Global illumination invariant object detection with level set based bimodal segmentation

Suk Ho Lee, Hyenkyun Woo, Moon Gi Kang

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In this letter, we propose a new detection method for video surveillance which provides for a robust and real-time working object detection under various global illumination conditions. The proposed scheme needs no manual parameter settings for different illumination conditions, which makes the algorithm applicable to automatic surveillance systems. Two special filters are designed to eliminate the spurious object regions that occur due to the charge coupled device (CCD) noise, making the scheme stable even in very low illumination conditions. We demonstrate the effectiveness of the proposed algorithm experimentally with different illumination conditions, changes in contrast, and noise level.

Original languageEnglish
Article number5401108
Pages (from-to)616-620
Number of pages5
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume20
Issue number4
DOIs
Publication statusPublished - 2010 Apr 1

Fingerprint

Lighting
Charge coupled devices
Object detection

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

@article{f40aaa17ed4c47da9c57df4e40ae85c8,
title = "Global illumination invariant object detection with level set based bimodal segmentation",
abstract = "In this letter, we propose a new detection method for video surveillance which provides for a robust and real-time working object detection under various global illumination conditions. The proposed scheme needs no manual parameter settings for different illumination conditions, which makes the algorithm applicable to automatic surveillance systems. Two special filters are designed to eliminate the spurious object regions that occur due to the charge coupled device (CCD) noise, making the scheme stable even in very low illumination conditions. We demonstrate the effectiveness of the proposed algorithm experimentally with different illumination conditions, changes in contrast, and noise level.",
author = "Lee, {Suk Ho} and Hyenkyun Woo and Kang, {Moon Gi}",
year = "2010",
month = "4",
day = "1",
doi = "10.1109/TCSVT.2010.2041824",
language = "English",
volume = "20",
pages = "616--620",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Global illumination invariant object detection with level set based bimodal segmentation. / Lee, Suk Ho; Woo, Hyenkyun; Kang, Moon Gi.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 20, No. 4, 5401108, 01.04.2010, p. 616-620.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Global illumination invariant object detection with level set based bimodal segmentation

AU - Lee, Suk Ho

AU - Woo, Hyenkyun

AU - Kang, Moon Gi

PY - 2010/4/1

Y1 - 2010/4/1

N2 - In this letter, we propose a new detection method for video surveillance which provides for a robust and real-time working object detection under various global illumination conditions. The proposed scheme needs no manual parameter settings for different illumination conditions, which makes the algorithm applicable to automatic surveillance systems. Two special filters are designed to eliminate the spurious object regions that occur due to the charge coupled device (CCD) noise, making the scheme stable even in very low illumination conditions. We demonstrate the effectiveness of the proposed algorithm experimentally with different illumination conditions, changes in contrast, and noise level.

AB - In this letter, we propose a new detection method for video surveillance which provides for a robust and real-time working object detection under various global illumination conditions. The proposed scheme needs no manual parameter settings for different illumination conditions, which makes the algorithm applicable to automatic surveillance systems. Two special filters are designed to eliminate the spurious object regions that occur due to the charge coupled device (CCD) noise, making the scheme stable even in very low illumination conditions. We demonstrate the effectiveness of the proposed algorithm experimentally with different illumination conditions, changes in contrast, and noise level.

UR - http://www.scopus.com/inward/record.url?scp=77951111130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951111130&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2010.2041824

DO - 10.1109/TCSVT.2010.2041824

M3 - Article

VL - 20

SP - 616

EP - 620

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 4

M1 - 5401108

ER -