An Improved Colorimetric Invariants and RGB-Depth-Based Codebook Model for Background Subtraction Using Kinect

In this paper we propose to join the benefits of multiple invariant information into the well-know background subtraction method ”Codebook”. Indeed, this method mainly repose on a color model allowing a separate process of color and intensity distortion. In order to manage hard situations involving high illumination changes, we propose to enhance this model with the use of two supplementary steps: 1/ transforming the input color image using a colorimetric invariant in order to obtain a color-invariant image whatever the illumination conditions; 2/ using depth information as a new data inside the Codebook model, thus performing an RGB-D fusion during the segmentation process.

[1]  Theo Gevers,et al.  Color Constancy Using Natural Image Statistics and Scene Semantics , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  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).

[3]  Louahdi Khoudour,et al.  People re-identification by spectral classification of silhouettes , 2010, Signal Process..

[4]  Bertrand Vachon,et al.  Statistical Background Modeling for Foreground Detection: A Survey , 2010 .

[5]  Ferdinand van der Heijden,et al.  Recursive unsupervised learning of finite mixture models , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Arnold W. M. Smeulders,et al.  Color-based object recognition , 1997, Pattern Recognit..

[7]  Raimondo Schettini,et al.  Automatic color constancy algorithm selection and combination , 2010, Pattern Recognit..

[8]  Yassine Ruichek,et al.  Gaussian Propagation Model Based Dense Optical Flow for Objects Tracking , 2012, ICIAR.

[9]  Riad I. Hammoud,et al.  Robust Multi-Pedestrian Tracking in Thermal-Visible Surveillance Videos , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[10]  Yassine Ruichek,et al.  Improvement of moving objects detection in continued all-day illumination conditions using color invariants and color spaces , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[11]  Gerald Schaefer,et al.  Illuminant and device invariant colour using histogram equalisation , 2005, Pattern Recognit..

[12]  Yassine Ruichek,et al.  Using Hidden Markov Model and Dempster-Shafer Theory for Evaluating and Detecting Dangerous Situations in Level Crossing Environments , 2012, MICAI.

[13]  Thierry Bouwmans,et al.  Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey , 2008 .

[14]  Mohamed S. Kamel,et al.  Image Analysis and Recognition , 2014, Lecture Notes in Computer Science.

[15]  Alvy Ray Smith,et al.  Color gamut transform pairs , 1978, SIGGRAPH.

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

[17]  Eduardo Ros,et al.  Background Subtraction Based on Color and Depth Using Active Sensors , 2013, Sensors.

[18]  G. Buchsbaum.  A spatial processor model for object colour perception , 1980 .

[19]  Thierry Carron.  Segmentations d'images couleur dans la base teinte-luminance-saturation : approche numérique et symbolique , 1995 .

[20]  Bernt Schiele,et al.  Comprehensive Colour Image Normalization , 1998, ECCV.