Physical condition analysis of road signs using image template

W. Mohd-Isa; N. F. Md-Saffi; S. Mat-Desa; N. Hashim; Z. Che-Embi; J. Abdullah; A. Ali

doi:10.1117/12.2521621

22 March 2019 Physical condition analysis of road signs using image template

W. Mohd-Isa, N. F. Md-Saffi, S. Mat-Desa, N. Hashim, Z. Che-Embi, J. Abdullah, A. Ali

Proceedings Volume 11049, International Workshop on Advanced Image Technology (IWAIT) 2019; 1104944 (2019) https://doi.org/10.1117/12.2521621
Event: 2019 Joint International Workshop on Advanced Image Technology (IWAIT) and International Forum on Medical Imaging in Asia (IFMIA), 2019, Singapore, Singapore

Abstract

Road signs play an essential role in ensuring road safety. However, due to external factors such as bad weather, road signs may not be in their best condition that may hinder effective communication between the road and the road users. Although the study on detection and classification of road signs is becoming more common these days, there is yet to exist a study that analyzes whether a road sign is in a good or bad condition. The basis of this study is to implement image template algorithms on road signs that will be used to analyze their physical condition as good or damaged. In addition to template matching, this study proposes a template difference method for its condition analysis. Analyses on three shapes of road signs: circular, triangular, and diamond give out the average correctly classified detection as 60% and 78%, respectively for template matching and template difference method.

Citation Download Citation

W. Mohd-Isa, N. F. Md-Saffi, S. Mat-Desa, N. Hashim, Z. Che-Embi, J. Abdullah, and A. Ali "Physical condition analysis of road signs using image template", Proc. SPIE 11049, International Workshop on Advanced Image Technology (IWAIT) 2019, 1104944 (22 March 2019); https://doi.org/10.1117/12.2521621

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available