Multi-Scale and Context-Aware Framework for Flood Segmentation in Post-Disaster High Resolution Aerial Images

Abstract

Floods are the most frequent natural disasters, occurring almost every year around the globe. To mitigate the damage caused by a flood, it is important to timely assess the magnitude of the damage and efficiently conduct rescue operations, deploy security personnel and allocate resources to the affected areas. To efficiently respond to the natural disaster, it is very crucial to swiftly obtain accurate information, which is hard to obtain during a post-flood crisis. Generally, high resolution satellite images are predominantly used to obtain post-disaster information. Recently, deep learning models have achieved superior performance in extracting high-level semantic information from satellite images. However, due to the loss of multi-scale and global contextual features, existing deep learning models still face challenges in extracting complete and uninterrupted results. In this work, we proposed a novel deep learning semantic segmentation model that reduces the loss of multi-scale features and enhances global context awareness. Generally, the proposed framework consists of three modules, encoder, decoder and bridge, combined in a popular U-shaped scheme. The encoder and decoder modules of the framework introduce Res-inception units to obtain reliable multi-scale features and employ a bridge module (between the encoder and decoder) to capture global context. To demonstrate the effectiveness of the proposed framework, we perform an evaluation using a publicly available challenging dataset, FloodNet. Furthermore, we compare the performance of the proposed framework with other reference methods. We compare the proposed framework with recent reference models. Quantitative and qualitative results show that the proposed framework outperforms other reference models by an obvious margin.