Automated Multiple Concrete Damage Detection Using Instance Segmentation Deep Learning Model

Abstract

In many developed countries with a long history of urbanization, there is an increasing need for automated computer vision (CV)-based inspection to replace conventional labor-intensive visual inspection. This paper proposes a technique for the automated detection of multiple concrete damage based on a state-of-the-art deep learning framework, Mask R-CNN, developed for instance segmentation. The structure of Mask R-CNN, which consists of three stages (region proposal, classification, and segmentation) is optimized for multiple concrete damage detection. The optimized Mask R-CNN is trained with 765 concrete images including cracks, efflorescence, rebar exposure, and spalling. The performance of the trained Mask R-CNN is evaluated with 25 actual test images containing damage as well as environmental objects. Two types of metrics are proposed to measure localization and segmentation performance. On average, 90.41% precision and 90.81% recall are achieved for localization and 87.24% precision and 87.58% recall for segmentation, which indicates the excellent field applicability of the trained Mask R-CNN. This paper also qualitatively discusses the test results by explaining that the architecture of Mask R-CNN that is optimized for general object detection purposes, can be modified to detect long and slender shapes of cracks, rebar exposure, and efflorescence in further research.

A Novel Approach for Detection of Pavement Crack and Sealed Crack Using Image Processing and Salp Swarm Algorithm Optimized Machine Learning

“…Moreover, to demonstrate the capability of the newly constructed CV-SSA-SVC, Random Forest Classification (RFC) model [97], Backpropagation Artificial Neural Network (BPANN) [98,99], and Convolutional Neural Network (CNN) models [100] have been selected as benchmark approaches. e RFC, BPANN, and CNN are capable classifiers and have been widely employed in pattern recognition and particularly in data-driven or structural health monitoring based on computer vision [101][102][103][104][105][106][107][108][109][110][111][112].…”

Concrete Spalling Severity Classification Using Image Texture Analysis and a Novel Jellyfish Search Optimized Machine Learning Approach

“…In addition, to demonstrate the JSO-SVC predictive performance, the random forest classification (RFC) model [79] and convolutional neural network (CNN) models [80] have been employed as benchmark approaches. e RFC and CNN are selected for result comparison in this study because these two machine learning approaches have been successfully applied in various works related to computer vision-based or nondestructive testing-based structural health monitoring/diagnosis [14,26,[81][82][83][84][85][86][87][88].…”

“…Recently, deep learning methods have also been applied to tackle the problem of interest. e main advantage of the deep learning models is that the feature extraction phase can be performed automatically [13,14].…”

Defect Detection of Subway Tunnels Using Advanced U-Net Network

“…In recent years, deep learning techniques have been successfully applied to defect detection tasks based on real-world datasets. For instance, Kim et al [ 50 ] used Mask R-CNN to detect and segment defects in multiple kings of civil infrastructure. Bai et al [ 51 ] used Robust Mask R-CNN for the task of crack detection.…”