Natural Disaster Classification using Aerial Photography Explainable for Typhoon Damaged Feature
This addresses the need for immediate response and decision support in disaster recovery for affected regions, though it is incremental as it applies existing techniques like Grad-CAM to a specific domain.
The paper tackles the problem of rapid damage assessment after typhoons by proposing a method to classify and visualize damaged areas from aerial photography, specifically demonstrating it on Typhoon Faxai data with eight classes including undamaged land covers and disaster features.
Recent years, typhoon damages has become social problem owing to climate change. In 9 September 2019, Typhoon Faxai passed on the Chiba in Japan, whose damages included with electric provision stop because of strong wind recorded on the maximum 45 meter per second. A large amount of tree fell down, and the neighbor electric poles also fell down at the same time. These disaster features have caused that it took 18 days for recovery longer than past ones. Immediate responses are important for faster recovery. As long as we can, aerial survey for global screening of devastated region would be required for decision support to respond where to recover ahead. This paper proposes a practical method to visualize the damaged areas focused on the typhoon disaster features using aerial photography. This method can classify eight classes which contains land covers without damages and areas with disaster. Using target feature class probabilities, we can visualize disaster feature map to scale a color range. Furthermore, we can realize explainable map on each unit grid images to compute the convolutional activation map using Grad-CAM. We demonstrate case studies applied to aerial photographs recorded at the Chiba region after typhoon.