Real-time traffic sign detection with vehicle camera images

Jihie Kim, Yeongwoo Choi, Seunggyu Kim, Kwangyong Lim, Hyeran Byun

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

Abstract

This paper presents a real-time traffic sign detection method using color properties and shape-based features for real-world environment applications. The proposed method has two main steps: color- based region segmentation and shape-based verification of the segmented area. In the first step, region-of-interest (ROI) is roughly segmented by a simple color-based thresholding method and each segment is corrected by a guided filter. Next, each ROI is verified through a shape analysis to decide whether the ROI is a circle or a triangle. For detecting circles, we compare three different methods: RSD, BCT, and STVUE. For triangles, RPD, VBT and STVUT were applied. We evaluated these alternatives with 232 experimental images containing 142 circular signs and 82 triangular signs. We found that RSD in the circle detection and STVUT in the triangle detection provide the best detection rates of 93% and 90% respectively. The main contribution of this paper is to present a novel approach for extracting boundary of traffic sign.

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013
DOIs
Publication statusPublished - 2013 Apr 10
Event7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013 - Kota Kinabalu, Malaysia
Duration: 2013 Jan 172013 Jan 19

Other

Other7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013
CountryMalaysia
CityKota Kinabalu
Period13/1/1713/1/19

Fingerprint

Traffic signs
Cameras
Color

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems

Cite this

Kim, J., Choi, Y., Kim, S., Lim, K., & Byun, H. (2013). Real-time traffic sign detection with vehicle camera images. In Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013 [20] https://doi.org/10.1145/2448556.2448576
Kim, Jihie ; Choi, Yeongwoo ; Kim, Seunggyu ; Lim, Kwangyong ; Byun, Hyeran. / Real-time traffic sign detection with vehicle camera images. Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013. 2013.
@inproceedings{de15153311fc4cbc88c1e70c6e4b5850,
title = "Real-time traffic sign detection with vehicle camera images",
abstract = "This paper presents a real-time traffic sign detection method using color properties and shape-based features for real-world environment applications. The proposed method has two main steps: color- based region segmentation and shape-based verification of the segmented area. In the first step, region-of-interest (ROI) is roughly segmented by a simple color-based thresholding method and each segment is corrected by a guided filter. Next, each ROI is verified through a shape analysis to decide whether the ROI is a circle or a triangle. For detecting circles, we compare three different methods: RSD, BCT, and STVUE. For triangles, RPD, VBT and STVUT were applied. We evaluated these alternatives with 232 experimental images containing 142 circular signs and 82 triangular signs. We found that RSD in the circle detection and STVUT in the triangle detection provide the best detection rates of 93{\%} and 90{\%} respectively. The main contribution of this paper is to present a novel approach for extracting boundary of traffic sign.",
author = "Jihie Kim and Yeongwoo Choi and Seunggyu Kim and Kwangyong Lim and Hyeran Byun",
year = "2013",
month = "4",
day = "10",
doi = "10.1145/2448556.2448576",
language = "English",
isbn = "9781450319584",
booktitle = "Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013",

}

Kim, J, Choi, Y, Kim, S, Lim, K & Byun, H 2013, Real-time traffic sign detection with vehicle camera images. in Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013., 20, 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013, Kota Kinabalu, Malaysia, 13/1/17. https://doi.org/10.1145/2448556.2448576

Real-time traffic sign detection with vehicle camera images. / Kim, Jihie; Choi, Yeongwoo; Kim, Seunggyu; Lim, Kwangyong; Byun, Hyeran.

Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013. 2013. 20.

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

TY - GEN

T1 - Real-time traffic sign detection with vehicle camera images

AU - Kim, Jihie

AU - Choi, Yeongwoo

AU - Kim, Seunggyu

AU - Lim, Kwangyong

AU - Byun, Hyeran

PY - 2013/4/10

Y1 - 2013/4/10

N2 - This paper presents a real-time traffic sign detection method using color properties and shape-based features for real-world environment applications. The proposed method has two main steps: color- based region segmentation and shape-based verification of the segmented area. In the first step, region-of-interest (ROI) is roughly segmented by a simple color-based thresholding method and each segment is corrected by a guided filter. Next, each ROI is verified through a shape analysis to decide whether the ROI is a circle or a triangle. For detecting circles, we compare three different methods: RSD, BCT, and STVUE. For triangles, RPD, VBT and STVUT were applied. We evaluated these alternatives with 232 experimental images containing 142 circular signs and 82 triangular signs. We found that RSD in the circle detection and STVUT in the triangle detection provide the best detection rates of 93% and 90% respectively. The main contribution of this paper is to present a novel approach for extracting boundary of traffic sign.

AB - This paper presents a real-time traffic sign detection method using color properties and shape-based features for real-world environment applications. The proposed method has two main steps: color- based region segmentation and shape-based verification of the segmented area. In the first step, region-of-interest (ROI) is roughly segmented by a simple color-based thresholding method and each segment is corrected by a guided filter. Next, each ROI is verified through a shape analysis to decide whether the ROI is a circle or a triangle. For detecting circles, we compare three different methods: RSD, BCT, and STVUE. For triangles, RPD, VBT and STVUT were applied. We evaluated these alternatives with 232 experimental images containing 142 circular signs and 82 triangular signs. We found that RSD in the circle detection and STVUT in the triangle detection provide the best detection rates of 93% and 90% respectively. The main contribution of this paper is to present a novel approach for extracting boundary of traffic sign.

UR - http://www.scopus.com/inward/record.url?scp=84875854244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875854244&partnerID=8YFLogxK

U2 - 10.1145/2448556.2448576

DO - 10.1145/2448556.2448576

M3 - Conference contribution

SN - 9781450319584

BT - Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013

ER -

Kim J, Choi Y, Kim S, Lim K, Byun H. Real-time traffic sign detection with vehicle camera images. In Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2013. 2013. 20 https://doi.org/10.1145/2448556.2448576