Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network

Suk Ho Lee, Nam Seok Choi, Byung Gook Lee, Moon Gi Kang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we propose a level set based energy functional, the minimization of which results in simultaneous background modeling, foreground segmentation, and contour smoothing. The simultaneous dealing of background modeling and foreground segmentation has the effect that the two processes constrain each other positively, such that a good estimate of the background can be obtained with a small number of frames, and a temporal change in the scene is reflected quickly in the construction of the background image. Furthermore, the simultaneous level set based contour smoothing eliminates spurious regions, and smooths the contour that encompasses the object, so that a good representation for the boundary of the object is obtained. The level set based approach makes it possible to derive a level set based Euler-Lagrangian equation, which can be directly implemented and works in real-time.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009
Pages1012-1017
Number of pages6
DOIs
Publication statusPublished - 2009 Oct 13
EventInternational Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009 - Fukuoka, Japan
Duration: 2009 Mar 162009 Mar 19

Publication series

NameProceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009

Other

OtherInternational Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009
CountryJapan
CityFukuoka
Period09/3/1609/3/19

Fingerprint

Euler equations
Partial differential equations

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Software
  • Control and Systems Engineering

Cite this

Lee, S. H., Choi, N. S., Lee, B. G., & Kang, M. G. (2009). Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network. In Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009 (pp. 1012-1017). [5066916] (Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009). https://doi.org/10.1109/CISIS.2009.198
Lee, Suk Ho ; Choi, Nam Seok ; Lee, Byung Gook ; Kang, Moon Gi. / Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network. Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009. 2009. pp. 1012-1017 (Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009).
@inproceedings{1f84235ac9b34139beb1ab4ef8d2f2ad,
title = "Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network",
abstract = "In this paper we propose a level set based energy functional, the minimization of which results in simultaneous background modeling, foreground segmentation, and contour smoothing. The simultaneous dealing of background modeling and foreground segmentation has the effect that the two processes constrain each other positively, such that a good estimate of the background can be obtained with a small number of frames, and a temporal change in the scene is reflected quickly in the construction of the background image. Furthermore, the simultaneous level set based contour smoothing eliminates spurious regions, and smooths the contour that encompasses the object, so that a good representation for the boundary of the object is obtained. The level set based approach makes it possible to derive a level set based Euler-Lagrangian equation, which can be directly implemented and works in real-time.",
author = "Lee, {Suk Ho} and Choi, {Nam Seok} and Lee, {Byung Gook} and Kang, {Moon Gi}",
year = "2009",
month = "10",
day = "13",
doi = "10.1109/CISIS.2009.198",
language = "English",
isbn = "9780769535753",
series = "Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009",
pages = "1012--1017",
booktitle = "Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009",

}

Lee, SH, Choi, NS, Lee, BG & Kang, MG 2009, Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network. in Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009., 5066916, Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009, pp. 1012-1017, International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009, Fukuoka, Japan, 09/3/16. https://doi.org/10.1109/CISIS.2009.198

Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network. / Lee, Suk Ho; Choi, Nam Seok; Lee, Byung Gook; Kang, Moon Gi.

Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009. 2009. p. 1012-1017 5066916 (Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network

AU - Lee, Suk Ho

AU - Choi, Nam Seok

AU - Lee, Byung Gook

AU - Kang, Moon Gi

PY - 2009/10/13

Y1 - 2009/10/13

N2 - In this paper we propose a level set based energy functional, the minimization of which results in simultaneous background modeling, foreground segmentation, and contour smoothing. The simultaneous dealing of background modeling and foreground segmentation has the effect that the two processes constrain each other positively, such that a good estimate of the background can be obtained with a small number of frames, and a temporal change in the scene is reflected quickly in the construction of the background image. Furthermore, the simultaneous level set based contour smoothing eliminates spurious regions, and smooths the contour that encompasses the object, so that a good representation for the boundary of the object is obtained. The level set based approach makes it possible to derive a level set based Euler-Lagrangian equation, which can be directly implemented and works in real-time.

AB - In this paper we propose a level set based energy functional, the minimization of which results in simultaneous background modeling, foreground segmentation, and contour smoothing. The simultaneous dealing of background modeling and foreground segmentation has the effect that the two processes constrain each other positively, such that a good estimate of the background can be obtained with a small number of frames, and a temporal change in the scene is reflected quickly in the construction of the background image. Furthermore, the simultaneous level set based contour smoothing eliminates spurious regions, and smooths the contour that encompasses the object, so that a good representation for the boundary of the object is obtained. The level set based approach makes it possible to derive a level set based Euler-Lagrangian equation, which can be directly implemented and works in real-time.

UR - http://www.scopus.com/inward/record.url?scp=70349740884&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349740884&partnerID=8YFLogxK

U2 - 10.1109/CISIS.2009.198

DO - 10.1109/CISIS.2009.198

M3 - Conference contribution

AN - SCOPUS:70349740884

SN - 9780769535753

T3 - Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009

SP - 1012

EP - 1017

BT - Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009

ER -

Lee SH, Choi NS, Lee BG, Kang MG. Simultaneous background/foreground segmentation and contour smoothing with level set based partial differential equation for intelligent surveillance systems over network. In Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009. 2009. p. 1012-1017. 5066916. (Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009). https://doi.org/10.1109/CISIS.2009.198