Next Article in Journal
Radiometric and Atmospheric Corrections of Multispectral μMCA Camera for UAV Spectroscopy
Next Article in Special Issue
Evaluating Resilience-Centered Development Interventions with Remote Sensing
Previous Article in Journal
Morphological Characteristics of Tidal Creeks in the Central Coastal Region of Jiangsu, China, Using LiDAR
Previous Article in Special Issue
Earthquake-Induced Landslide Mapping for the 2018 Hokkaido Eastern Iburi Earthquake Using PALSAR-2 Data
Open AccessArticle

Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data

1
Department of Earth Systems Analysis (ESA), Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7500 AE Enschede, The Netherlands
2
Department of Agricultural Sciences, University of Naples Federico II, Via Universita 100, 80055 Portici, Naples, Italy
3
Geoinformatics Research Group, Department of Planning and Development, Aalborg University Copenhagen, A.C. Meyers Vænge 15, DK-2450 Copenhagen, Denmark
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(20), 2427; https://doi.org/10.3390/rs11202427
Received: 8 July 2019 / Revised: 11 October 2019 / Accepted: 18 October 2019 / Published: 19 October 2019
First responders and recovery planners need accurate and quickly derived information about the status of buildings as well as newly built ones to both help victims and to make decisions for reconstruction processes after a disaster. Deep learning and, in particular, convolutional neural network (CNN)-based approaches have recently become state-of-the-art methods to extract information from remote sensing images, in particular for image-based structural damage assessment. However, they are predominantly based on manually extracted training samples. In the present study, we use pre-disaster OpenStreetMap building data to automatically generate training samples to train the proposed deep learning approach after the co-registration of the map and the satellite images. The proposed deep learning framework is based on the U-net design with residual connections, which has been shown to be an effective method to increase the efficiency of CNN-based models. The ResUnet is followed by a Conditional Random Field (CRF) implementation to further refine the results. Experimental analysis was carried out on selected very high resolution (VHR) satellite images representing various scenarios after the 2013 Super Typhoon Haiyan in both the damage and the recovery phases in Tacloban, the Philippines. The results show the robustness of the proposed ResUnet-CRF framework in updating the building map after a disaster for both damage and recovery situations by producing an overall F1-score of 84.2%. View Full-Text
Keywords: post-disaster; building database update; damage assessment; recovery assessment; OpenStreetMap; deep learning; convolutional neural network; multi-temporal satellite imagery; U-Net; Super Typhoon Haiyan post-disaster; building database update; damage assessment; recovery assessment; OpenStreetMap; deep learning; convolutional neural network; multi-temporal satellite imagery; U-Net; Super Typhoon Haiyan
Show Figures

Graphical abstract

MDPI and ACS Style

Ghaffarian, S.; Kerle, N.; Pasolli, E.; Jokar Arsanjani, J. Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data. Remote Sens. 2019, 11, 2427.

AMA Style

Ghaffarian S, Kerle N, Pasolli E, Jokar Arsanjani J. Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data. Remote Sensing. 2019; 11(20):2427.

Chicago/Turabian Style

Ghaffarian, Saman; Kerle, Norman; Pasolli, Edoardo; Jokar Arsanjani, Jamal. 2019. "Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data" Remote Sens. 11, no. 20: 2427.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop