Improving the performance of traffic sign detection using blob tracking

We propose a new approach for tracking circular traffic signs from image sequences to improve the performance of traffic sign detection, by reducing search region and suppressing misdetection caused by temporal occlusion or poor quality of image. Our proposed tracking, called two-layered blobs track...

Full description

Bibliographic Details
Main Authors: Soetedjo, Aryuanto, Yamada, Koichi
Format: Article
Published: IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG 2007
Subjects:
Online Access:http://shdl.mmu.edu.my/2982/
_version_ 1848790201673973760
author Soetedjo, Aryuanto
Yamada, Koichi
author_facet Soetedjo, Aryuanto
Yamada, Koichi
author_sort Soetedjo, Aryuanto
building MMU Institutional Repository
collection Online Access
description We propose a new approach for tracking circular traffic signs from image sequences to improve the performance of traffic sign detection, by reducing search region and suppressing misdetection caused by temporal occlusion or poor quality of image. Our proposed tracking, called two-layered blobs tracking, does not require an accurate model of the fixed object-moving camera system, which is essential in the Kalman-Filter tracking. The experimental results show that the proposed approach could track the circular tra. c signs from a moving camera effectively, without any restrictions on speed and movement of the vehicle, and camera installation, thus it is easy to be implemented in real situation.
first_indexed 2025-11-14T18:08:51Z
format Article
id mmu-2982
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:08:51Z
publishDate 2007
publisher IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
recordtype eprints
repository_type Digital Repository
spelling mmu-29822011-09-29T07:02:24Z http://shdl.mmu.edu.my/2982/ Improving the performance of traffic sign detection using blob tracking Soetedjo, Aryuanto Yamada, Koichi T Technology (General) QA75.5-76.95 Electronic computers. Computer science We propose a new approach for tracking circular traffic signs from image sequences to improve the performance of traffic sign detection, by reducing search region and suppressing misdetection caused by temporal occlusion or poor quality of image. Our proposed tracking, called two-layered blobs tracking, does not require an accurate model of the fixed object-moving camera system, which is essential in the Kalman-Filter tracking. The experimental results show that the proposed approach could track the circular tra. c signs from a moving camera effectively, without any restrictions on speed and movement of the vehicle, and camera installation, thus it is easy to be implemented in real situation. IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG 2007-11 Article NonPeerReviewed Soetedjo, Aryuanto and Yamada, Koichi (2007) Improving the performance of traffic sign detection using blob tracking. IEICE Electronics Express, 4 (21). pp. 684-689. ISSN 1349-2543 http://dx.doi.org/10.1587/elex.4.684 doi:10.1587/elex.4.684 doi:10.1587/elex.4.684
spellingShingle T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
Soetedjo, Aryuanto
Yamada, Koichi
Improving the performance of traffic sign detection using blob tracking
title Improving the performance of traffic sign detection using blob tracking
title_full Improving the performance of traffic sign detection using blob tracking
title_fullStr Improving the performance of traffic sign detection using blob tracking
title_full_unstemmed Improving the performance of traffic sign detection using blob tracking
title_short Improving the performance of traffic sign detection using blob tracking
title_sort improving the performance of traffic sign detection using blob tracking
topic T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2982/
http://shdl.mmu.edu.my/2982/
http://shdl.mmu.edu.my/2982/