Automated processing of high resolution airborne images for earthquake damage assessment

Emergency response ought to be rapid, reliable and efficient in terms of bringing the necessary help to sites where it is actually needed. Although the remote sensing techniques require minimum fieldwork and allow for continuous coverage, the established approaches rely on a vast manual work and visual assessment thus are time-consuming and imprecise. Automated processes with little possible interaction are in demand. This paper attempts to address the aforementioned issues by employing an unsupervised classification approach to identify building areas affected by an earthquake event. The classification task is formulated in the Markov Random Fields (MRF) framework and only post-event airborne high-resolution images serve as the input. The generated photogrammetric Digital Surface Model (DSM) and a true orthophoto provide height and spectral information to characterize the urban scene through a set of features. The classification proceeds in two phases, one for distinguishing the buildings out of an urban context (urban classification), and the other for identifying the damaged structures (building classification). The algorithms are evaluated on a dataset consisting of aerial images (7 cm GSD) taken after the Emilia-Romagna (Italy) earthquake in 2012.

[1]  Joachim Höhle,et al.  AUTOMATED MAPPING OF BUILDING FACADES BY MACHINE LEARNING , 2014 .

[2]  I. Colomina,et al.  Unmanned aerial systems for photogrammetry and remote sensing: A review , 2014 .

[3]  Fabio Remondino,et al.  State of the art in high density image matching , 2014 .

[4]  Tong Liu,et al.  Monitoring Geologic Hazards and Vegetation Recovery in the Wenchuan Earthquake Region Using Aerial Photography , 2014, ISPRS Int. J. Geo Inf..

[5]  F. Nex,et al.  OBLIQUE MULTI-CAMERA SYSTEMS - ORIENTATION AND DENSE MATCHING ISSUES , 2014 .

[6]  F. Nex,et al.  UAV for 3D mapping applications: a review , 2014 .

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

[8]  Fabio Remondino,et al.  AUTOMATIC ORIENTATION OF LARGE BLOCKS OF OBLIQUE IMAGES , 2013 .

[9]  M. Pierrot Deseilligny,et al.  APERO, AN OPEN SOURCE BUNDLE ADJUSMENT SOFTWARE FOR AUTOMATIC CALIBRATION AND ORIENTATION OF SET OF IMAGES , 2012 .

[10]  Fabio Remondino,et al.  AUTOMATIC ROOF OUTLINES RECONSTRUCTION FROM PHOTOGRAMMETRIC DSM , 2012 .

[11]  Paolo Gamba,et al.  Remote Sensing and Earthquake Damage Assessment: Experiences, Limits, and Perspectives , 2012, Proceedings of the IEEE.

[12]  Konrad Schindler,et al.  An Overview and Comparison of Smooth Labeling Methods for Land-Cover Classification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Florent Lafarge,et al.  Creating Large-Scale City Models from 3D-Point Clouds: A Robust Approach with Hybrid Representation , 2012, International Journal of Computer Vision.

[14]  S. Bartels,et al.  Medical complications associated with earthquakes , 2012, The Lancet.

[15]  Alfred Stein,et al.  Markov-random-field-based super-resolution mapping for identification of urban trees in VHR images , 2011 .

[16]  M. Gerke,et al.  Automatic Structural Seismic Damage Assessment with Airborne Oblique Pictometry© Imagery , 2011 .

[17]  Armin Gruen,et al.  Automatic 3D building extraction from aerial and space images for earthquake risk management , 2011 .

[18]  Norman Kerle,et al.  Satellite-based damage mapping following the 2006 Indonesia earthquake - How accurate was it? , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[19]  Valentyn Tolpekin,et al.  Markov random field based super-resolution mapping for identification of urban trees in VHR images , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[20]  P. Reinartz,et al.  Change Visualization through a Texture-Based Analysis Approach for Disaster Applications , 2010 .

[21]  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.

[22]  Huadong Guo,et al.  An improved automatic detection method for earthquake-collapsed buildings from ADS40 image , 2009 .

[23]  Cem Unsalan,et al.  Damaged building detection in aerial images using shadow Information , 2009, 2009 4th International Conference on Recent Advances in Space Technologies.

[24]  Sergey V. Samsonov,et al.  A review of the status of satellite remote sensing and image processing techniques for mapping natural hazards and disasters , 2009 .

[25]  Norbert Pfeifer,et al.  Real - time data collection and information generation using airborne sensors , 2008 .

[26]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[27]  Martial Hebert,et al.  Discriminative Random Fields , 2006, International Journal of Computer Vision.

[28]  Michael Markus,et al.  Classification of Collapsed Buildings for Fast Damage and Loss Assessment , 2006 .

[29]  M. Crawford,et al.  Damage Patterns from Satellite Images of the 2003 Bam, Iran, Earthquake , 2005 .

[30]  Charles K. Huyck,et al.  Towards Rapid Citywide Damage Mapping Using Neighborhood Edge Dissimilarities in Very High-Resolution Optical Satellite Imagery—Application to the 2003 Bam, Iran, Earthquake , 2005 .

[31]  M. Turker,et al.  Automatic detection of earthquake‐damaged buildings using DEMs created from pre‐ and post‐earthquake stereo aerial photographs , 2005 .

[32]  Jingyuan Yin,et al.  Automatic recognition of damaged town buildings caused by earthquake using remote sensing information: Taking the 2001 Bhuj, India, earthquake and the 1976 Tangshan, China, earthquake as examples , 2004 .

[33]  Vladimir Estivill-Castro,et al.  Why so many clustering algorithms: a position paper , 2002, SKDD.

[34]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[35]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Monika Sester,et al.  Photogrammetry and geographic information systems for quick assessment, documentation and analysis of earthquakes , 2001 .

[37]  Jing Xiao,et al.  Fusion of airborne laserscanning point clouds and images for supervised and unsupervised scene classification , 2014 .

[38]  N. Haala.  The Landscape of Dense Image Matching Algorithms , 2013 .

[39]  A. J. Clark,et al.  Collaborative Geospatial Data as Applied to Disaster Relief: Haiti 2010 , 2010, FGIT-SecTech/DRBC.

[40]  T. Chou,et al.  DISASTER MONITORING AND MANAGEMENT BY THE UNMANNED AERIAL VEHICLE TECHNOLOGY , 2010 .

[41]  M. Rehor,et al.  Improvement of building damage detection and classification based on laser scanning data by integrating spectral information , 2008 .

[42]  F. Samadzadegan,et al.  AUTOMATIC DETECTION AND CLASSIFICATION OF DAMAGED BUILDINGS , USING HIGH RESOLUTION SATELLITE IMAGERY AND VECTOR DATA , 2008 .

[43]  M. Rehor,et al.  Classification of building damages based on laser scanning data , 2007 .

[44]  Armin Gruen,et al.  Automatic Classification of Collapsed Buildings Using Object and Image Space Features , 2007 .

[45]  M. Pierrot-Deseilligny,et al.  A MULTIRESOLUTION AND OPTIMIZATION-BASED IMAGE MATCHING APPROACH : AN APPLICATION TO SURFACE RECONSTRUCTION FROM SPOT 5-HRS STEREO IMAGERY , 2006 .

[46]  M. Turker,et al.  DETECTION OF THE EARTHQUAKE DAMAGED BUILDINGS FROM POST-EVENT AERIAL PHOTOGRAPHS USING PERCEPTUAL GROUPING , 2004 .

[47]  L. Gusella,et al.  IMAGE CHANGE DETECTION ON URBAN AREA : THE EARTHQUAKE CASE , 2004 .

[48]  Stan Z. Li,et al.  Markov Random Field Modeling in Image Analysis , 2001, Computer Science Workbench.