吕道双;林娜;冯丽蓉;张小青;

• 1:重庆交通大学土木工程学院
• 2:重庆市地理信息和遥感应用中心

摘要(Abstract)：

针对传统人工提取方法自动化程度低、过分依赖人工设计的特征,以及现有的深度学习方法中存在的提取精度不高等问题,提出了一种基于改进型U-Net网络的高分辨率遥感影像建筑物提取方法。首先将空洞卷积加入到网络中,利用不同尺度的空洞卷积对来自网络编码部分的结果进行多尺度特征提取;再对提取的特征进行特征融合,并输入到网络的下一层;然后将制作的数据集输入到网络中进行训练;最后利用Softmax得到最终分割结果。在建筑物公开的数据集中进行测试,提取结果的像素精度为96.26%;Iou精度为78.59%、Recall为95.65%,表明该方法具有良好的鲁棒性和精度,能从影像中准确地提取建筑物。

关键词(KeyWords)： 建筑物提取;卷积神经网络;空洞卷积;高分辨率遥感影像

Abstract:

Keywords:

基金项目(Foundation): 重庆市研究生科研创新资助项目(CYS19236);; 重庆市教委科技资助项目(KJQN201800747)

作者(Author): 吕道双;林娜;冯丽蓉;张小青;

Email:

DOI:

参考文献(References)：

• [1]HUANG X,ZHANG L.An SVM Ensemble Approach Combining Spectral,Structural,and Semantic Features for the Classification of High-resolution Remotely Sensed Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(1):257-272
• [2]Ghanea M,Moallem P,Momeni M.Automatic Building Extraction in Dense Urban Areas Through Geo Eye Multispectral Imagery[J].International Journal of Remote Sensing,2014,35(13):5 094-5 119
• [3]Dikmen M,Halici U.A Leaning-based Resegmentation Method for Extraction of Buildings in Satellite Images[J].IEEEGeoscience and Remote Sensing Letters,2014,11(12):2 150-2 153
• [4]WANG J,YANG X C,QIN X B,et al.An Efficient Approach for Automatic Rectangular Building Extraction from very High Resolution Optical Satellite Imagery[J].IEEE Geoscience and Remote Sensing Letters,2015,12(3):487-491
• [5]TIAN J,Reinartz P,D’Angelo P,et al.Region-based Automatic Building and Forest Change Detection on Cartosat-1 Stereo Imagery[J].ISPRS Journal of Photogrammetry and Remote Sensing,2013,79:226-239
• [6]LI Y,ZHU L,GONG P,et al.A Refined Marker Controlled Watershed for Building Extraction from DSM and Imagery[J].International Journal of Remote Sensing,2010,31(6):1 441-1 452
• [7]Saeid P,Meisam A.Building Extraction from Fused Li DARand Hyperspectral Data Using Random Forest Algorithm[J].Geomatic,2017,71(4):185-193
• [8]HUANG X,ZHANG L P.Morphological Building/Shadow Index for Building Extraction from High-resolution Imagery over Urban Areas[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012,5(1):161-172
• [9]王港,陈金勇,高峰,等.基于深度学习的遥感影像基础设施目标检测研究[J].无线电工程,2018,48(3):219-224
• [10]张欢,雷宏,陈凯强.密集反卷积网络在遥感建筑物提取中的应用[J].计算机工程与应用,2018,54(11):140-144
• [11]左童春.基于高分辨率可见光遥感图像的建筑物提取技术研究[D].合肥:中国科学技术大学,2017
• [12]LONG J,Shelhamer E,Darrell T.Fully Convolutional Net-works for Semantic Segmentation[C].Proceedings of the 2015 IEEEConference on Computer Vision and Pattern Recognition(CVPR),Boston,Massachusetts,USA,2015:431-440
• [13]Ronneberger O,Fischer P,Brox T.U-Net:Convolutional Networks for Biomedical Image Segmentation[C].International Conference on Medical Image Computing and Computer Assisted Intervention,Springer,2015:234-241