QTU-Net: Quaternion Transformer-Based U-Net for Water Body Extraction of RGB Satellite Image

Mingzhi Wang, Chunshan Li, Xiaofei Yang, Dianhui Chu, Zhiquan Zhou, Raymond Y. K. Lau

Abstract: Deep learning models have achieved great success in water body extraction (WBE) from remote sensing images. However, the existing deep learning-based extraction methods exhibit limitations in their ability to fully explore the intricate interconnections inherent in RGB color satellite imagery and to enhance semantic representation across diverse regions. Furthermore, these methods often struggle with challenges posed by the uneven distribution of water bodies at different scales within the image, as well as substantial color disparities between water and land areas. In this article, we tackle WBE task from quaternion domain and introduce a novel approach called quaternion transformer-based U-Net (QTU-Net) to address these challenges. Our method specifically leverages quaternion convolution operations to capture the holistic relationships among RGB channels, thereby enhancing the semantic representation of WBE. Additionally, we propose a quaternion initialization module (QIM) to determine optimal RGB weights and facilitate the generation of quaternion data. To further improve the accuracy of water body delineation, we incorporate an innovative multiscale similarity aggregation attention (MSAA) component that enhances local similarity capture across various scales. Finally, we evaluate the proposed QTU-Net based on three publicly available benchmark datasets. The experimental results demonstrate that the proposed QTU-Net outperforms state-of-the-art baseline methods.