Automated regional seismic damage assessment of buildings using an unmanned aerial vehicle and a convolutional neural network

Abstract A rapid assessment of the seismic damage to buildings can facilitate improved emergency response and timely relief in earthquake-prone areas. In this study, an automated building seismic damage assessment method using an unmanned aerial vehicle (UAV) and a convolutional neural network (CNN) is introduced. The method consists of three parts: (1) data preparation, (2) building image segmentation, and (3) CNN-based building seismic damage assessment. First, a three-dimensional (3D) building model, aerial images, and camera data are used for the following simulation. Next, a building image segmentation method is proposed using the 3D building model as georeference, through which multi-view segmented building images can be obtained. Subsequently, a CNN model based on VGGNet is adopted to assess the seismic damage of each building. The CNN model is fine-tuned based on manually tagged building images obtained from the Internet. Finally, a case study of the old Beichuan town is used to demonstrate the effectiveness of the proposed method. The damage distribution of the area is obtained with an accuracy of 89.39%.

[1]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[2]  C. Song,et al.  Urban 3D GIS From LiDAR and digital aerial images , 2004, Comput. Geosci..

[3]  D. Dominici,et al.  UAV photogrammetry in the post-earthquake scenario: case studies in L'Aquila , 2017 .

[4]  Xuefeng Zhao,et al.  Automatic pixel‐level multiple damage detection of concrete structure using fully convolutional network , 2019, Comput. Aided Civ. Infrastructure Eng..

[5]  Tom Davis,et al.  Opengl programming guide: the official guide to learning opengl , 1993 .

[6]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Carol J. Friedland,et al.  High Resolution Imagery Collection Utilizing Unmanned Aerial Vehicles (UAVs) for Post-Disaster Studies , 2012 .

[8]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[9]  Norman Kerle,et al.  UAV-based urban structural damage assessment using object-based image analysis and semantic reasoning , 2014 .

[10]  Haoting Liu,et al.  Damage Degree Evaluation of Earthquake Area Using UAV Aerial Image , 2016 .

[11]  Zhen Xu,et al.  Improving the Accuracy of near Real-Time Seismic Loss Estimation using Post-Earthquake Remote Sensing Images , 2018, Earthquake Spectra.

[12]  Billie F. Spencer,et al.  Towards Automated Post-Earthquake Inspections with Deep Learning-based Condition-Aware Models , 2018, ArXiv.

[13]  M. Pauline Baker,et al.  Computer graphics with OpenGL , 1986 .

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  Dulcy M. Abraham,et al.  Automated defect classification in sewer closed circuit television inspections using deep convolutional neural networks , 2018, Automation in Construction.

[16]  Hong Guan,et al.  Seismic damage simulation in urban areas based on a high-fidelity structural model and a physics engine , 2014, Natural Hazards.

[17]  Takayuki Okatani,et al.  A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks , 2019, Automation in Construction.

[18]  Takis Kasparis,et al.  Automatic Vegetation Identification and Building Detection from a Single Nadir Aerial Image , 2009, Remote. Sens..

[19]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Jianda Han,et al.  Search and Rescue Rotary‐Wing UAV and Its Application to the Lushan Ms 7.0 Earthquake , 2016, J. Field Robotics.

[21]  Hong Guan,et al.  Building seismic response and visualization using 3D urban polygonal modeling , 2015 .

[22]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[23]  Khalid M. Mosalam,et al.  Deep Transfer Learning for Image‐Based Structural Damage Recognition , 2018, Comput. Aided Civ. Infrastructure Eng..

[24]  J. Goltz.  The Northridge, California Earthquake of January 17, 1994: General Reconnaissance Report , 1994 .

[25]  Antonia Teresa Spano,et al.  UAV STRATEGIES VALIDATION AND REMOTE SENSING DATA FOR DAMAGE ASSESSMENT IN POST-DISASTER SCENARIOS , 2018 .

[26]  Cao Vu Dung,et al.  Autonomous concrete crack detection using deep fully convolutional neural network , 2019, Automation in Construction.

[27]  Timo Balz,et al.  Building-damage detection using post-seismic high-resolution SAR satellite data , 2010 .

[28]  Jie Shan,et al.  A comprehensive review of earthquake-induced building damage detection with remote sensing techniques , 2013 .

[29]  Babak Mansouri,et al.  Streamlining Post-Earthquake Data Collection and Damage Assessment for the 2003 Bam, Iran, Earthquake using VIEWS™ (Visualizing Impacts of Earthquakes with Satellites) , 2005 .

[30]  Lorenzo Bruzzone,et al.  Earthquake Damage Assessment of Buildings Using VHR Optical and SAR Imagery , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Yu. G. Puzachenko,et al.  USE OF REMOTE SENSING IMAGERY IN ANALYSIS OF CONSEQUENCES OF THE ARMENIAN EARTHQUAKE , 1990 .

[32]  Tania Landes,et al.  Contribution of two plane detection algorithms to recognition of intact and damaged buildings in lidar data , 2008 .

[33]  Ioannis Brilakis,et al.  Visual retrieval of concrete crack properties for automated post-earthquake structural safety evaluation , 2011 .

[34]  Ahmed El-Mowafy.  Performance Analysis of the RTK Technique in an Urban Environment , 2000 .

[35]  W. Y. Kam,et al.  Seismic performance of reinforced concrete buildings in the 22 February Christchurch (Lyttelton) earthquake , 2011 .

[36]  Huili Gong,et al.  Collapsed houses automatic identification based on texture changes of post-earthquake aerial remote sensing image , 2010, 2010 18th International Conference on Geoinformatics.

[37]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[38]  Dongho Kang,et al.  Autonomous UAVs for Structural Health Monitoring Using Deep Learning and an Ultrasonic Beacon System with Geo‐Tagging , 2018, Comput. Aided Civ. Infrastructure Eng..

[39]  Muneo Hori,et al.  Petascale Computation for Earthquake Engineering , 2011, Computing in Science & Engineering.