Attention Based Semantic Segmentation on UAV Dataset for Natural Disaster Damage Assessment

The detrimental impacts of climate change include stronger and more destructive hurricanes happening all over the world. Identifying different damaged structures of an area including buildings and roads are vital since it helps the rescue team to plan their efforts to minimize the damage caused by a natural disaster. Semantic segmentation helps to identify different parts of an image. We implement a novel self-attention based semantic segmentation model on a high resolution UAV dataset and attain Mean IoU score of around 88% on the test set. The result inspires to use self-attention schemes in natural disaster damage assessment which will save human lives and reduce economic losses.

1. Introduction

In recent time, the world has seen numerous natural disasters which have brought both personal injury and economic loss to several countries all over the world. A major step to both save valuable human lives and reduce financial loss is an accurate assessment of the damage inflicted by these events. A correct estimation of the damage helps to plan efficiently and allows the rescue team to allocate their efforts and aid properly.