Geometrical, physical and text/symbol analysis based approach of traffic sign detection system

Yangxing Liu, Takeshi Ikenaga, Satoshi Goto

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

8 Citations (Scopus)

Abstract

Traffic sign detection is a valuable part of future driver support system. In this paper, we present a novel framework to accurately detect traffic signs from a single color image by analyzing geometrical, physical andtext/symbol features of traffic signs. First, we utilize an elaborate edge detection algorithm to extract edge map and accurate edge pixel gradient information. Second 2-D geometric primitives (circles, ellipses, rectangles and triangles) are quickly extracted from image edge map. Third the candidate traffic sign regions are selected by analyzing the intrinsic color features, which are invariant to different illumination conditions, of each region circumvented by geometric primitives. Finally a text and symbol detection algorithm is introduced to classify true traffic signs. Experimental results demonstrated the capabilities of our algorithm to detect traffic signs with respect to different size, shape, color and illumination conditions.

Original languageEnglish
Title of host publicationIEEE Intelligent Vehicles Symposium, Proceedings
Pages238-243
Number of pages6
Publication statusPublished - 2006
Event2006 IEEE Intelligent Vehicles Symposium, IV 2006 - Meguro-Ku, Tokyo
Duration: 2006 Jun 132006 Jun 15

Other

Other2006 IEEE Intelligent Vehicles Symposium, IV 2006
CityMeguro-Ku, Tokyo
Period06/6/1306/6/15

Fingerprint

Traffic signs
Color
Lighting
Advanced driver assistance systems
Edge detection
Pixels

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Liu, Y., Ikenaga, T., & Goto, S. (2006). Geometrical, physical and text/symbol analysis based approach of traffic sign detection system. In IEEE Intelligent Vehicles Symposium, Proceedings (pp. 238-243). [1689635]

Geometrical, physical and text/symbol analysis based approach of traffic sign detection system. / Liu, Yangxing; Ikenaga, Takeshi; Goto, Satoshi.

IEEE Intelligent Vehicles Symposium, Proceedings. 2006. p. 238-243 1689635.

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

Liu, Y, Ikenaga, T & Goto, S 2006, Geometrical, physical and text/symbol analysis based approach of traffic sign detection system. in IEEE Intelligent Vehicles Symposium, Proceedings., 1689635, pp. 238-243, 2006 IEEE Intelligent Vehicles Symposium, IV 2006, Meguro-Ku, Tokyo, 06/6/13.
Liu Y, Ikenaga T, Goto S. Geometrical, physical and text/symbol analysis based approach of traffic sign detection system. In IEEE Intelligent Vehicles Symposium, Proceedings. 2006. p. 238-243. 1689635
Liu, Yangxing ; Ikenaga, Takeshi ; Goto, Satoshi. / Geometrical, physical and text/symbol analysis based approach of traffic sign detection system. IEEE Intelligent Vehicles Symposium, Proceedings. 2006. pp. 238-243
@inproceedings{c1918517a6cd44d3bba0d3b1d873669b,
title = "Geometrical, physical and text/symbol analysis based approach of traffic sign detection system",
abstract = "Traffic sign detection is a valuable part of future driver support system. In this paper, we present a novel framework to accurately detect traffic signs from a single color image by analyzing geometrical, physical andtext/symbol features of traffic signs. First, we utilize an elaborate edge detection algorithm to extract edge map and accurate edge pixel gradient information. Second 2-D geometric primitives (circles, ellipses, rectangles and triangles) are quickly extracted from image edge map. Third the candidate traffic sign regions are selected by analyzing the intrinsic color features, which are invariant to different illumination conditions, of each region circumvented by geometric primitives. Finally a text and symbol detection algorithm is introduced to classify true traffic signs. Experimental results demonstrated the capabilities of our algorithm to detect traffic signs with respect to different size, shape, color and illumination conditions.",
author = "Yangxing Liu and Takeshi Ikenaga and Satoshi Goto",
year = "2006",
language = "English",
isbn = "490112286X",
pages = "238--243",
booktitle = "IEEE Intelligent Vehicles Symposium, Proceedings",

}

TY - GEN

T1 - Geometrical, physical and text/symbol analysis based approach of traffic sign detection system

AU - Liu, Yangxing

AU - Ikenaga, Takeshi

AU - Goto, Satoshi

PY - 2006

Y1 - 2006

N2 - Traffic sign detection is a valuable part of future driver support system. In this paper, we present a novel framework to accurately detect traffic signs from a single color image by analyzing geometrical, physical andtext/symbol features of traffic signs. First, we utilize an elaborate edge detection algorithm to extract edge map and accurate edge pixel gradient information. Second 2-D geometric primitives (circles, ellipses, rectangles and triangles) are quickly extracted from image edge map. Third the candidate traffic sign regions are selected by analyzing the intrinsic color features, which are invariant to different illumination conditions, of each region circumvented by geometric primitives. Finally a text and symbol detection algorithm is introduced to classify true traffic signs. Experimental results demonstrated the capabilities of our algorithm to detect traffic signs with respect to different size, shape, color and illumination conditions.

AB - Traffic sign detection is a valuable part of future driver support system. In this paper, we present a novel framework to accurately detect traffic signs from a single color image by analyzing geometrical, physical andtext/symbol features of traffic signs. First, we utilize an elaborate edge detection algorithm to extract edge map and accurate edge pixel gradient information. Second 2-D geometric primitives (circles, ellipses, rectangles and triangles) are quickly extracted from image edge map. Third the candidate traffic sign regions are selected by analyzing the intrinsic color features, which are invariant to different illumination conditions, of each region circumvented by geometric primitives. Finally a text and symbol detection algorithm is introduced to classify true traffic signs. Experimental results demonstrated the capabilities of our algorithm to detect traffic signs with respect to different size, shape, color and illumination conditions.

UR - http://www.scopus.com/inward/record.url?scp=34547332003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547332003&partnerID=8YFLogxK

M3 - Conference contribution

SN - 490112286X

SN - 9784901122863

SP - 238

EP - 243

BT - IEEE Intelligent Vehicles Symposium, Proceedings

ER -