sampling. Experiments are conducted on public datasets to demonstrate the effectiveness of our method.

[1]  Gerhard Rigoll,et al.  Background segmentation with feedback: The Pixel-Based Adaptive Segmenter , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[2]  Xiang Ma,et al.  Learning a background model for change detection , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[3]  Benjamin Höferlin,et al.  Evaluation of background subtraction techniques for video surveillance , 2011, CVPR 2011.

[4]  Carla E. Brodley,et al.  Class Imbalance, Redux , 2011, 2011 IEEE 11th International Conference on Data Mining.

[5]  Rubén Heras Evangelio,et al.  Complementary background models for the detection of static and moving objects in crowded environments , 2011, 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[6]  Tao Xiang,et al.  Background Subtraction with Dirichlet Processes , 2012, ECCV.

[7]  Ferdinand van der Heijden,et al.  Efficient adaptive density estimation per image pixel for the task of background subtraction , 2006, Pattern Recognit. Lett..

[8]  Lucia Maddalena,et al.  A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications , 2008, IEEE Transactions on Image Processing.

[9]  Yaser Sheikh,et al.  Bayesian modeling of dynamic scenes for object detection , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Kurt Keutzer,et al.  Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow , 2010, ECCV.

[11]  Gary M. Weiss.  Mining with rarity: a unifying framework , 2004, SKDD.

[12]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[13]  L. Davis,et al.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance , 2002, Proc. IEEE.

[14]  Yunqian Ma,et al.  Imbalanced Learning: Foundations, Algorithms, and Applications , 2013 .

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

[16]  Rainer Stiefelhagen,et al.  Improving foreground segmentations with probabilistic superpixel Markov random fields , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.