Proceedings Article | 20 September 2020
Marc Bosch, Christian Conroy, Benjamin Ortiz, Philip Bogden
KEYWORDS: Floods, Image segmentation, Image analysis, Machine vision, Computer vision technology, Natural disasters, Image processing
We have developed a framework for crisis response and management that incorporates the latest technologies in computer vision (CV), inland flood prediction, damage assessment and data visualization. The framework uses data collected before, during, and after the crisis to enable rapid and informed decision making during all phases of disaster response. Our computer-vision model analyzes spaceborne and airborne imagery to detect relevant features during and after a natural disaster and creates metadata that is transformed into actionable information through web-accessible mapping tools. In particular, we have designed an ensemble of models to identify features including water, roads, buildings, and vegetation from the imagery. We have investigated techniques to bootstrap and reduce dependency on large data annotation efforts by adding use of open source labels including OpenStreetMaps and adding complementary data sources including Height Above Nearest Drainage (HAND) as a side channel to the network's input to encourage it to learn other features orthogonal to visual characteristics. Modeling efforts include modification of connected U-Nets for (1) semantic segmentation, (2) flood line detection, and (3) for damage assessment. In particular for the case of damage assessment, we added a second encoder to U-Net so that it could learn pre-event and post-event image features simultaneously. Through this method, the network is able to learn the difference between the pre- and post-disaster images, and therefore more effectively classify the level of damage. We have validated our approaches using publicly available data from the National Oceanic and Atmospheric Administration (NOAA)'s Remote Sensing Division, which displays the city and street-level details as mosaic tile images as well as data released as part of the Xview2 challenge. In addition, we have integrated the CV-generated artifacts and results in a collection of analytic tools including routing, damage assessment, and response prioritization, to assist with response management and strategic decision. The routing tool allows users to plan optimal alternate routes given automatically detected flood lines from the latest imagery. Response prioritization estimators look for critical areas, e.g., homes surrounded by water, flooded roads, and other anomalies detected in the impacted area. Finally, the damage assessment tool includes a pixel-based financial model capable of outputting estimated financial damage costs projected according to the United States National Grid (USNG) coordinate system. In conclusion, we are working towards an emergency response system that provides stakeholders timely access to comprehensive, relevant, and reliable information. The faster emergency personnel are able to analyze, disseminate, and act on key information, the more effective and timelier their response will be and the greater the benefit to affected populations.
