基于深度学习的河道提取与变化监测应用——以永定河为例
|
摘要
本文基于2014年、2017年、2018年三期GF1遥感影像,针对北京市石景山永定河河道变化特征,开展基于深度学习算法的河道自动提取与变化图斑自动发现。选择GEOWAY GFLP作为地理要素智能训练平台,采用基于疑似变化区域自动发现与人工交互确认相结合的遥感监测技术路线,选取典型水体样本进行分析、训练,构建深度学习卷积神经网络水体提取模型。通过分析与验证发现,基于深度学习水体提取模型自动提取的河道准确率高于90%,精度高于最小距离、最大似然及SVM分类方法,可用于城市河道的自动提取和变化发现。
This paper carries out a research on the automatic extraction and change detection of river channels based on deep learning,using GF-1 remote sensing images of three different phases from 2014,2017 to 2017.Remote sensing monitoring technology route based on the combination of automatic detection of suspected change areas and manual interactive confirmation is adopted.Taking GEOWAY GFLP as intelligent training platform for geographical elements,typical water samples are selected for analyzing,training and constructing a depth learning convolution neural network water extraction model.We drawn the conclusion that the accuracy of a water extraction model based on deep learning is higher than 90%,and the method whose accuracy is better than Minimum distance method,Maximum likelihood method and SVM classification method is feasible.
This paper carries out a research on the automatic extraction and change detection of river channels based on deep learning,using GF-1 remote sensing images of three different phases from 2014,2017 to 2017.Remote sensing monitoring technology route based on the combination of automatic detection of suspected change areas and manual interactive confirmation is adopted.Taking GEOWAY GFLP as intelligent training platform for geographical elements,typical water samples are selected for analyzing,training and constructing a depth learning convolution neural network water extraction model.We drawn the conclusion that the accuracy of a water extraction model based on deep learning is higher than 90%,and the method whose accuracy is better than Minimum distance method,Maximum likelihood method and SVM classification method is feasible.
引文
[1]许杰玉,赵晓飞,吕春英,等.星云湖流域水环境污染特征分析与综合整治研究[C].中国环境科学学会学术年会,2015.
[2]吴阳.星云湖流域水域遥感监测及其演变分析研究[D].云南昆明:昆明理工大学,2017.
[3]CRASTO N,HOPKINSON C,FORBES D L,et al.A LiDAR-based Decision-tree Classification of Open Water Surfaces in an Arctic Delta[J].Remote Sensing of Environment,2015,164(46):90-102.
[4]NIELSEN E S,JENSEN E A.Primary Ocean Production.The Autotrophic Production of Organic Matter in the Oceans[J].Galathea Report,1957:49-136.
[5]BARTON I J,BATHOLS J M.Monitoring floods with AVHRR[J].Remote Sensing of Environment,1989,30(1):89-94.
[6]MCFEETERS S K.The Use of the Normalized Difference Water Index(NDWI)in the Delineation of Open Water Features[J].International Journal of Remote Sensing,1996,17(7):1425-1432.
[7]SAGHEBIAN S M,SATTARI M T,MIRABBASIR,et al.Ground Water Quality Classification by Decision Tree Method in Ardebil Region,Iran[J].Arabian Journal of Geosciences,2014,7(11):4767-4777.
[8]杨存建,徐美.遥感信息机理的水体提取方法的探讨[J].地理研究,1998(17):86-89.
[9]韩栋,杨晓梅,纪凯.小卫星遥感影像自动提取水体方法研究[J].测绘科学,2008,33(1):51-54.
[10]BAATZ R,LANDGREEBE D.Classification of Multispectral Image Date by Extraction and Classification of Homogeneous[J].IEEE Transaction on Geoscience Eletronics,1976,14(10):19-26.
[11]曹凯,江南,吕恒,等.面向对象的SPOT5影像城区水体信息提取研究[J].国土资源遥感,2007,19(2):27-30.
[12]殷亚秋,李家国,余涛,等.基于高分辨率遥感影像的面向对象水体提取方法研究[J].测绘通报,2015(1):81-85.
[13]MARTZ L W,GARBRECHT J.Numerical Definition of Drainage Network and Subcatchment Areas from Digital Elevation Models[J].Computers&Geosciences,1992,18(6):747-761.
[14]李晶,张征,朱建刚,等.基于DEM的太湖流域水文特征提取[J].环境科学与管理,2009,34(5):138-142.
[15]杜敬.基于深度学习的湖泊湿地信息提取及时空演变特征研究[D].上海:华东理工大学,2017.
[16]HINTON G E,SALAKHUTDINOV R R.Reducing the Dimensionality of Data with Neural Networks.[J].Science,2006,313(5786):504-507.
[17]LNGKVIST M,KISELEV A,ALIREZAIE M,et al.Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks[J].Remote Sensing,2016,8(4):329.
[18]ZHAO W,DU S.Learning Multiscale and Deep Representations for Classifying Remotely Sensed Imagery[J].ISPRS Journal of Photogrammetry&Remote Sensing,2016(113):155-165.
[19]许夙晖,慕晓冬,赵鹏,等.利用多尺度特征与深度网络对遥感影像进行场景分类[J].测绘学报,2016,45(7):834-840.
[20]冯学兵,任海英,马福光,等.北京市平原区小流域划分技术研究[J].北京测绘,2012(6):34-36.
[21]闫琰,董秀兰,李燕.基于ENVI的遥感图像监督分类方法比较研究[J].北京测绘,2011(3):14-16.
[2]吴阳.星云湖流域水域遥感监测及其演变分析研究[D].云南昆明:昆明理工大学,2017.
[3]CRASTO N,HOPKINSON C,FORBES D L,et al.A LiDAR-based Decision-tree Classification of Open Water Surfaces in an Arctic Delta[J].Remote Sensing of Environment,2015,164(46):90-102.
[4]NIELSEN E S,JENSEN E A.Primary Ocean Production.The Autotrophic Production of Organic Matter in the Oceans[J].Galathea Report,1957:49-136.
[5]BARTON I J,BATHOLS J M.Monitoring floods with AVHRR[J].Remote Sensing of Environment,1989,30(1):89-94.
[6]MCFEETERS S K.The Use of the Normalized Difference Water Index(NDWI)in the Delineation of Open Water Features[J].International Journal of Remote Sensing,1996,17(7):1425-1432.
[7]SAGHEBIAN S M,SATTARI M T,MIRABBASIR,et al.Ground Water Quality Classification by Decision Tree Method in Ardebil Region,Iran[J].Arabian Journal of Geosciences,2014,7(11):4767-4777.
[8]杨存建,徐美.遥感信息机理的水体提取方法的探讨[J].地理研究,1998(17):86-89.
[9]韩栋,杨晓梅,纪凯.小卫星遥感影像自动提取水体方法研究[J].测绘科学,2008,33(1):51-54.
[10]BAATZ R,LANDGREEBE D.Classification of Multispectral Image Date by Extraction and Classification of Homogeneous[J].IEEE Transaction on Geoscience Eletronics,1976,14(10):19-26.
[11]曹凯,江南,吕恒,等.面向对象的SPOT5影像城区水体信息提取研究[J].国土资源遥感,2007,19(2):27-30.
[12]殷亚秋,李家国,余涛,等.基于高分辨率遥感影像的面向对象水体提取方法研究[J].测绘通报,2015(1):81-85.
[13]MARTZ L W,GARBRECHT J.Numerical Definition of Drainage Network and Subcatchment Areas from Digital Elevation Models[J].Computers&Geosciences,1992,18(6):747-761.
[14]李晶,张征,朱建刚,等.基于DEM的太湖流域水文特征提取[J].环境科学与管理,2009,34(5):138-142.
[15]杜敬.基于深度学习的湖泊湿地信息提取及时空演变特征研究[D].上海:华东理工大学,2017.
[16]HINTON G E,SALAKHUTDINOV R R.Reducing the Dimensionality of Data with Neural Networks.[J].Science,2006,313(5786):504-507.
[17]LNGKVIST M,KISELEV A,ALIREZAIE M,et al.Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks[J].Remote Sensing,2016,8(4):329.
[18]ZHAO W,DU S.Learning Multiscale and Deep Representations for Classifying Remotely Sensed Imagery[J].ISPRS Journal of Photogrammetry&Remote Sensing,2016(113):155-165.
[19]许夙晖,慕晓冬,赵鹏,等.利用多尺度特征与深度网络对遥感影像进行场景分类[J].测绘学报,2016,45(7):834-840.
[20]冯学兵,任海英,马福光,等.北京市平原区小流域划分技术研究[J].北京测绘,2012(6):34-36.
[21]闫琰,董秀兰,李燕.基于ENVI的遥感图像监督分类方法比较研究[J].北京测绘,2011(3):14-16.