SuperBE: computationally light background estimation with superpixels

This paper presents a motion-based superpixel-level background estimation algorithm that aims to be competitively accurate while requiring less computation time for background modelling and updating. Superpixels are chosen for their spatial and colour coherency and can be grouped together to better define the shapes of objects in an image. RGB mean and colour covariance matrices are used as the discriminative features for comparing superpixels to their background model samples. The background model initialisation and update procedures are inspired by existing approaches, with the key aim of minimising computational complexity and therefore processing time. Experiments carried out with a widely used dataset show that SuperBE can achieve a high level of accuracy and is competitive against other state-of-the-art background estimation algorithms. The main contribution of this paper is the computationally efficient use of superpixels in background estimation while maintaining high accuracy, reaching 135 fps on 320 × 240 resolution images.

[1]  Massimo Piccardi,et al.  Background subtraction techniques: a review , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

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

[3]  K. Suganya Devi,et al.  Improving the Efficiency of Background Subtraction using Superpixel Extraction and Midpoint for Centroid , 2012 .

[4]  W. Förstner,et al.  A Metric for Covariance Matrices , 2003 .

[5]  José Muñoz,et al.  A Neural Network Approach for Video Object Segmentation in Traffic Surveillance , 2008, ICIAR.

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

[7]  Slawomir Bak,et al.  Person Re-identification Using Spatial Covariance Regions of Human Body Parts , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[8]  Larry S. Davis,et al.  M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo , 2002, ECCV.

[9]  Dariu Gavrila,et al.  Joint multi-person detection and tracking from overlapping cameras , 2014, Comput. Vis. Image Underst..

[10]  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.

[11]  Rui Wang,et al.  Static and Moving Object Detection Using Flux Tensor with Split Gaussian Models , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[12]  Anoop Cherian,et al.  Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Gerhard Rigoll,et al.  A Deep Convolutional Neural Network for Background Subtraction , 2017, ArXiv.

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

[15]  James M. Rehg,et al.  Video Segmentation by Tracking Many Figure-Ground Segments , 2013, 2013 IEEE International Conference on Computer Vision.

[16]  Francesca Murabito,et al.  Superpixel-based video object segmentation using perceptual organization and location prior , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Wen Gao,et al.  Background Subtraction via generalized fused lasso foreground modeling , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[19]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Vittorio Ferrari,et al.  Fast Object Segmentation in Unconstrained Video , 2013, 2013 IEEE International Conference on Computer Vision.

[21]  Alexandre Bernardino,et al.  The HDA+ Data Set for Research on Fully Automated Re-identification Systems , 2014, ECCV Workshops.

[22]  Martin K. Purvis,et al.  Improving superpixel-based image segmentation by incorporating color covariance matrix manifolds , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[23]  David Suter,et al.  Background Subtraction Based on a Robust Consensus Method , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[24]  Soon Ki Jung,et al.  Background Subtraction via Superpixel-Based Online Matrix Decomposition with Structured Foreground Constraints , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[25]  Simone Palazzo,et al.  A texton-based kernel density estimation approach for background modeling under extreme conditions , 2014, Comput. Vis. Image Underst..

[26]  L. Davis,et al.  M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene , 2003, International Journal of Computer Vision.

[27]  Yap-Peng Tan,et al.  A color histogram based people tracking system , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[28]  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.

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

[30]  Aaron F. Bobick,et al.  Fast Lighting Independent Background Subtraction , 2004, International Journal of Computer Vision.

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

[32]  J. Krumm,et al.  Multi-camera multi-person tracking for EasyLiving , 2000, Proceedings Third IEEE International Workshop on Visual Surveillance.

[33]  Bohyung Han,et al.  Generalized Background Subtraction Using Superpixels with Label Integrated Motion Estimation , 2014, ECCV.

[34]  Thierry Bouwmans,et al.  Type-2 Fuzzy Mixture of Gaussians Model: Application to Background Modeling , 2008, ISVC.

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

[36]  Afshin Dehghan,et al.  Improving an Object Detector and Extracting Regions Using Superpixels , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  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..

[38]  Guillaume-Alexandre Bilodeau,et al.  A Self-Adjusting Approach to Change Detection Based on Background Word Consensus , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[39]  Dariu Gavrila,et al.  A Comparative Study on Multi-person Tracking Using Overlapping Cameras , 2013, ICVS.

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

[41]  Du-Ming Tsai,et al.  Independent Component Analysis-Based Background Subtraction for Indoor Surveillance , 2009, IEEE Transactions on Image Processing.