This paper compares the performance of common edge detectors and deep convolutional neural networks (DCNN) for image-based crack detection in concrete structures. A dataset of 19 high definition images (3420 sub-images, 319 with cracks and 3101 without) of concrete is analyzed using six common edge detection schemes (Roberts, Prewitt, Sobel, Laplacian of Gaussian, Butterworth, and Gaussian) and using the AlexNet DCNN architecture in fully trained, transfer learning, and classifier modes. The relative performance of each crack detection method is compared here for the first time on a single dataset. Edge detection methods accurately detected 53-79% of cracked pixels, but they produced residual noise in the final binary images. The best of these methods was useful in detecting cracks wider than 0.1 mm. DCNN methods were used to label images, and accurately labeled them with 99% accuracy. In transfer learning mode, the network accurately detected about 86% of cracked images. DCNN methods also detected much finer cracks than edge detection methods. In fully trained and classifier modes, the network detected cracks wider than 0.08 mm; in transfer learning mode, the network was able to detect cracks wider than 0.04 mm. Computational times for DCNN are shorter than the most efficient edge detection algorithms, not considering the training process. These results show significant promise for future adoption of DCNN

SDNET2018 is an annotated image dataset for training, validation, and benchmarking of artificial intelligence based crack detection algorithms for concrete. SDNET2018 contains over 56,000 images of cracked and non-cracked concrete bridge decks, walls, and pavements. The dataset includes cracks as narrow as 0.06 mm and as wide as 25 mm. The dataset also includes images with a variety of obstructions, including shadows, surface roughness, scaling, edges, holes, and background debris. SDNET2018 will be useful for the continued development of concrete crack detection algorithms based on deep convolutional neural networks (DCNNs), which are a subject of continued research in the field of structural health monitoring. The authors present benchmark results for crack detection using SDNET2018 and a crack detection algorithm based on the AlexNet DCNN architecture. SDNET2018 is freely available at https://doi.org/10.15142/T3TD19.

No abstract

Unmanned Aerial Systems (UASs) have become of considerable private and commercial interest for a variety of jobs and entertainment in the past 10 years. This paper is a literature review of the state of practice for the United States bridge inspection programs and outlines how automated and unmanned bridge inspections can be made suitable for present and future needs. At its best, current technology limits UAS use to an assistive tool for the inspector to perform a bridge inspection faster, safer, and without traffic closure. The major challenges for UASs are satisfying restrictive Federal Aviation Administration regulations, control issues in a GPS denied environment, pilot expenses and availability, time and cost allocated to tuning, maintenance, post-processing time, and acceptance of the collected data by bridge owners. Using UASs with self-navigation abilities and improving imageprocessing algorithms to provide results near real-time could revolutionize the bridge inspection industry by providing accurate, multi-use, autonomous three-dimensional models and damage identification.

No abstract