Abstract
Abstract. In this paper, we develop and implement end-to-end deep learning approaches to automatically detect two important types of structural failures, cracks and spalling, of buildings and bridges in extreme events such as major earthquakes. A total of 2,229 images were annotated, and are used to train and validate three newly developed Mask Regional Convolutional Neural Networks (Mask R-CNNs). In addition, three sets of public images for different disasters were used to test the accuracy of these models. For detecting and marking these two types of structural failures, one of proposed methods can achieve an accuracy of 67.6% and 81.1%, respectively, on low- and high-resolution images collected from field investigations. The results demonstrate that it is feasible to use the proposed end-to-end method for automatically locating and segmenting the damage using 2D images which can help human experts in cases of disasters.
Highlights
Automation on Structural Damage Detection (SDD) and Structural Health Monitoring (SHM) is made possible with the rapid development of vision- and vibration-based technologies
With the successful application of deep learning methods on a wide range of problems, it is imperative to apply these techniques on SDD and SHM
The goal of this study is to facilitate the backbone of Mask Regional Convolutional Neural Networks (R-CNNs) to extract more useful features in cracks and spalling detection
Summary
Automation on Structural Damage Detection (SDD) and Structural Health Monitoring (SHM) is made possible with the rapid development of vision- and vibration-based technologies. The application of deep learning on SDD and SHM requires an interdisciplinary team. These teams typically use low-cost sensors and autonomous platforms such as Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) in field inspections for real-time inspection and monitoring. Detection and identification of structural damage can typically be performed by image segmentation and image classification. The goal of image segmentation is to detect and mark damage in specific regions where each pixel in the image is labeled to denote types of material failures, such as cracks, spalling and other indicators of structural failures. On the other hand, are the phenomena of discontinuity of materials observed on the surface of them
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
