Real-Time Ground-Level Building Damage Detection Based on Lightweight and Accurate YOLOv5 Using Terrestrial Images
Open Access
- 8 June 2022
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 14 (12) , 2763
Abstract
Real-time building damage detection effectively improves the timeliness of post-earthquake assessments. In recent years, terrestrial images from smartphones or cameras have become a rich source of disaster information that may be useful in assessing building damage at a lower cost. In this study, we present an efficient method of building damage detection based on terrestrial images in combination with an improved YOLOv5. We compiled a Ground-level Detection in Building Damage Assessment (GDBDA) dataset consisting of terrestrial images with annotations of damage types, including debris, collapse, spalling, and cracks. A lightweight and accurate YOLOv5 (LA-YOLOv5) model was used to optimize the detection efficiency and accuracy. In particular, a lightweight Ghost bottleneck was added to the backbone and neck modules of the YOLOv5 model, with the aim to reduce the model size. A Convolutional Block Attention Module (CBAM) was added to the backbone module to enhance the damage recognition effect. In addition, regarding the scale difference of building damage, the Bi-Directional Feature Pyramid Network (Bi-FPN) for multi-scale feature fusion was used in the neck module to aggregate features with different damage types. Moreover, depthwise separable convolution (DSCONV) was used in the neck module to further compress the parameters. Based on our GDBDA dataset, the proposed method not only achieved detection accuracy above 90% for different damage targets, but also had the smallest weight size and fastest detection speed, which improved by about 64% and 24%, respectively. The model performed well on datasets from different regions. The overall results indicate that the proposed model realizes rapid and accurate damage detection, and meets the requirement of lightweight embedding in the future.Keywords
Funding Information
- National Natural Science Foundation of China Major Program (42192580, 42192583, 41771457, AA22068072)
- National Natural Science Foundation of China (42192580, 42192583, 41771457, AA22068072)
- Guangxi science and technology major project (42192580, 42192583, 41771457, AA22068072)
This publication has 46 references indexed in Scilit:
- Displacement capacity of masonry piers: parametric numerical analyses versus international building codesBulletin of Earthquake Engineering, 2016
- Using Remote Sensing for Building Damage Assessment: GEOCAN Study and Validation for 2011 Christchurch EarthquakeEarthquake Spectra, 2016
- Accelerating Very Deep Convolutional Networks for Classification and DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Building Damage Detection Using Object-Based Image Analysis and ANFIS From High-Resolution Image (Case Study: BAM Earthquake, Iran)IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- High Resolution Imagery Collection for Post-Disaster Studies Utilizing Unmanned Aircraft Systems (UAS)Photogrammetric Engineering & Remote Sensing, 2014
- Towards a rapid automatic detection of building damage using remote sensing for disaster managementDisaster Prevention and Management: An International Journal, 2014
- A comprehensive review of earthquake-induced building damage detection with remote sensing techniquesISPRS Journal of Photogrammetry and Remote Sensing, 2013
- Building damage characteristics based on surveyed data and fragility curves of the 2011 Great East Japan tsunamiNatural Hazards, 2012
- Damage Assessment of 2010 Haiti Earthquake with Post-Earthquake Satellite Image by Support Vector Selection and AdaptationPhotogrammetric Engineering & Remote Sensing, 2011
- Comparative Seismic Risk Studies for German Earthquake Regions on the Basis of the European Macroseismic Scale EMS-98Natural Hazards, 2006