Deep learning‐based multi‐class damage detection for autonomous post‐disaster reconnaissance

Abstract

Timely assessment of damages induced to buildings due to an earthquake is critical for ensuring life safety, mitigating financial losses, and expediting the rehabilitation process as well as enhancing the structural resilience where resilience is measured by an infrastructure's capacity to restore full functionality post extreme events. Since manual inspection is expensive, time consuming and risky, low‐cost unmanned aerial vehicles or robots can be leveraged as a viable alternative for quick reconnaissance. Visual data captured by the sensors mounted on the robots can be analyzed, and the damages can be detected and classified autonomously. The present study proposes the use of deep learning‐based approaches to this end. Region‐based convolutional neural network (Faster RCNN) is exploited to detect four different damage types, namely, surface crack, spalling (which includes façade spalling and concrete spalling), and severe damage with exposed rebars and severely buckled rebars. The performance of the proposed approach is evaluated on manually annotated image data collected from reinforced concrete buildings damaged under several past earthquakes such as Nepal (2015), Taiwan (2016), Ecuador (2016), Erzincan (1992), Duzce (1999), Bingol (2003), Peru (2007), Wenchuan (2008), and Haiti (2010). Several experiments are presented in the paper to illustrate the capabilities, as well as the limitations, of the proposed approach for earthquake reconnaissance. It was observed that Inception‐ResNet‐v2 significantly outperforms the other networks considered in this study. The research outcome is a stepping stone forward to facilitate the autonomous assessment of buildings where this can be potentially useful for insurance companies, government agencies, and property owners.

Deep learning smartphone application for real‐time detection of defects in buildings

“…CAHM is an increasingly growing research field with a number of applications for detecting defects in civil structures such as the ones proposed in previous studies 61–63 . In this current research, we developed a deep learning‐based smartphone application for real‐time detection of key building defects including cracks and another three categories of building defects caused by dampness, namely, mould, stain and paint deterioration which also includes peeling, blistering, flacking and crazing.…”

Detecting Cracks and Spalling Automatically in Extreme Events by End-to-End Deep Learning Frameworks

“…Finally, they used photogrammetry software to construct a 3D reality mesh model so that the cracks can be visualized and quantified further. Mondal et al (2020) used Faster R-CNN to automatically detect four common types of structural damage, including surface cracks, spalling (which includes facade spalling and concrete spalling), and severe damage with exposed rebars and severely buckled rebars, but they didn't mark the enclosing regions of these damage. Instead, they used bounding boxes to give the scope of them.…”

Deep learning for post‐hurricane aerial damage assessment of buildings

“…Some examples of deep learning applications for damage detection and assessment include road crack detection (K. Zhang, Cheng, & Zhang, 2018; A. Zhang et al., 2017; ), rust grade classification (Xu, Gui, & Han, 2020), reinforced concrete (RC) bridge inspection (Liang, 2019), damage detection in high‐rise buildings (Rafiei & Adeli, 2017b), structural damage detection (Abdeljaber, Avci, Kiranyaz, Gabbouj, & Inman, 2017; Gao & Mosalam, 2018; Kang & Cha, 2018; Y.‐Z. Lin, Nie, & Ma, 2017), structural damage classification (Wang, Zhao, Li, Zhao, & Zhao, 2018), and multi‐class damage detection for RC buildings (Ghosh Mondal, Jahanshahi, Wu, & Wu, 2020). Additionally, Lenjani, Yeum, Dyke, and Bilionis (2020) used a region‐based convolutional neural network (CNN) to detect buildings in 2D ground‐level images for post‐disaster evaluation.…”