Cracks are important indexes to evaluate the health status of concrete structures. To accurately and automatically identify the cracks of concrete structures, and solve the time-consuming and labor-intensive limits of manual detection methods, this paper proposed an image-based concrete cracks identification method based on a lightweight Convolutional Neural Network, which includes three modules: crack classification, semantic segmentation and quantitative calculation of crack geometric size. Firstly, the S_MobileNet was used to classify cracks, exclude irrelevant regions, and reduce the interference of non-crack images; Secondly, the optimized method SM-UNet based on the U-Net network was employed to segment the detected crack image at the pixel level; Finally, based on the results of crack semantic segmentation, image post-processing technology was used to realize the quantitative calculation of crack geometric size parameters, which provides a basis for crack damage assessment of concrete structures. The experimental results show that this study provides a solution for the automatic detection of crack images and high-precision measurement of crack size, which has an important value in scientific research and engineering application.
Image-based Concrete Cracks Identification under Complex Background with Lightweight Convolutional Neural Network
KSCE J Civ Eng
KSCE Journal of Civil Engineering ; 27 , 12 ; 5231-5242
01.12.2023
12 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Research on Concrete Cracks Recognition based on Dual Convolutional Neural Network
Springer Verlag | 2019
|Research on Concrete Cracks Recognition based on Dual Convolutional Neural Network
Online Contents | 2019
|British Library Conference Proceedings | 2018
|