Illumination invariant color segmentation method based on cluster center tree for traffic sign detection

Byeongdae Woo; Yeongwoo Choi; Youngjung Uh; Kwangyong Lim; Hyeran Byun

doi:10.1145/2701126.2701139

Illumination invariant color segmentation method based on cluster center tree for traffic sign detection

Byeongdae Woo, Yeongwoo Choi, Youngjung Uh, Kwangyong Lim, Hyeran Byun

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

Abstract

This paper proposes a color segmentation method that can locate candidate regions of traffic signs accurately and reliably from real world images. In the real world, there are various light conditions which make the color segmentation very difficult problem. Hence, we propose an illumination invariant color segmentation method. The proposed method consists of two parts; 1) cluster center treebased segmentation 2) illumination estimation. Cluster center tree is trained for color segmentation. Illumination estimation algorithm classifies light condition of the input images. We validate the proposed method qualitatively and quantitatively with 1,745 images containing red and blue traffic signs captured with four light conditions; sunny, cloudy, rainy and night. The proposed method achieves the high detection rate of 99.25% in sunny, 98.33% in cloudy, 87.85% in rainy and 88.70% at night.

Original language	English
Title of host publication	ACM IMCOM 2015 - Proceedings
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450333771
DOIs	https://doi.org/10.1145/2701126.2701139
Publication status	Published - 2015 Jan 8
Event	9th International Conference on Ubiquitous Information Management and Communication, ACM IMCOM 2015 - Bali, Indonesia Duration: 2015 Jan 8 → 2015 Jan 10

Publication series

Name	ACM IMCOM 2015 - Proceedings

Other

Other	9th International Conference on Ubiquitous Information Management and Communication, ACM IMCOM 2015
Country	Indonesia
City	Bali
Period	15/1/8 → 15/1/10

All Science Journal Classification (ASJC) codes

Computer Science(all)
Control and Systems Engineering
Management Information Systems

Access to Document

10.1145/2701126.2701139

Fingerprint Dive into the research topics of 'Illumination invariant color segmentation method based on cluster center tree for traffic sign detection'. Together they form a unique fingerprint.

Cite this

@inproceedings{1be5839e4051475081a0cbd6e0787e62,

title = "Illumination invariant color segmentation method based on cluster center tree for traffic sign detection",

abstract = "This paper proposes a color segmentation method that can locate candidate regions of traffic signs accurately and reliably from real world images. In the real world, there are various light conditions which make the color segmentation very difficult problem. Hence, we propose an illumination invariant color segmentation method. The proposed method consists of two parts; 1) cluster center treebased segmentation 2) illumination estimation. Cluster center tree is trained for color segmentation. Illumination estimation algorithm classifies light condition of the input images. We validate the proposed method qualitatively and quantitatively with 1,745 images containing red and blue traffic signs captured with four light conditions; sunny, cloudy, rainy and night. The proposed method achieves the high detection rate of 99.25% in sunny, 98.33% in cloudy, 87.85% in rainy and 88.70% at night.",

author = "Byeongdae Woo and Yeongwoo Choi and Youngjung Uh and Kwangyong Lim and Hyeran Byun",

note = "Copyright: Copyright 2015 Elsevier B.V., All rights reserved.; 9th International Conference on Ubiquitous Information Management and Communication, ACM IMCOM 2015 ; Conference date: 08-01-2015 Through 10-01-2015",

year = "2015",

month = jan,

day = "8",

doi = "10.1145/2701126.2701139",

language = "English",

series = "ACM IMCOM 2015 - Proceedings",

publisher = "Association for Computing Machinery, Inc",

booktitle = "ACM IMCOM 2015 - Proceedings",

}

Woo, B, Choi, Y, Uh, Y, Lim, K & Byun, H 2015, Illumination invariant color segmentation method based on cluster center tree for traffic sign detection. in ACM IMCOM 2015 - Proceedings., a74, ACM IMCOM 2015 - Proceedings, Association for Computing Machinery, Inc, 9th International Conference on Ubiquitous Information Management and Communication, ACM IMCOM 2015, Bali, Indonesia, 15/1/8. https://doi.org/10.1145/2701126.2701139

Illumination invariant color segmentation method based on cluster center tree for traffic sign detection. / Woo, Byeongdae; Choi, Yeongwoo; Uh, Youngjung; Lim, Kwangyong; Byun, Hyeran.

ACM IMCOM 2015 - Proceedings. Association for Computing Machinery, Inc, 2015. a74 (ACM IMCOM 2015 - Proceedings).

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

TY - GEN

T1 - Illumination invariant color segmentation method based on cluster center tree for traffic sign detection

AU - Woo, Byeongdae

AU - Choi, Yeongwoo

AU - Uh, Youngjung

AU - Lim, Kwangyong

AU - Byun, Hyeran

PY - 2015/1/8

Y1 - 2015/1/8

N2 - This paper proposes a color segmentation method that can locate candidate regions of traffic signs accurately and reliably from real world images. In the real world, there are various light conditions which make the color segmentation very difficult problem. Hence, we propose an illumination invariant color segmentation method. The proposed method consists of two parts; 1) cluster center treebased segmentation 2) illumination estimation. Cluster center tree is trained for color segmentation. Illumination estimation algorithm classifies light condition of the input images. We validate the proposed method qualitatively and quantitatively with 1,745 images containing red and blue traffic signs captured with four light conditions; sunny, cloudy, rainy and night. The proposed method achieves the high detection rate of 99.25% in sunny, 98.33% in cloudy, 87.85% in rainy and 88.70% at night.

AB - This paper proposes a color segmentation method that can locate candidate regions of traffic signs accurately and reliably from real world images. In the real world, there are various light conditions which make the color segmentation very difficult problem. Hence, we propose an illumination invariant color segmentation method. The proposed method consists of two parts; 1) cluster center treebased segmentation 2) illumination estimation. Cluster center tree is trained for color segmentation. Illumination estimation algorithm classifies light condition of the input images. We validate the proposed method qualitatively and quantitatively with 1,745 images containing red and blue traffic signs captured with four light conditions; sunny, cloudy, rainy and night. The proposed method achieves the high detection rate of 99.25% in sunny, 98.33% in cloudy, 87.85% in rainy and 88.70% at night.

UR - http://www.scopus.com/inward/record.url?scp=84926224679&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926224679&partnerID=8YFLogxK

U2 - 10.1145/2701126.2701139

DO - 10.1145/2701126.2701139

M3 - Conference contribution

AN - SCOPUS:84926224679

T3 - ACM IMCOM 2015 - Proceedings

BT - ACM IMCOM 2015 - Proceedings

PB - Association for Computing Machinery, Inc

T2 - 9th International Conference on Ubiquitous Information Management and Communication, ACM IMCOM 2015

Y2 - 8 January 2015 through 10 January 2015

ER -