Real-time illumination-invariant speed-limit sign recognition based on a modified census transform and Support Vector Machines

Kwangyong Lim, Taewoo Lee, Changmok Shin, Soonwook Chung, Yeongwoo Choi, Hyeran Byun

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

In this paper, we propose a robust illumination system for speed-limit sign recognition in real-time. Real-time traffic sign detection with various illuminations is one of the challenges in a vision-based intelligent vehicle system, as illumination varies greatly in real-world road images based on factors such as driving time, weather, lighting conditions, and driving directions. Our method uses a MCT (Modified Census Transform) as an illumination-invariant method for the real-time detection of traffic signs and uses a SVM (Support Vector Machine) as a classifier for detection and validation. With the proposed method, we have obtained a very high detection rate of 99.8% and recognition rates of 98.4% on various real-world driving images.

Original languageEnglish
DOIs
Publication statusPublished - 2014 Jan 1
Event8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014 - Siem Reap, Cambodia
Duration: 2014 Jan 92014 Jan 11

Other

Other8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014
CountryCambodia
CitySiem Reap
Period14/1/914/1/11

Fingerprint

Support vector machines
Lighting
Traffic signs
Intelligent vehicle highway systems
Classifiers
Mathematical transformations

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems

Cite this

Lim, K., Lee, T., Shin, C., Chung, S., Choi, Y., & Byun, H. (2014). Real-time illumination-invariant speed-limit sign recognition based on a modified census transform and Support Vector Machines. Paper presented at 8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014, Siem Reap, Cambodia. https://doi.org/10.1145/2557977.2558090
Lim, Kwangyong ; Lee, Taewoo ; Shin, Changmok ; Chung, Soonwook ; Choi, Yeongwoo ; Byun, Hyeran. / Real-time illumination-invariant speed-limit sign recognition based on a modified census transform and Support Vector Machines. Paper presented at 8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014, Siem Reap, Cambodia.
@conference{2c2ccbef5a634bd6aa5a13294e0a033c,
title = "Real-time illumination-invariant speed-limit sign recognition based on a modified census transform and Support Vector Machines",
abstract = "In this paper, we propose a robust illumination system for speed-limit sign recognition in real-time. Real-time traffic sign detection with various illuminations is one of the challenges in a vision-based intelligent vehicle system, as illumination varies greatly in real-world road images based on factors such as driving time, weather, lighting conditions, and driving directions. Our method uses a MCT (Modified Census Transform) as an illumination-invariant method for the real-time detection of traffic signs and uses a SVM (Support Vector Machine) as a classifier for detection and validation. With the proposed method, we have obtained a very high detection rate of 99.8{\%} and recognition rates of 98.4{\%} on various real-world driving images.",
author = "Kwangyong Lim and Taewoo Lee and Changmok Shin and Soonwook Chung and Yeongwoo Choi and Hyeran Byun",
year = "2014",
month = "1",
day = "1",
doi = "10.1145/2557977.2558090",
language = "English",
note = "8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014 ; Conference date: 09-01-2014 Through 11-01-2014",

}

Lim, K, Lee, T, Shin, C, Chung, S, Choi, Y & Byun, H 2014, 'Real-time illumination-invariant speed-limit sign recognition based on a modified census transform and Support Vector Machines' Paper presented at 8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014, Siem Reap, Cambodia, 14/1/9 - 14/1/11, . https://doi.org/10.1145/2557977.2558090

Real-time illumination-invariant speed-limit sign recognition based on a modified census transform and Support Vector Machines. / Lim, Kwangyong; Lee, Taewoo; Shin, Changmok; Chung, Soonwook; Choi, Yeongwoo; Byun, Hyeran.

2014. Paper presented at 8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014, Siem Reap, Cambodia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Real-time illumination-invariant speed-limit sign recognition based on a modified census transform and Support Vector Machines

AU - Lim, Kwangyong

AU - Lee, Taewoo

AU - Shin, Changmok

AU - Chung, Soonwook

AU - Choi, Yeongwoo

AU - Byun, Hyeran

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper, we propose a robust illumination system for speed-limit sign recognition in real-time. Real-time traffic sign detection with various illuminations is one of the challenges in a vision-based intelligent vehicle system, as illumination varies greatly in real-world road images based on factors such as driving time, weather, lighting conditions, and driving directions. Our method uses a MCT (Modified Census Transform) as an illumination-invariant method for the real-time detection of traffic signs and uses a SVM (Support Vector Machine) as a classifier for detection and validation. With the proposed method, we have obtained a very high detection rate of 99.8% and recognition rates of 98.4% on various real-world driving images.

AB - In this paper, we propose a robust illumination system for speed-limit sign recognition in real-time. Real-time traffic sign detection with various illuminations is one of the challenges in a vision-based intelligent vehicle system, as illumination varies greatly in real-world road images based on factors such as driving time, weather, lighting conditions, and driving directions. Our method uses a MCT (Modified Census Transform) as an illumination-invariant method for the real-time detection of traffic signs and uses a SVM (Support Vector Machine) as a classifier for detection and validation. With the proposed method, we have obtained a very high detection rate of 99.8% and recognition rates of 98.4% on various real-world driving images.

UR - http://www.scopus.com/inward/record.url?scp=84899707632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899707632&partnerID=8YFLogxK

U2 - 10.1145/2557977.2558090

DO - 10.1145/2557977.2558090

M3 - Paper

ER -

Lim K, Lee T, Shin C, Chung S, Choi Y, Byun H. Real-time illumination-invariant speed-limit sign recognition based on a modified census transform and Support Vector Machines. 2014. Paper presented at 8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014, Siem Reap, Cambodia. https://doi.org/10.1145/2557977.2558090