Extended Codebook with Multispectral Sequences for Background Subtraction †

The Codebook model is one of the popular real-time models for background subtraction. In this paper, we first extend it from traditional Red-Green-Blue (RGB) color model to multispectral sequences. A self-adaptive mechanism is then designed based on the statistical information extracted from the data themselves, with which the performance has been improved, in addition to saving time and effort to search for the appropriate parameters. Furthermore, the Spectral Information Divergence is introduced to evaluate the spectral distance between the current and reference vectors, together with the Brightness and Spectral Distortion. Experiments on five multispectral sequences with different challenges have shown that the multispectral self-adaptive Codebook model is more capable of detecting moving objects than the corresponding RGB sequences. The proposed research framework opens a door for future works for applying multispectral sequences in moving object detection.

[1]  Yun-Tao Zhang,et al.  Multi-Layer Multi-Feature Background Subtraction Using Codebook Model Framework , 2015 .

[2]  Hamdi Bouchech,et al.  Selection of optimal narrowband multispectral images for face recognition. (Sélection des bandes spectrales optimales pour la reconnaissance des visages) , 2015 .

[3]  Jean-Baptiste Thomas,et al.  Background subtraction with multispectral video sequences , 2014 .

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

[5]  Bojan Cukic,et al.  Multi-spectral face recognition: Identification of people in difficult environments , 2012, 2012 IEEE International Conference on Intelligence and Security Informatics.

[6]  Andrei Zaharescu,et al.  Multi-scale multi-feature codebook-based background subtraction , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[7]  Jeremy Dawson,et al.  SWIR imaging for facial image capture through tinted materials , 2012, Defense + Commercial Sensing.

[8]  Bob Zhang,et al.  Background modeling methods in video analysis: A review and comparative evaluation , 2016, CAAI Trans. Intell. Technol..

[9]  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).

[10]  Qi Li,et al.  Double-Trapezium Cylinder Codebook Model Based on YUV Color Model for Foreground Detection with Shadow and Highlight Suppression , 2016, J. Signal Process. Syst..

[11]  Yoshio Makino,et al.  Hyperspectral imaging and multispectral imaging as the novel techniques for detecting defects in raw and processed meat products: Current state-of-the-art research advances , 2018 .

[12]  Yassine Ruichek,et al.  Enhanced Codebook Model and Fusion for Object Detection with Multispectral Images , 2018, ACIVS.

[13]  Mohan M. Trivedi,et al.  "Hybrid Cone-Cylinder" Codebook Model for Foreground Detection with Shadow and Highlight Suppression , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.

[14]  Ronald Kemker,et al.  High-Resolution Multispectral Dataset for Semantic Segmentation , 2017, ArXiv.

[15]  Chein-I Chang,et al.  An information-theoretic approach to spectral variability, similarity, and discrimination for hyperspectral image analysis , 2000, IEEE Trans. Inf. Theory.

[16]  A.-M. Cretu,et al.  Multispectral image analysis for object recognition and classification , 2016, SPIE Defense + Security.

[17]  Hélène Laurent,et al.  Comparative study of background subtraction algorithms , 2010, J. Electronic Imaging.

[18]  Zhou He-qin.  A two-layers background modeling method based on codebook and texture , 2012 .

[19]  Worapan Kusakunniran,et al.  Foreground segmentation in a video by using a novel dynamic codebook , 2016, 2016 13th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON).

[20]  Nikos Paragios,et al.  Motion-based background subtraction using adaptive kernel density estimation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[21]  Brendon J. Woodford,et al.  A Self-adaptive CodeBook (SACB) model for real-time background subtraction , 2015, Image Vis. Comput..

[22]  Gary A. Shaw,et al.  Spectral Imaging for Remote Sensing , 2003 .

[23]  Yassine Ruichek,et al.  Background Subtraction with Multispectral Images Using Codebook Algorithm , 2017, ACIVS.

[24]  Anna Tonazzini,et al.  Analysis of Multispectral Images in Cultural Heritage and Archaeology , 2014 .

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

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