A Deep Convolutional Neural Network for Background Subtraction

In this work, we present a novel background subtraction system that uses a deep Convolutional Neural Network (CNN) to perform the segmentation. With this approach, feature engineering and parameter tuning become unnecessary since the network parameters can be learned from data by training a single CNN that can handle various video scenes. Additionally, we propose a new approach to estimate background model from video. For the training of the CNN, we employed randomly 5 percent video frames and their ground truth segmentations taken from the Change Detection challenge 2014(CDnet 2014). We also utilized spatial-median filtering as the post-processing of the network outputs. Our method is evaluated with different data-sets, and the network outperforms the existing algorithms with respect to the average ranking over different evaluation metrics. Furthermore, due to the network architecture, our CNN is capable of real time processing.

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

[2]  Guna Seetharaman,et al.  Flux Tensor Constrained Geodesic Active Contours with Sensor Fusion for Persistent Object Tracking , 2007, J. Multim..

[3]  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.

[4]  Hanqing Lu,et al.  Learning sharable models for robust background subtraction , 2015, 2015 IEEE International Conference on Multimedia and Expo (ICME).

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

[6]  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.

[7]  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.

[8]  Gerhard Rigoll,et al.  PID-based regulation of background dynamics for foreground segmentation , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[9]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[10]  Marc Van Droogenbroeck,et al.  Deep background subtraction with scene-specific convolutional neural networks , 2016, 2016 International Conference on Systems, Signals and Image Processing (IWSSIP).

[11]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

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

[13]  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).

[14]  Fatih Murat Porikli,et al.  Changedetection.net: A new change detection benchmark dataset , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

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

[16]  Mohamed Sedky,et al.  Image Processing: Object Segmentation Using Full-Spectrum Matching of Albedo Derived from Colour Images , 2010 .

[17]  Marko Heikkilä,et al.  A texture-based method for modeling the background and detecting moving objects , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  KimKyungnam,et al.  Real-time foreground-background segmentation using codebook model , 2005 .

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

[20]  Hasan Sajid,et al.  Background subtraction for static & moving camera , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[21]  Guillaume-Alexandre Bilodeau,et al.  Change Detection in Feature Space Using Local Binary Similarity Patterns , 2013, 2013 International Conference on Computer and Robot Vision.

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

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

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

[25]  J. Ferryman,et al.  An overview of the PETS 2009 challenge , 2009 .

[26]  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).