An Effective Foreground Detection Approach Using a Block-Based Background Modeling

Omar Elharrouss; Driss Moujahid; Soukaina Elidrissi Elkaitouni; Hamid Tairi

doi:10.1109/CGiV.2016.44

An Effective Foreground Detection Approach Using a Block-Based Background Modeling

Omar Elharrouss, Driss Moujahid, Soukaina Elidrissi Elkaitouni, Hamid Tairi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

The moving objects detection is considered as an important factor for many video surveillance applications. To assure a best detection a background model should be generated. This paper proposes a background modeling approach. To generate this model, we use both pixel-based and block-based processes to classify background pixels from those belong to the foreground. After that, to minimize the noise in the results of the background subtraction the structure-texture decomposition is applied on the absolute difference image. Just the structure component which contains the homogeneous parts of the image is used in the segmentation. The binary motion detection mask computation is made using a selected threshold. The experimental results demonstrate that our approach is effective and accurate for moving objects detection.

Original language	English
Title of host publication	Proceedings - Computer Graphics, Imaging and Visualization
Subtitle of host publication	New Techniques and Trends, CGiV 2016
Editors	Mohamed Fakir, Ebad Banissi, Muhammad Sarfraz
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	190-195
Number of pages	6
ISBN (Electronic)	9781509008117
DOIs	https://doi.org/10.1109/CGiV.2016.44
Publication status	Published - May 10 2016
Externally published	Yes
Event	13th Computer Graphics, Imaging and Visualization, CGiV 2016 - Beni Mellal, Morocco Duration: Mar 29 2016 → Apr 1 2016

Publication series

Name	Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016

Conference

Conference	13th Computer Graphics, Imaging and Visualization, CGiV 2016
Country/Territory	Morocco
City	Beni Mellal
Period	3/29/16 → 4/1/16

Keywords

Background model
Background subtraction
Motion detection
Video surveillance

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Signal Processing
Modelling and Simulation

Access to Document

10.1109/CGiV.2016.44

Cite this

Elharrouss, O., Moujahid, D., Elkaitouni, S. E., & Tairi, H. (2016). An Effective Foreground Detection Approach Using a Block-Based Background Modeling. In M. Fakir, E. Banissi, & M. Sarfraz (Eds.), Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016 (pp. 190-195). Article 7467706 (Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CGiV.2016.44

An Effective Foreground Detection Approach Using a Block-Based Background Modeling. / Elharrouss, Omar; Moujahid, Driss; Elkaitouni, Soukaina Elidrissi et al.
Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016. ed. / Mohamed Fakir; Ebad Banissi; Muhammad Sarfraz. Institute of Electrical and Electronics Engineers Inc., 2016. p. 190-195 7467706 (Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Elharrouss, O, Moujahid, D, Elkaitouni, SE & Tairi, H 2016, An Effective Foreground Detection Approach Using a Block-Based Background Modeling. in M Fakir, E Banissi & M Sarfraz (eds), Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016., 7467706, Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016, Institute of Electrical and Electronics Engineers Inc., pp. 190-195, 13th Computer Graphics, Imaging and Visualization, CGiV 2016, Beni Mellal, Morocco, 3/29/16. https://doi.org/10.1109/CGiV.2016.44

Elharrouss O, Moujahid D, Elkaitouni SE, Tairi H. An Effective Foreground Detection Approach Using a Block-Based Background Modeling. In Fakir M, Banissi E, Sarfraz M, editors, Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 190-195. 7467706. (Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016). doi: 10.1109/CGiV.2016.44

Elharrouss, Omar ; Moujahid, Driss ; Elkaitouni, Soukaina Elidrissi et al. / An Effective Foreground Detection Approach Using a Block-Based Background Modeling. Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016. editor / Mohamed Fakir ; Ebad Banissi ; Muhammad Sarfraz. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 190-195 (Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016).

@inproceedings{c190fe62639e4a798da1c7f25f523ed9,

title = "An Effective Foreground Detection Approach Using a Block-Based Background Modeling",

abstract = "The moving objects detection is considered as an important factor for many video surveillance applications. To assure a best detection a background model should be generated. This paper proposes a background modeling approach. To generate this model, we use both pixel-based and block-based processes to classify background pixels from those belong to the foreground. After that, to minimize the noise in the results of the background subtraction the structure-texture decomposition is applied on the absolute difference image. Just the structure component which contains the homogeneous parts of the image is used in the segmentation. The binary motion detection mask computation is made using a selected threshold. The experimental results demonstrate that our approach is effective and accurate for moving objects detection.",

keywords = "Background model, Background subtraction, Motion detection, Video surveillance",

author = "Omar Elharrouss and Driss Moujahid and Elkaitouni, {Soukaina Elidrissi} and Hamid Tairi",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 13th Computer Graphics, Imaging and Visualization, CGiV 2016 ; Conference date: 29-03-2016 Through 01-04-2016",

year = "2016",

month = may,

day = "10",

doi = "10.1109/CGiV.2016.44",

language = "English",

series = "Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "190--195",

editor = "Mohamed Fakir and Ebad Banissi and Muhammad Sarfraz",

booktitle = "Proceedings - Computer Graphics, Imaging and Visualization",

}

TY - GEN

T1 - An Effective Foreground Detection Approach Using a Block-Based Background Modeling

AU - Elharrouss, Omar

AU - Moujahid, Driss

AU - Elkaitouni, Soukaina Elidrissi

AU - Tairi, Hamid

PY - 2016/5/10

Y1 - 2016/5/10

N2 - The moving objects detection is considered as an important factor for many video surveillance applications. To assure a best detection a background model should be generated. This paper proposes a background modeling approach. To generate this model, we use both pixel-based and block-based processes to classify background pixels from those belong to the foreground. After that, to minimize the noise in the results of the background subtraction the structure-texture decomposition is applied on the absolute difference image. Just the structure component which contains the homogeneous parts of the image is used in the segmentation. The binary motion detection mask computation is made using a selected threshold. The experimental results demonstrate that our approach is effective and accurate for moving objects detection.

AB - The moving objects detection is considered as an important factor for many video surveillance applications. To assure a best detection a background model should be generated. This paper proposes a background modeling approach. To generate this model, we use both pixel-based and block-based processes to classify background pixels from those belong to the foreground. After that, to minimize the noise in the results of the background subtraction the structure-texture decomposition is applied on the absolute difference image. Just the structure component which contains the homogeneous parts of the image is used in the segmentation. The binary motion detection mask computation is made using a selected threshold. The experimental results demonstrate that our approach is effective and accurate for moving objects detection.

KW - Background model

KW - Background subtraction

KW - Motion detection

KW - Video surveillance

UR - http://www.scopus.com/inward/record.url?scp=84973650030&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973650030&partnerID=8YFLogxK

U2 - 10.1109/CGiV.2016.44

DO - 10.1109/CGiV.2016.44

M3 - Conference contribution

AN - SCOPUS:84973650030

T3 - Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016

SP - 190

EP - 195

BT - Proceedings - Computer Graphics, Imaging and Visualization

A2 - Fakir, Mohamed

A2 - Banissi, Ebad

A2 - Sarfraz, Muhammad

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th Computer Graphics, Imaging and Visualization, CGiV 2016

Y2 - 29 March 2016 through 1 April 2016

ER -

An Effective Foreground Detection Approach Using a Block-Based Background Modeling

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this