Background subtraction under sudden illumination change

Hasan Sajid; Sen Ching Samson Cheung

doi:10.1109/MMSP.2014.6958814

Background subtraction under sudden illumination change

Hasan Sajid, Sen Ching Samson Cheung

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

7 Scopus citations

Abstract

In this paper, we propose a Multiple Background Model based Background Subtraction (MB²S) algorithm that is robust against sudden illumination changes in indoor environment. It uses multiple background models of expected illumination changes followed by both pixel and frame based background subtraction on both RGB and YCbCr color spaces. The masks generated after processing these input images are then combined in a framework to classify background and foreground pixels. Evaluation of proposed approach on publicly available test sequences show higher precision and recall than other state-of-the-art algorithms.

Original language	English
Title of host publication	2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014
ISBN (Electronic)	9781479958962
DOIs	https://doi.org/10.1109/MMSP.2014.6958814
State	Published - Nov 14 2014
Event	2014 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014 - Jakarta, Indonesia Duration: Sep 22 2014 → Sep 24 2014

Publication series

Name	2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014

Conference

Conference	2014 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014
Country/Territory	Indonesia
City	Jakarta
Period	9/22/14 → 9/24/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Signal Processing

Access to Document

10.1109/MMSP.2014.6958814

Cite this

@inproceedings{f27d394536be4f7cb7d34a9770f63fc1,

title = "Background subtraction under sudden illumination change",

abstract = "In this paper, we propose a Multiple Background Model based Background Subtraction (MB2S) algorithm that is robust against sudden illumination changes in indoor environment. It uses multiple background models of expected illumination changes followed by both pixel and frame based background subtraction on both RGB and YCbCr color spaces. The masks generated after processing these input images are then combined in a framework to classify background and foreground pixels. Evaluation of proposed approach on publicly available test sequences show higher precision and recall than other state-of-the-art algorithms.",

author = "Hasan Sajid and Cheung, {Sen Ching Samson}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014 ; Conference date: 22-09-2014 Through 24-09-2014",

year = "2014",

month = nov,

day = "14",

doi = "10.1109/MMSP.2014.6958814",

language = "English",

series = "2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014",

booktitle = "2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014",

}

Sajid, H & Cheung, SCS 2014, Background subtraction under sudden illumination change. in 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014., 6958814, 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014, 2014 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014, Jakarta, Indonesia, 9/22/14. https://doi.org/10.1109/MMSP.2014.6958814

Background subtraction under sudden illumination change. / Sajid, Hasan; Cheung, Sen Ching Samson.
2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014. 2014. 6958814 (2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014).

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

TY - GEN

T1 - Background subtraction under sudden illumination change

AU - Sajid, Hasan

AU - Cheung, Sen Ching Samson

PY - 2014/11/14

Y1 - 2014/11/14

N2 - In this paper, we propose a Multiple Background Model based Background Subtraction (MB2S) algorithm that is robust against sudden illumination changes in indoor environment. It uses multiple background models of expected illumination changes followed by both pixel and frame based background subtraction on both RGB and YCbCr color spaces. The masks generated after processing these input images are then combined in a framework to classify background and foreground pixels. Evaluation of proposed approach on publicly available test sequences show higher precision and recall than other state-of-the-art algorithms.

AB - In this paper, we propose a Multiple Background Model based Background Subtraction (MB2S) algorithm that is robust against sudden illumination changes in indoor environment. It uses multiple background models of expected illumination changes followed by both pixel and frame based background subtraction on both RGB and YCbCr color spaces. The masks generated after processing these input images are then combined in a framework to classify background and foreground pixels. Evaluation of proposed approach on publicly available test sequences show higher precision and recall than other state-of-the-art algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84914170924&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84914170924&partnerID=8YFLogxK

U2 - 10.1109/MMSP.2014.6958814

DO - 10.1109/MMSP.2014.6958814

M3 - Conference contribution

AN - SCOPUS:84914170924

T3 - 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014

BT - 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014

T2 - 2014 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014

Y2 - 22 September 2014 through 24 September 2014

ER -

Background subtraction under sudden illumination change

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this