Detecting Natural Disasters, Damage, and Incidents in the Wild
Name
2008.09188.pdf
Description
Accepted version
Size
16.53 MB
Format
Adobe PDF
Checksum (MD5)
c010b42da5828f90ee2bcfd297f69b3c
Author(s)
Weber, Ethan
Marzo, Nuria
Papadopoulos, Dim P
Biswas, Aritro
Lapedriza Garcia, Agata
Ofli, Ferda
Imran, Muhammad
Torralba, Antonio
Date Issued
November 2020
Journal
Lecture Notes in Computer Science
Publisher
Springer International Publishing
Citation
Weber, Ethan et al. "Detecting Natural Disasters, Damage, and Incidents in the Wild." ECCV: European Conference on Computer Vision, Lecture Notes in Computer Science, 12364, Springer International Publishing, 2020, 331-350. © 2020 Springer Nature
Version
Author's final manuscript
Abstract
Responding to natural disasters, such as earthquakes, floods, and wildfires, is a laborious task performed by on-the-ground emergency responders and analysts. Social media has emerged as a low-latency data source to quickly understand disaster situations. While most studies on social media are limited to text, images offer more information for understanding disaster and incident scenes. However, no large-scale image datasets for incident detection exists. In this work, we present the Incidents Dataset, which contains 446,684 images annotated by humans that cover 43 incidents across a variety of scenes. We employ a baseline classification model that mitigates false-positive errors and we perform image filtering experiments on millions of social media images from Flickr and Twitter. Through these experiments, we show how the Incidents Dataset can be used to detect images with incidents in the wild. Code, data, and models are available online at http://incidentsdataset.csail.mit.edu.
Description
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12364)
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-58529-7_20
