Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure

Abstract

With the growing number of aging infrastructure across the world, there is a high demand for a more effective inspection method to assess its conditions. Routine assessment of structural conditions is a necessity to ensure the safety and operation of critical infrastructure. However, the current practice to detect structural damages, such as cracks, depends on human visual observation methods, which are prone to efficiency, cost, and safety concerns. In this article, we present an automated detection method, which is based on convolutional neural network models and a non-overlapping window-based approach, to detect crack/non-crack conditions of concrete structures from images. To this end, we construct a data set of crack/non-crack concrete structures, comprising 32,704 training patches, 2074 validation patches, and 6032 test patches. We evaluate the performance of our approach using 15 state-of-the-art convolutional neural network models in terms of number of parameters required to train the models, area under the curve, and inference time. Our approach provides over 95% accuracy and over 87% precision in detecting the cracks for most of the convolutional neural network models. We also show that our approach outperforms existing models in literature in terms of accuracy and inference time. The best performance in terms of area under the curve was achieved by visual geometry group-16 model (area under the curve = 0.9805) and best inference time was provided by AlexNet (0.32 s per image in size of 256 × 256 × 3). Our evaluation shows that deeper convolutional neural network models have higher detection accuracies; however, they also require more parameters and have higher inference time. We believe that this study would act as a benchmark for real-time, automated crack detection for condition assessment of infrastructure.

Real-Time Concrete Damage Detection Using Deep Learning for High Rise Structures

“… The comparison of the detection results obtained in this article with the current work is presented in Table V and Table VI. The F1 score of the YOLO-v3 is found to be 4% and 3% higher than that of AlexNet and VGG models, 6% higher than that of the InceptionResnet-v2 deep learning model proposed by A.S. Rao et al [41], and 5% higher than that of the ResNeXt-101-32x8d proposed by A.S. Rao et al [41]. TYOLO-v3 also achieves a comparable F1 score.…”

Drone-Based Container Crane Inspection: Concept, Challenges and Preliminary Results

“…Health monitoring is an essential process in ensuring the safety and serviceability of civil infrastructure like bridges and container cranes (Rao et al, 2020;Saleem et al, 2020;Stein, 2018). Current practice for assessing structural health of container cranes is mainly based on visual inspections by human operators (Hoskere et al, 2020).…”

Image-Based Automated Width Measurement of Surface Cracking

“…The latter techniques have recently raised interest among researchers mainly because DL allows the implementation of robust solutions that can be applied in a wide variety of materials/structural elements such as paving, walls, and columns. In addition, it allows the use of different illumination conditions, orientation, distance, and objects [27][28][29][30]. DL-based algorithms rely on a learning process, which involves a previous labeling of images, so that the network can make a prediction through the learning process.…”

“…DL-based algorithms rely on a learning process, which involves a previous labeling of images, so that the network can make a prediction through the learning process. Several types of network architectures have been explored in the literature [14,30,31]. The main difference across them is the generated output: images composed of blocks classified as failures [28,30], pixel-level binary segmentation [29,[32][33][34], or a combination of both [34,35].…”