An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module

Abstract

Buildings and infrastructure in congested metropolitan areas are continuously deteriorating. Various structural flaws such as surface cracks, spalling, delamination, and other defects are found, and keep on progressing. Traditionally, the assessment and inspection is conducted by humans; however, due to human physiology, the assessment limits the accuracy of image evaluation, making it more subjective rather than objective. Thus, in this study, a multivariant defect recognition technique was developed to efficiently assess the various structural health issues of concrete. The image dataset used was comprised of 3650 different types of concrete defects, including surface cracks, delamination, spalling, and non-crack concretes. The proposed scheme of this paper is the development of an automated image-based concrete condition recognition technique to categorize, not only non-defective concrete into defective concrete, but also multivariant defects such as surface cracks, delamination, and spalling. The developed convolution-based model multivariant defect recognition neural network can recognize different types of defects on concretes. The trained model observed a 98.8% defect detection accuracy. In addition, the proposed system can promote the development of various defect detection and recognition methods, which can accelerate the evaluation of the conditions of existing structures.

Computer Vision-Based Bridge Inspection and Monitoring: A Review

“…With the continuous progress of CV technology, comprehensive multi-parameter identification of vehicles is a trend that will continue to grow in the future. (10) The current bridge SHM systems mostly perform independent measurements of vehicles and bridges, and most of the assessment of bridge conditions is achieved only through the analysis of the output responses of the bridge, lacking accurate input information. Simultaneously obtaining the parameter information of the bridge structure and the vehicles on the bridge is an important direction for the development of the bridge SHM system in the future.…”

“…The traditional visual inspection has difficulty meeting the inspection requirements of modern bridges, due to its relatively subjective decision-making process, low detection efficiency, and low safety. To improve the detection efficiency of bridge surface defects detection and promote the intelligence of the industry, many researchers have used cameras to collect images of bridge surface defects [ 7 , 8 , 9 , 10 ] and have combined deep learning (DL) and computer vision (CV) techniques to analyze the camera-recorded images intelligently [ 11 , 12 , 13 , 14 , 15 , 16 ]. In addition, vibration measurement is very important for evaluating the integrity and safety of bridges.…”

Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open- Access Papers

“…Five publications cover crack detection use cases. For example, Alqahtani [86] used a CNN, and Elhariri et al [87] as well as Kim et al [88] used a VGG. Also, DL models like ResNet, DenseNet, and an ensemble architecture are proposed by some authors.…”