卢彻,徐胜华,朱军

• 1:西南交通大学地球科学与环境工程学院
• 2:中国测绘科学研究院

摘要(Abstract)：

针对高分辨率遥感影像中普遍存在的同谱异物和同物异谱现象以及传统全卷积神经网络随网络层数增加导致的梯度消失等问题,该文提出了基于改进U-Net的高分辨率遥感影像建筑物提取方法。利用残差思想对U-Net网络结构进行优化,采用Adam优化器进行参数的更新,同时引入Dropout与批标准化,改进U-Net可以有效防止模型的过拟合现象,从而提高模型的泛化能力。实验结果表明,该文提出的改进U-Net对影像中的建筑物提取结果较好,在测试集上达到了94%以上的正确率,召回率达到79%,精确率达到78%,Kappa系数达到95%,相比U-Net分别提高了2%、2%、16%以及4%,实现了对城市区域遥感影像中的建筑物精确、快速提取。

关键词(KeyWords)： 高分辨率遥感影像;U-Net模型;残差学习;建筑物提取;深度学习

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划项目(2016YFC0803100)

作者(Author): 卢彻,徐胜华,朱军

DOI: 10.16251/j.cnki.1009-2307.2021.12.019

参考文献(References)：

• [1] 安文，杨俊峰，赵羲，等.高分辨率遥感影像的建筑物自动提取[J].测绘科学，2014,39(11):80-84.(AN Wen,YANG Junfeng,ZHAO Xi,et al.Buildings automatic extraction from high resolution RS images[J].Science of Surveying and Mapping,2014,39(11):80-84.)
• [2] DONG Yanni,DU Bo,ZHANG Liangpei.Target detection based on random forest metric learning[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(4):1830-1838.
• [3] 王旭东，段福洲，屈新原，等.面向对象和SVM结合的无人机数据建筑物提取[J].国土资源遥感，2017,29(1):97-103.(WANG Xudong,DUAN Fuzhou,QU Xinyuan,et al.Building extraction based on UAV imagery data with the synergistic use of objected-based method and SVM classifier[J].Remote Sensing for Land & Resources,2017,29(1):97-103.)
• [4] 周建伟，吴一全.MRELBP特征、Franklin矩和SVM相结合的遥感图像建筑物识别方法[J].测绘学报，2020,49(3):355-364.(ZHOU Jianwei,WU Yiquan.Building area recognition method of remote sensing image based on MRELBP feature,Franklin moment and SVM[J].Acta Geodaetica et Cartographica Sinica,2020,49(3):355-364.)
• [5] 任晓娟，肖双九，彭小朋.基于改进分水岭变换的遥感图像建筑物提取[J].计算机应用与软件，2011,28(12):249-252.(REN Xiaojuan,XIAO Shuangjiu,PENG Xiaopeng.Building extraction from remote sensing image using improved watershed transform[J].Computer Applications and Software,2011,28(12):249-252.)
• [6] 曹林林，李海涛，韩颜顺，等.卷积神经网络在高分遥感影像分类中的应用[J].测绘科学，2016,41(9):170-175.(CAO Linlin,LI Haitao,HAN Yanshun,et al.Application of convolutional neural networks in classification of high resolution remote sensing imagery[J].Science of Surveying and Mapping,2016,41(9):170-175.)
• [7] 李冠东，张春菊，王铭恺，等.卷积神经网络迁移的高分影像场景分类学习[J].测绘科学，2019,44(4):116-123.(LI Guandong,ZHANG Chunju,WANG Mingkai,et al.Transfer learning using convolutional neural network for scene classification within high resolution remote sensing image[J].Science of Surveying and Mapping,2019,44(4):116-123.)
• [8] MAGGIORI E,TARABALKA Y,CHARPIAT G,et al.Convolutional neural networks for large-scale remote-sensing image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(2):645-657.
• [9] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Boston,MA,USA:IEEE,2015:3431-3440.
• [10] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
• [11] NOH H,HONG S,HAN B.Learning deconvolution network for semantic segmentation[C]//2015 IEEE International Conference on Computer Vision (ICCV).Santiago,Chile:IEEE,2015:1520-1528.
• [12] RONNEBERGER O,FISCHER P,BROX T.U-net:才onvolutional networks for biomedical image segmentation[M]//Lecture Notes in Computer Science.Cham:Springer International Publishing,2015:234-241.
• [13] 张春森，葛英伟，蒋萧.基于稀疏约束SegNet的高分辨率遥感影像建筑物提取[J].西安科技大学学报，2020,40(3):441-448.(ZHANG Chunsen,GE Yingwei,JIANG Xiao.High-resolution remote sensing image building extraction based on sparsely constrained SegNet[J].Journal of Xi’an University of Science and Technology,2020,40(3):441-448.)
• [14] 伍广明，陈奇，SHIBASAKI R,等.基于U型卷积神经网络的航空影像建筑物检测[J].测绘学报，2018,47(6):864-872.(WU Guangming,CHEN Qi,SHIBASAKI R,et al.High precision building detection from aerial imagery using a U-net like convolutional architecture[J].Acta Geodaetica et Cartographica Sinica,2018,47(6):864-872.)
• [15] 季顺平，魏世清.遥感影像建筑物提取的卷积神经元网络与开源数据集方法[J].测绘学报，2019,48(4):448-459.(JI Shunping,WEI Shiqing.Building extraction via convolutional neural networks from an open remote sensing building dataset[J].Acta Geodaetica et Cartographica Sinica,2019,48(4):448-459.)
• [16] 刘浩，骆剑承，黄波，等.基于特征压缩激活Unet网络的建筑物提取[J].地球信息科学学报，2019,21(11):1779-1789.(LIU Hao,LUO Jiancheng,HUANG Bo,et al.Building extraction based on SE-unet[J].Journal of Geo-Information Science,2019,21(11):1779-1789.)
• [17] 冯凡，王双亭，张津，等.基于尺度自适应全卷积网络的遥感影像建筑物提取[J/OL].激光与光电子学进展：1-20[2021-02-22].http://kns.cnki.net/kcms/detail/31.1690.TN.20210222.1100.021.html.(FENG Fan,WANG Shuangting,ZHANG Jin,et al.Building extraction from remote sensing imagery based on scale-adaptive fully convolutional network[J/OL].Laser & Optoelectronics Progress:1-20[2021-02-22].http://kns.cnki.net/kcms/detail/31.1690.TN.20210222.1100.021.html.)
• [18] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition[J].2016 IEEE Conference on Computer Vision and Pattern Recognition:CVPR,2016:770-778.