基于CNN和Efficient Transformer的多尺度遥感图像语义分割算法  

Semantic segmentation algorithm for multiscale remote sensing images based on CNN and Efficient Transformer

作　　者：张振利 胡新凯[1,2] 李凡 冯志成 陈智超 ZHANG Zhenli;HU Xinkai;LI Fan;FENG Zhicheng;CHEN Zhichao(School of Electrical Engineering and Automation,Jiangxi University of Science and Technology,Ganzhou 341000,China;Jiangxi Province Key Laboratory of Maglev Rail Transit Equipment,Jiangxi University of Science and Technology,Ganzhou 341000,China)

机构地区：[1]江西理工大学电气工程与自动化学院,江西赣州341000 [2]江西理工大学磁浮轨道交通装备江西省重点实验室,江西赣州341000

出　　处：《浙江大学学报(工学版)》2025年第4期778-786,共9页Journal of Zhejiang University:Engineering Science

基　　金：国家自然科学基金资助项目(62063009);国家重点研发计划项目(2023YFB4302100).

摘　　要：针对现有方法存在遥感图像的多尺度地物特征提取困难和目标边缘分割不准确的问题,提出新的语义分割算法.利用CNN和Efficient Transformer构建双编码器,解耦上下文信息和空间信息.提出特征融合模块加强编码器间的信息交互,有效融合全局上下文信息和局部细节信息.构建分层Transformer结构提取不同尺度的特征信息,使编码器有效专注不同尺度的物体.提出边缘细化损失函数,缓解遥感图像目标边缘分割不准确的问题.实验结果表明,在ISPRS Vaihingen和ISPRS Potsdam数据集上,所提算法的平均交并比(MIoU)分别为72.45%和82.29%.在SAMRS数据集中的SOTA、SIOR和FAST子集上,所提算法的MIoU分别为88.81%、97.29%和86.65%,总体精度和平均交并比指标均优于对比模型.所提算法在各类不同尺度的目标上有较好的分割性能.Aiming at the problems of the existing methods,such as the difficulty of multi-scale feature extraction and the inaccuracy of target edge segmentation in remote sensing images,a new semantic segmentation algorithm was proposed.CNN and Efficient Transformer were utilized to construct a dual encoder to decouple context and spatial information.A feature fusion module was proposed to enhance the information interaction between the encoders,effectively fusing the global context and local detail information.A hierarchical Transformer structure was constructed to extract feature information at different scales,allowing the encoder to focus effectively on objects at different scales.An edge thinning loss function was proposed to mitigate the problem of inaccurate target edge segmentation.Experimental results showed that mean intersection over union(MIoU)of 72.45%and 82.29%was achieved by the proposed algorithm on the ISPRS Vaihingen and ISPRS Potsdam datasets,respectively.On the SOTA,SIOR,and FAST subsets of the SAMRS dataset,the MIoU of the proposed algorithm was 88.81%,97.29%,and 86.65%,respectively,overall accuracy and mean intersection over union metrics were better than those of the comparison models.The proposed algorithm has good segmentation performance on various types of targets with different scales.

关 键 词：遥感图像 语义分割 双编码器结构 特征融合 Efficient Transformer 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置] U212[自动化与计算机技术—控制科学与工程]