摘要
针对高分辨率遥感影像建筑物语义分割中存在单体建筑部分漏分与纹理相近的非建筑物错分的问题,提出深度特征提取与多输出增强建筑物语义分割网络。首先,在编码与解码交替处设计并行连续空洞空间注意力金字塔模块,对建筑物高维特征实现深层提取;然后,在网络解码阶段设计多输出增强融合模块,提升不同尺度建筑物特征对输出结果的有效参与度。选取U-Net、DeeplabV3+、MA-FCN、BRRNet同类算法进行对比,在Massachusetts和WHU公共数据集上测试,OA、precision、recall、IoU、F1指标分别达到98.87%、94.53%、95.40%、90.41%、94.96%,与同类算法相比,除precision之外其他4项指标更高,与U-Net相比,依次高出0.25%、1.12%、1.14%、2.02%、1.12%。
This paper proposes a deep feature extraction and multi output enhanced building semantic segmentation network to address the problem of missing individual building parts and similar texture non building misclassification in high-resolution remote sensing image building semantic segmentation.Firstly,a parallel continuous void spatial attention pyramid module is designed at the alternation of encoding and decoding to achieve deep extraction of high-dimensional features of buildings.Then,in the network decoding stage,a multi-output enhanced fusion module is designed to improve the effective participation of building features at different scales in the output results.Selecting the similar algorithms of U-Net,DeeplabV3+,MA-FCN and BRRNet for comparison and testing on the public datasets of Massachusetts and WHU,the OA,precision,recall,F1 and IoU indicators can reach 98.87%,94.53%,95.40%,90.41%,and 94.96%,respectively.OA,F1,recall and IoU accuracy are higher than that of the other four indicators.The OA,precision,recall,IoU and F1 of the proposed method are higher than that of U-Net by 0.25%,1.12%,1.14%,2.02%,and 1.12%,respectively.
作者
田保慧
胡颖雷
刘晓旭
刘用
杨元维
TIAN Baohui;HU Yinglei;LIU Xiaoxu;LIU Yong;YANG Yuanwei(Henan College of Transportation,Zhengzhou 451460,China;Transportation Development Center of Henan Province,Zhengzhou 450000,China;Guojiao Spatial Information Technology(Beijing)Co.Ltd.,Beijing 101300,China;School of Geosciences,Yangtze University,Wuhan 430100,China)
出处
《遥感信息》
CSCD
北大核心
2024年第1期35-42,共8页
Remote Sensing Information
基金
城市轨道交通数字化建设与测评技术国家工程实验室开放课题基金(2023ZH01)
湖南科技大学测绘遥感信息工程湖南省重点实验室开放基金(E22205)
自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室开放基金(MEMI-2021-2022-08)。
关键词
建筑物提取
注意力机制
多输出融合
深层特征
空洞卷积
building extraction
attention mechanism
multi output fusion
deep feature
Atrous convolution