摘要
高分辨率遥感图像建筑物分割是遥感影像研究的热点之一,而高分辨率遥感图像中建筑物尺度多样容易导致错分割、漏分割和边界模糊。针对上述问题,基于U-Net网络结构提出了一种双路径编码的遥感建筑物图像分割网络(DCU-Net)。DCU-Net在U-Net上加入一条并行编码路径,形成双路径编码结构。在编码阶段设计了密集残差编码模块(DRCM)和多尺度空洞卷积编码模块(MDCCM)以增强多尺度特征提取。在网络中加入双路融合注意力模块(DFAM),增强网络对特征的表达能力。为验证网络有效性,在WHU与Massachusetts数据集上进行实验,召回率、F1分数和交并比指标在WHU上达到91.26%、92.33%和86.15%,在Massachusetts Buildings上达到81.64%、84.33%和82.72%。结果表明,DCU-Net对于不同尺度的建筑物提取有较高的提取精度。
Building segmentation in high resolution remote sensing images is one of the hotspots in remote sensing image research.The diversity of building scales in high-resolution remote sensing images easily leads to wrong seg-mentation,missing segmentation and fuzzy boundaries.In order to solve the above problems,this paper proposes a remote sensing building image segmentation network based on U-Net network structure with double coder U-shaped network(DCU-Net).DCU-Net adds a parallel coding path to U-Net to form a dual-path coding structure.Dense residual coding module(DRCM)and multi-scale dilated convolutional coding module(MDCCM)are de-signed in the encoding stage to enhance multi-scale feature extraction.The dual hybrid attention module(DFAM)is added to the network to enhance the expression ability of the network for features.In order to verify the effective-ness of the network,experiments are carried out on WHU and Massachusetts datasets.The recall,F1 and intersec-tion over union ratio indicators reach 91.26%,92.33%and 86.15%on WHU dataset,and reach 81.64%,84.33%and 82.72%on Massachusetts Buildings dataset.The results show that DCU-Net has high extraction accuracy for building extraction at different scales.
作者
苏赋
李沁
马傲
SU Fu;LI Qin;MA Ao(School of Electrical Engineering and Information,Southwest Petroleum University,Chengdu 610500,China)
出处
《计算机科学与探索》
CSCD
北大核心
2024年第10期2704-2711,共8页
Journal of Frontiers of Computer Science and Technology
基金
成都市国际科技合作资助项目(2020-GH02-00016-HZ)。
关键词
遥感影像
建筑物分割
双路径编码
注意力机制
多尺度特征
remote sensing image
building segmentation
dual-path coding
attention mechanism
multi-scale feature
作者简介
通信作者:李沁(1999-),男,四川成都人,硕士研究生,主要研究方向为计算机视觉、深度学习、遥感图像处理等。E-mail:1076908138@qq.com;苏赋(1973-),女,湖南长沙人,博士,副教授,主要研究方向为信号与信息处理等。;马傲(1999-),男,四川德阳人,硕士研究生,主要研究方向为深度学习、医学图像处理等。
