Attentive Dual Stream Siamese U-net for Flood Detection on Multi-temporal Sentinel-1 Data

TL;DR

This paper introduces an attentive dual-stream Siamese U-net that leverages bi-temporal Sentinel-1 SAR data for improved flood detection accuracy, outperforming existing uni-temporal methods on benchmark datasets.

Contribution

The paper presents a novel dual-stream Siamese U-net architecture with attention mechanisms for bi-temporal flood detection, demonstrating superior performance over state-of-the-art uni-temporal approaches.

Findings

Outperforms existing methods by 6% IOU on benchmark dataset

Effective fusion of pre- and post-flood images improves detection accuracy

Attention blocks enhance feature map quality for better segmentation

Abstract

Due to climate and land-use change, natural disasters such as flooding have been increasing in recent years. Timely and reliable flood detection and mapping can help emergency response and disaster management. In this work, we propose a flood detection network using bi-temporal SAR acquisitions. The proposed segmentation network has an encoder-decoder architecture with two Siamese encoders for pre and post-flood images. The network's feature maps are fused and enhanced using attention blocks to achieve more accurate detection of the flooded areas. Our proposed network is evaluated on publicly available Sen1Flood11 benchmark dataset. The network outperformed the existing state-of-the-art (uni-temporal) flood detection method by 6\% IOU. The experiments highlight that the combination of bi-temporal SAR data with an effective network architecture achieves more accurate flood detection than uni-temporal methods.