Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks

Abstract

A number of image processing techniques (IPTs) have been implemented for detecting civil infrastructure defects to partially replace human-conducted onsite inspections. These IPTs are primarily used to manipulate images to extract defect features, such as cracks in concrete and steel surfaces. However, the extensively varying real-world situations (e.g., lighting and shadow changes) can lead to challenges to the wide adoption of IPTs. To overcome these challenges, this article proposes a vision-based method using a deep architecture of convolutional neural networks (CNNs) for detecting concrete cracks without calculating the defect features. As CNNs are capable of learning image features automatically, the proposed method works without the conjugation of IPTs for extracting features. The designed CNN is trained on 40 K images of 256 × 256 pixel resolutions and, consequently, records with about 98% accuracy. The trained CNN is combined with a sliding window technique to scan any image size larger than 256 × 256 pixel resolutions. The robustness and adaptability of the proposed approach are tested on 55 images of 5,888 × 3,584 pixel resolutions taken from a different structure which is not used for training and validation processes under various conditions (e.g., strong light spot, shadows, and very thin cracks). Comparative studies are conducted to examine the performance of the proposed CNN using traditional Canny and Sobel edge detection methods. The results show that the proposed method shows

Neurocomputing in Civil Infrastructure

“…A recent application of deep neural network learning model in construction has been presented in this paper. In addition, Cha et al [124] presented deep learningbased crack damage detection using convolutional neural network. Other applications of deep neural network learning model should follow.…”

Health Monitoring for Balancing Tail Ropes of a Hoisting System Using a Convolutional Neural Network

“…It is expressed as the probabilistic expression p(y = j/x), where x is the input sample and the corresponding label is y, p is the probability of sample j. Therefore, the output will be an n-dimensional vector for a classifier with n classes and the sum of the elements in a vector is 1, as shown by Equation (6) [20,35]:…”

“…In the training process, the optimization algorithm is used to minimize the loss function to complete the network training. The loss function J(θ) is defined by Equation (7) [35]:…”

“…The structure of CNN is shown in Figure 3, and the configurations of each layer are listed in Table 1. In addition, before each round of training, the dataset is randomly disturbed, the network parameters are randomly initialized, the L 2 regularization term is added to the fully connected layer F1, and a stochastic gradient descent (SGD) algorithm is used to train the network [35]. Before the training and testing of the BTRs dataset, 70% of the total sample is selected randomly as the training sample, and the remaining 30% is used as the testing sample (i.e., 3150 samples are selected as the training dataset and 1350 samples are used as the testing dataset).…”

Deep Learning for Financial Time Series Forecasting in A-Trader System

“…This involves intensive computation, especially for networks with more than two layers. Often, the gradient converges to machine-zero value and training stops or explodes into a huge value; ultimately training process becomes intractable [30,31]. Deep learning offers a new learning algorithm: to find the initial parameters for deep CNN, it uses a series of single layer networks -which do not suffer from vanishing or exploding gradients.…”