基于改进的U-Net卷积神经网络的遥感影像水体信息提取方法
Water body information extraction method for remote sensing images based on improved U-Net convolutional neural network
宋子俊 1董张玉 2张鹏飞 1张远南1
作者信息
- 1. 合肥工业大学 计算机与信息学院,安徽 合肥 230601;工业安全与应急技术安徽省重点实验室,安徽 合肥 230601
- 2. 合肥工业大学 计算机与信息学院,安徽 合肥 230601;工业安全与应急技术安徽省重点实验室,安徽 合肥 230601;合肥工业大学 智能互联系统安徽省实验室,安徽 合肥 230601
- 折叠
摘要
针对当前遥感影像水体信息提取存在细节水体提取能力较弱、重要特征损失较大的问题,文章提出一种基于改进的U-Net网络实现遥感影像水体信息提取的方法.该方法首先通过引入Resnet残差卷积模块深化传统U-Net网络架构提升特征挖掘能力,并引入Respath残差连接模块减少跳跃连接过程中的语义差距,同时引入PSConv多尺度卷积模块、Eca有效通道注意力机制模块,提高网络特征学习能力,构建 PS-Eca-M ultiresunet网络模型,弥补传统U-Net网络存在的细节特征提取能力较弱问题.选择"2020 年第四届中科星图杯高分遥感图像解译软件大赛"数据集进行实验,结果表明,与传统U-Net网络模型相比,该方法水体提取的平均交并比提高了9.08,像素精度提升了 7.4%.改进的网络提取结果能够有效避免阴影影响,提高对细节水体的提取精度,实现遥感影像水体信息的高精度提取.
Abstract
Aiming at the problems of weak ability to extract detailed water bodies and large loss of im-portant features in current water body information extraction from remote sensing images,this paper proposes a method to extract water body information from remote sensing images using an improved U-Net network.The method firstly deepens the traditional U-Net network architecture by introducing the Resnet residual convolution module to improve the feature mining ability,and introduces the Res-path residual connection module to reduce the semantic gap in the skip connection process,while in-troducing the PSConv multi-scale convolution module and Eca effective channel attention mechanism module to improve the network feature learning ability,and constructs the PS-Eca-Multiresunet net-work model to compensate for the shallow feature loss problem that exists in general networks.The dataset of 2020 GEOVIS Cup Gaofen Challenge on Automated High-Resolution Earth Observation Im-age Interpretation is selected for the experiment.The results show that the average intersection ratio of water extraction by this method is 9.08 higher than that of the traditional U-Net network model,and the precision of image elements is 7.4%higher than that of the traditional U-Net network model.The improved network extraction results can effectively avoid the influence of shadows,improve the extraction accuracy of detailed water bodies,and achieve high-precision extraction of water body infor-mation from remote sensing images.
关键词
水体提取/深度学习/多尺度卷积/有效通道注意力机制/Multiresunet网络Key words
water body extraction/deep learning/multi-scale convolution/effective channel attention mechanism/Multiresunet network引用本文复制引用
基金项目
安徽省重点研究与开发计划资助项目(202004a07020030)
安徽省自然科学基金资助项目(2108085MF233)
中央高校基本科研业务费专项资金资助项目(JZ2021HGTB0111)
出版年
2024
NETL
NSTL
万方数据