Abstract
The visual inspection of massive civil infrastructure is a common trend for maintaining its reliability and structural health. However, this procedure, which uses human inspectors, requires long inspection times and relies on the subjective and empirical knowledge of the inspectors. To address these limitations, a machine vision-based autonomous crack detection method is proposed using a deep convolutional neural network (DCNN) technique. It consists of a fully convolutional neural network (FCN) with an encoder and decoder framework for semantic segmentation, which performs pixel-wise classification to accurately detect cracks. The main idea is to capture the global context of a scene and determine whether cracks are in the image while also providing a reduced and essential picture of the crack locations. The visual geometry group network (VGGNet), a variant of the DCCN, is employed as a backbone in the proposed FCN for end-to-end training. The efficacy of the proposed FCN method is tested on a publicly available benchmark dataset of concrete crack images. The experimental results indicate that the proposed method is highly effective for concrete crack classification, obtaining scores of approximately 92% for both the recall and F1 average.
Highlights
Reliability, performance, and life cycle costs are real concerns for almost all in-service massive structures, such as buildings, bridges, nuclear facilities, hydroelectric structures, and dams
Inspired by the recent result of semantic segmentation for precise object detection, we propose a fully convolutional network (FCN) with an encoder and decoder for accurate concrete crack detection
As the concrete crack appears as a strip of line with varied angles and directions, this validates the use of the FCN model with encoder–decoder frameworks for crack detection
Summary
Reliability, performance, and life cycle costs are real concerns for almost all in-service massive structures, such as buildings, bridges, nuclear facilities, hydroelectric structures, and dams. In comparison to the traditional manual inspection-based crack detection system, computer vision and machine learning-based approaches are quickly becoming an integral part of the modern SHM of civil infrastructures to automate crack detection and identification systems [1,7,8]. These methods are mainly built upon common image processing techniques, such as segmentation, fuzzy clustering [9], pattern recognition, image filtering [10], histogram analysis [8,11], edge detection [12], and texture matching. Researchers in [12] applied various edge detection algorithms and found that the wavelet method is the most reliable among such approaches for the purpose of a crack detection system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
