Non-static backgrounds modeling including high traffic regions

Park Daeyong, Byun Hyeran

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

2 Citations (Scopus)

Abstract

For the detection of moving objects in surveillance systems, background subtraction methods are widely used. In case the background is non-stationary, modeling the background is not a simple problem. To solve the problem, many methods are proposed. In the high traffic region such as airport and subways, however, few researches have been conducted. In this paper, we classify each pixel into four different types: still background, dynamic background, and moving object, and temporary still object. And update the background according to the result. For the classification, we analyze the temporal characteristics of each pixel's intensity with likelihood test. With public video data, we experimentally show that modeling based on pixel classification improves detection accuracy in public areas which has high traffic.

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC
Pages3423-3427
Number of pages5
DOIs
Publication statusPublished - 2008 Dec 29
Event7th International Conference on Machine Learning and Cybernetics, ICMLC - Kunming, China
Duration: 2008 Jul 122008 Jul 15

Publication series

NameProceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC
Volume6

Other

Other7th International Conference on Machine Learning and Cybernetics, ICMLC
CountryChina
CityKunming
Period08/7/1208/7/15

Fingerprint

Pixels
Subways
Airports

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this

Daeyong, P., & Hyeran, B. (2008). Non-static backgrounds modeling including high traffic regions. In Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC (pp. 3423-3427). [4620996] (Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC; Vol. 6). https://doi.org/10.1109/ICMLC.2008.4620996
Daeyong, Park ; Hyeran, Byun. / Non-static backgrounds modeling including high traffic regions. Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC. 2008. pp. 3423-3427 (Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC).
@inproceedings{fa67c9a785f843058047908e5898d3d8,
title = "Non-static backgrounds modeling including high traffic regions",
abstract = "For the detection of moving objects in surveillance systems, background subtraction methods are widely used. In case the background is non-stationary, modeling the background is not a simple problem. To solve the problem, many methods are proposed. In the high traffic region such as airport and subways, however, few researches have been conducted. In this paper, we classify each pixel into four different types: still background, dynamic background, and moving object, and temporary still object. And update the background according to the result. For the classification, we analyze the temporal characteristics of each pixel's intensity with likelihood test. With public video data, we experimentally show that modeling based on pixel classification improves detection accuracy in public areas which has high traffic.",
author = "Park Daeyong and Byun Hyeran",
year = "2008",
month = "12",
day = "29",
doi = "10.1109/ICMLC.2008.4620996",
language = "English",
isbn = "9781424420964",
series = "Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC",
pages = "3423--3427",
booktitle = "Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC",

}

Daeyong, P & Hyeran, B 2008, Non-static backgrounds modeling including high traffic regions. in Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC., 4620996, Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC, vol. 6, pp. 3423-3427, 7th International Conference on Machine Learning and Cybernetics, ICMLC, Kunming, China, 08/7/12. https://doi.org/10.1109/ICMLC.2008.4620996

Non-static backgrounds modeling including high traffic regions. / Daeyong, Park; Hyeran, Byun.

Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC. 2008. p. 3423-3427 4620996 (Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC; Vol. 6).

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

TY - GEN

T1 - Non-static backgrounds modeling including high traffic regions

AU - Daeyong, Park

AU - Hyeran, Byun

PY - 2008/12/29

Y1 - 2008/12/29

N2 - For the detection of moving objects in surveillance systems, background subtraction methods are widely used. In case the background is non-stationary, modeling the background is not a simple problem. To solve the problem, many methods are proposed. In the high traffic region such as airport and subways, however, few researches have been conducted. In this paper, we classify each pixel into four different types: still background, dynamic background, and moving object, and temporary still object. And update the background according to the result. For the classification, we analyze the temporal characteristics of each pixel's intensity with likelihood test. With public video data, we experimentally show that modeling based on pixel classification improves detection accuracy in public areas which has high traffic.

AB - For the detection of moving objects in surveillance systems, background subtraction methods are widely used. In case the background is non-stationary, modeling the background is not a simple problem. To solve the problem, many methods are proposed. In the high traffic region such as airport and subways, however, few researches have been conducted. In this paper, we classify each pixel into four different types: still background, dynamic background, and moving object, and temporary still object. And update the background according to the result. For the classification, we analyze the temporal characteristics of each pixel's intensity with likelihood test. With public video data, we experimentally show that modeling based on pixel classification improves detection accuracy in public areas which has high traffic.

UR - http://www.scopus.com/inward/record.url?scp=57849094587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57849094587&partnerID=8YFLogxK

U2 - 10.1109/ICMLC.2008.4620996

DO - 10.1109/ICMLC.2008.4620996

M3 - Conference contribution

AN - SCOPUS:57849094587

SN - 9781424420964

T3 - Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC

SP - 3423

EP - 3427

BT - Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC

ER -

Daeyong P, Hyeran B. Non-static backgrounds modeling including high traffic regions. In Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC. 2008. p. 3423-3427. 4620996. (Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC). https://doi.org/10.1109/ICMLC.2008.4620996