Improved Semantic Segmentation for Identification of Flooded Regions in UAV Aerial Images: A Transformer-Based Approach

The Earth Observation data provides an effective tool to assess post-disaster damage for better relief and rescue efforts management. However, the longer satellite revisit time might delay the rescue efforts. In contrast, Unmanned Aerial Vehicles (UAV) can be rapidly deployed with a customized flight plan. This work focuses on analyzing images from UAV to identify flooded regions. Specifically, a Transformer based semantic segmentation method is proposed for flooded region identification. The proposed encoder-decoder model integrates the features of UNet (ResNet18 backbone) with that of Vision in Transformer (ViT). These fused features are fed to a decoder module to obtain the final segmentation map. The proposed work is evaluated on the FloodNet dataset containing post-disaster UAV images after Hurricane Harvey. A mIoU of 86.84% is obtained using the proposed approach compared to a mIoU of 74.95% using the traditional UNet model. The significant improvement in mIoU demonstrates the robustness of ViT in learning discriminant features for post-disaster scene understanding.