Detecting natural disasters, damage, and incidents in the wild
This work addresses the need for large-scale image datasets to improve disaster response by leveraging social media, though it is incremental as it builds on existing text-based methods by introducing image data.
The authors tackled the problem of detecting natural disasters and incidents from images by creating the Incidents Dataset with 446,684 human-annotated images covering 43 incidents, and demonstrated its use in filtering social media images from Flickr and Twitter to detect incidents in the wild.
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.