xBD: A Dataset for Assessing Building Damage from Satellite Imagery

We present a preliminary report for xBD, a new large-scale dataset for the advancement of change detection and building damage assessment for humanitarian assistance and disaster recovery research.Logistics, resource planning, and damage estimation are difficult tasks after a disaster, and putting first responders into post-disaster situations is dangerous and costly.Using passive methods, such as analysis on satellite imagery, to perform damage assessment saves manpower, lowers risk, and expedites an otherwise dangerous process.xBD provides pre- and post-event multi-band satellite imagery from a variety of disaster events with building polygons, classification labels for damage types, ordinal labels of damage level, and corresponding satellite metadata.Furthermore, the dataset contains bounding boxes and labels for environmental factors such as fire, water, and smoke.xBD will be the largest building damage assessment dataset to date, containing $\sim$700,000 building annotations across over 5,000 km\textsuperscript{2} of imagery from 15 countries.

[1]  Gordon Christie,et al.  Functional Map of the World , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Kah Kay Sung,et al.  Learning and example selection for object and pattern detection , 1995 .

[3]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[4]  M. Matsuoka,et al.  DAMAGE DETECTION FROM HIGH-RESOLUTION SATELLITE IMAGES FOR THE 2003 BOUMERDES , ALGERIA EARTHQUAKE , 2002 .

[5]  M. V. van Aalst The impacts of climate change on the risk of natural disasters. , 2006, Disasters.

[6]  Seyed Majid Azimi,et al.  Road Segmentation in SAR Satellite Images With Deep Fully Convolutional Neural Networks , 2018, IEEE Geoscience and Remote Sensing Letters.

[7]  Marc Bosch,et al.  A multiple view stereo benchmark for satellite imagery , 2016, 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[8]  Alexandre Boulch,et al.  Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[9]  Deren Li,et al.  Cloud Detection for High-Resolution Satellite Imagery Using Machine Learning and Multi-Feature Fusion , 2016, Remote. Sens..

[10]  J. Randerson,et al.  Analysis of daily, monthly, and annual burned area using the fourth‐generation global fire emissions database (GFED4) , 2013 .

[11]  Alexey Shvets,et al.  Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  Taher M. Bazan,et al.  Smear effect on high-resolution remote sensing satellite image quality , 2018, 2018 IEEE Aerospace Conference.

[13]  Carol J. Friedland,et al.  Residential building damage from hurricane storm surge: proposed methodologies to describe, assess and model building damage , 2009 .

[14]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[15]  Martin J. Alperen The Federal Emergency Management Agency , 2011 .

[16]  Yaroslav Bulatov,et al.  xView: Objects in Context in Overhead Imagery , 2018, ArXiv.

[17]  B. Merz,et al.  METHODS FOR THE EVALUATION OF DIRECT AND INDIRECT FLOOD LOSSES , 2008 .

[18]  F. Dell’acqua,et al.  Post-event Only VHR Radar Satellite Data for Automated Damage Assessment , 2011 .

[19]  O. R. Mitchell,et al.  Filtering to remove cloud cover in satellite imagery , 1977, IEEE Transactions on Geoscience Electronics.

[20]  Manfred F. Buchroithner,et al.  Identifying Collapsed Buildings Using Post-Earthquake Satellite Imagery and Convolutional Neural Networks: A Case Study of the 2010 Haiti Earthquake , 2018, Remote. Sens..

[21]  L. Chiroiu,et al.  DAMAGE ASSESSMENT USING HIGH RESOLUTION SATELLITE IMAGERY: APPLICATION TO 2001 BHUJ, INDIA, EARTHQUAKE , 2001 .

[22]  Youngjun Choe,et al.  Benchmark Dataset for Automatic Damaged Building Detection from Post-Hurricane Remotely Sensed Imagery , 2018, ArXiv.

[23]  Ryosuke Nakamura,et al.  Damage detection from aerial images via convolutional neural networks , 2017, 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA).

[24]  Feng Wu,et al.  Remote sensing imaging simulation and cloud removal , 2017 .

[25]  Abhinav Gupta,et al.  Training Region-Based Object Detectors with Online Hard Example Mining , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Ilan Kelman,et al.  Physical Flood Vulnerability of Residential Properties in Coastal , Eastern England Extended , 2003 .

[27]  G. D'Arboussier,et al.  United Nations Institute for Training and Research , 1967 .

[28]  Shigeyuki Okada,et al.  CLASSIFICATIONS OF STRUCTURAL TYPES AND DAMAGE PATTERNS OF BUILDINGS FOR EARTHQUAKE FIELD INVESTIGATION , 1999 .

[29]  Jing Huang,et al.  DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[30]  Geoffrey E. Hinton,et al.  Learning to Detect Roads in High-Resolution Aerial Images , 2010, ECCV.