Balancing Accuracy and Efficiency: HWBENet for Water Body Extraction in Complex Rural Landscapes

The accurate and timely extraction of water bodies from high-resolution remote sensing imagery is vital for environmental monitoring, yet segmenting small, scattered, and irregularly shaped water bodies in complex rural landscapes remains a persistent challenge. While state-of-the-art deep learning models have advanced segmentation accuracy, they often achieve this at the cost of substantial computational overhead, limiting their practical application for large-scale monitoring. To address this trade-off between precision and efficiency, this paper introduces HWBENet, a novel hybrid network for water body extraction. HWBENet is built upon a lightweight MobileNetV3 encoder to ensure computational efficiency while preserving strong feature extraction capabilities. Its core innovation lies in two specifically designed modules. First, the Contextual Information Mining Module (CIMM) is proposed to enhance the network’s ability to learn and fuse both global scene-level context and fine-grained local details, which is crucial for identifying fragmented water bodies. Second, an Edge Refinement Module (ERM) is integrated into the decoder, which uniquely leverages transformer mechanisms to sharpen boundary details by effectively fusing prior feature information with up-sampled features. Extensive experiments on challenging rural water body datasets demonstrate that HWBENet strikes a superior balance between accuracy and computational cost. The experimental results validate the finding that HWBENet is an efficient, accurate, and scalable solution, offering significant practical value for large-scale hydrological mapping in complex rural environments.