计算技术与自动化2025，Vol.44Issue(3)：88-93,6.DOI:10.16339/j.cnki.jsjsyzdh.202503016
基于多尺度特征融合的遥感图像水体分割
Remote Sensing Image Water Body Segmentation Based on Multi-scale Feature Fusion
摘要
Abstract
Water area semantic segmentation plays a crucial role in remote sensing and earth observation.Existing meth-ods can hardly effectively segment small boundaries of multi-scale water areas in complex scenarios,and face the challenge of high annotation data costs.Consequently,a multi-scale fusion based water area segmentation method for remote sensing im-ages is proposed.The proposed water segmentation network is designed based on dual attention modules and transformed at-tention modules.A multi-scale feature fusion module is introduced to reduce the semantic gap between different scale fea-tures in the encoder and decoder.Prior to model training,the encoder is pre-trained with mask-reconstruction based self-su-pervised learning to obtain initial weights with rich feature representations.Experimental evaluation was conducted on the FloodNet dataset.The proposed method achieved the highest mIoU of 89.77％,which is a 1.31％improvement compared to the state-of-the-art semantic segmentation algorithm DAE-Former.The experimental results demonstrate the accuracy of the proposed method.关键词
多尺度特征融合/注意力/语义分割/遥感图像Key words
multi-scale feature fusion/attention/semantic segmentation/remote sensing images分类
信息技术与安全科学引用本文复制引用
李益..基于多尺度特征融合的遥感图像水体分割[J].计算技术与自动化,2025,44(3):88-93,6.
