Coarse-to-fine sample-based background subtraction for moving object detection

Abstract Background subtraction is crucial for detecting moving objects in videos. However, most background subtraction methods usually fail to deal well with illumination changes, static foreground, ghosts, and dynamic background. In this paper, we propose an efficient coarse-to-fine sample-based algorithm to address these issues simultaneously. Specifically, a rough motion region estimation method, is first proposed by combining an improved frame difference method, the block-based image partition algorithm and multi-scale region-based technique to locate the possible area of moving objects. It can compensate the global illumination change and suppress dynamic background. Then, an improved Vibe algorithm with adaptive distance threshold and time sub-sampling factor parameters for each pixel is proposed to detect precise moving objects. It can not only retain static foreground for a long time while eliminating ghosts rapidly, but also detect camouflaged foreground efficiently. Experimental results demonstrate that our proposed algorithm can extract moving objects more accurately with less time cost than several state-of-the-art background subtraction approaches.

[1]  Rubén Heras Evangelio,et al.  Adaptively Splitted GMM With Feedback Improvement for the Task of Background Subtraction , 2014, IEEE Transactions on Information Forensics and Security.

[2]  Z. Zivkovic.  Improved adaptive Gaussian mixture model for background subtraction , 2004, ICPR 2004.

[3]  G. Sreelekha,et al.  Sample-based integrated background subtraction and shadow detection , 2017, IPSJ Transactions on Computer Vision and Applications.

[4]  Fatih Murat Porikli,et al.  CDnet 2014: An Expanded Change Detection Benchmark Dataset , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

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

[6]  Henri Nicolas,et al.  Video traffic analysis using scene and vehicle models , 2014, Signal Process. Image Commun..

[7]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[8]  Rita Cucchiara,et al.  Detecting Moving Objects, Ghosts, and Shadows in Video Streams , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Pascal Fua,et al.  Making Background Subtraction Robust to Sudden Illumination Changes , 2008, ECCV.

[10]  Guillaume-Alexandre Bilodeau,et al.  A Multiscale Region-Based Motion Detection and Background Subtraction Algorithm , 2010, Sensors.

[11]  Helmut E. Bez,et al.  A practical adaptive approach for dynamic background subtraction using an invariant colour model and object tracking , 2005, Pattern Recognit. Lett..

[12]  Huiyu Zhou,et al.  Region-based Mixture of Gaussians modelling for foreground detection in dynamic scenes , 2015, Pattern Recognit..

[13]  Larry S. Davis,et al.  Real-time foreground-background segmentation using codebook model , 2005, Real Time Imaging.

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

[15]  F. Xavier Roca,et al.  A coarse-to-fine approach for fast deformable object detection , 2015, Pattern Recognit..

[16]  Guillaume-Alexandre Bilodeau,et al.  SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity , 2015, IEEE Transactions on Image Processing.

[17]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Nicolas Martel-Brisson,et al.  Moving cast shadow detection from a Gaussian mixture shadow model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Guillaume-Alexandre Bilodeau,et al.  Universal Background Subtraction Using Word Consensus Models , 2016, IEEE Transactions on Image Processing.

[20]  Zhi Zeng,et al.  Adaptive maintenance scheme for codebook-based dynamic background subtraction , 2016, Comput. Vis. Image Underst..

[21]  Y. Li,et al.  Robust 2D Principal Component Analysis: A Structured Sparsity Regularized Approach , 2015, IEEE Transactions on Image Processing.

[22]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Wonjun Kim,et al.  Illumination-Invariant Background Subtraction: Comparative Review, Models, and Prospects , 2017, IEEE Access.

[24]  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).

[25]  Antoine Vacavant,et al.  A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos , 2014, Comput. Vis. Image Underst..

[26]  Xiaowei Zhou,et al.  Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Sahin Isik,et al.  SWCD: a sliding window and self-regulated learning-based background updating method for change detection in videos , 2018, J. Electronic Imaging.

[28]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Marc Van Droogenbroeck,et al.  Background subtraction: Experiments and improvements for ViBe , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

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

[31]  Hüseyin Demirel,et al.  Moving object detection using an adaptive background subtraction method based on block-based structure in dynamic scene , 2018, Optik.

[32]  Hironobu Fujiyoshi,et al.  Moving target classification and tracking from real-time video , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[33]  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.

[34]  Thierry Bouwmans,et al.  Traditional and recent approaches in background modeling for foreground detection: An overview , 2014, Comput. Sci. Rev..

[35]  Mark A. Richardson,et al.  Efficient visual object detection with spatially global Gaussian mixture models and uncertainties , 2016, J. Vis. Commun. Image Represent..

[36]  Marc Van Droogenbroeck,et al.  ViBe: A Universal Background Subtraction Algorithm for Video Sequences , 2011, IEEE Transactions on Image Processing.

[37]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.