Pavement crack identification based on automatic threshold iterative method

Guofeng Lu; Qiancheng Zhao; Jianguo Liao; Yongbiao He

doi:10.1117/12.2265253

23 January 2017 Pavement crack identification based on automatic threshold iterative method

Guofeng Lu, Qiancheng Zhao, Jianguo Liao, Yongbiao He

Proceedings Volume 10322, Seventh International Conference on Electronics and Information Engineering; 103221F (2017) https://doi.org/10.1117/12.2265253
Event: Seventh International Conference on Electronics and Information Engineering, 2016, Nanjing, China

Abstract

Crack detection is an important issue in concrete infrastructure. Firstly, the accuracy of crack geometry parameters measurement is directly affected by the extraction accuracy, the same as the accuracy of the detection system. Due to the properties of unpredictability, randomness and irregularity, it is difficult to establish recognition model of crack. Secondly, various image noise, caused by irregular lighting conditions, dark spots, freckles and bump, exerts an influence on the crack detection accuracy. Peak threshold selection method is improved in this paper, and the processing of enhancement, smoothing and denoising is conducted before iterative threshold selection, which can complete the automatic selection of the threshold value in real time and stability.

Citation Download Citation

Guofeng Lu, Qiancheng Zhao, Jianguo Liao, and Yongbiao He "Pavement crack identification based on automatic threshold iterative method", Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103221F (23 January 2017); https://doi.org/10.1117/12.2265253

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