23 January 2017 Pavement crack identification based on automatic threshold iterative method
Author Affiliations +
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.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Guofeng Lu, Qiancheng Zhao, Jianguo Liao, 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); doi: 10.1117/12.2265253; https://doi.org/10.1117/12.2265253
PROCEEDINGS
6 PAGES


SHARE
Back to Top