任金铜,杨武年,邓晓宇,王蕾,王芳

• 1:成都理工大学国土资源部地学空间信息技术重点实验室
• 2:贵州工程应用技术学院贵州省教育厅生物资源开发与生态修复特色重点实验室

摘要(Abstract)：

高分二号作为国产高分辨率遥感的代表,其影像数据对提高地物信息提取的质量和精度的作用值得研究和探索。通过分析高分二号多光谱数据特点,利用OIF指数选取最佳波段组合,选用ESP最优尺度分析算法获得研究区最优分割尺度,最后在最佳波段组合和最优分割尺度的基础上提取典型地物,并对分类结果进行精度验证。研究发现,高分二号多光谱数据最佳波段组合为134;利用最佳波段组合和最优分割尺度提取地物信息的总体分类精度均大于85%,Kappa系数均大于0.8,分类结果精度较高;从总体来看,当选用最优分割尺度为82时,分类结果精度最高,其总体精度为93%,Kappa系数为0.910;其次是最优分割尺度为31,其总体精度为89%,Kappa系数为0.859;最优分割尺度为42的分类结果精度表现最差,其总体精度为85%,Kappa系数为0.808。

关键词(KeyWords)： 高分二号;OIF;多尺度分割;面向对象分类;KNN;遥感卫星;地物信息提取

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金资助项目(41372340);国家自然科学基金(41671432);; 四川省国土资源厅应用基础研究项目(KJ-2016-12);; 贵州省教育厅自然科学研究项目(黔教合KY字(2015)448号);; 贵州省科技厅联合基金项目(黔科合J字LKB[2012]20号、21号);; 四川省教育厅科研项目重点项目(17ZA0027)~~

作者(Author): 任金铜,杨武年,邓晓宇,王蕾,王芳

DOI: 10.16652/j.issn.1004-373x.2018.08.018

参考文献(References)：

• [1]方涛,霍宏,马贺平,等.高分辨率遥感影像智能解译[M].北京:科学出版社,2016.FANG Tao,HUO Hong,MA Heping,et al.Intelligent interpretation of high resolution remote sensing image[M].Beijing:Science Press,2016.
• [2]胡如忠,刘雪萍,楚良才,等.国产遥感卫星进展与应用实例[M].北京:电子工业出版社,2016.HU Ruzhong,LIU Xueping,CHU Liangcai,et al.Progress and application of domestic remote sensing satellites[M].Beijing:Publishing House of Electronic Industry,2016.
• [3]施骏骋,王金强,文广,等.资源三号影像的DOM制作对比分析[J].测绘科学,2016,41(1):133-138.SHI Juncheng,WANG Jinqiang,WEN Guang,et al.Comparative analysis on DOM production by ZY3 data[J].Science of surveying and mapping,2016,41(1):133-138.
• [4]胡芬,杨博,唐新明,等.ZY-3卫星异轨立体影像几何定位精度分析[J].航天返回与遥感,2016,37(1):71-79.HU Fen,YANG Bo,TANG Xinming,et al.Geo-positioning accuracy analysis of ZY-3 cross-track stereo-images[J].Spacecraft recovery&remote sensing,2016,37(1):71-79.
• [5]李德仁,张过,蒋永华,等.国产光学卫星影像几何精度研究[J].航天器工程,2016,25(1):1-9.LI Deren,ZHANG Guo,JIANG Yonghua,et al.Research on image geometric precision of domestic optical satellites[J].Spacecraft engineering,2016,25(1):1-9.
• [6]甘世书,贺鹏,胡觉,等.基于国产资源卫星遥感影像正判率及其影响因素分析[J].中南林业调查规划,2015,34(4):32-34.GAN Shishu,HE Peng,HU Jue,et al.Analysis of correct interpretation rate and influence factors based on domestic resource satellite images[J].Central south forest inventory and planning,2015,34(4):32-34.
• [7]刘玉红,赵筱榕,刘津.基于RPC像方改正模型的国产卫星几何纠正算法研究[J].地理信息世界,2014,21(6):43-47.LIU Yuhong,ZHAO Xiaorong,LIU Jin.Research on the geometry correction of domestic satellite based on RPC-image space correction model[J].Geomatics world,2014,21(6):43-47.
• [8]李卫红,周平华,李琦,等.“资源一号”02C卫星影像几何校正方法试验[J].华北科技学院学报,2015,12(1):99-102.LI Weihong,ZHOU Pinghua,LI Qi,et al.The geometry rectification experiment of"ZY-1"02C satellite[J].Journal of North China Institute of Science and Technology,2015,12(1):99-102.
• [9]王雪平.基于稀少控制点的资源三号影像几何纠正研究[D].长沙:中南大学,2014.WANG Xueping.Geometric rectification for ZY-3 image with sparse control points[D].Changsha:Central South University,2014.
• [10]赵欣,王晓晶,赵院,等.国产高分一号卫星数据傅里叶变换提取梯田影像可行性分析[J].中国水土保持,2016(1):63-65.ZHAO Xin,WANG Xiaojing,ZHAO Yuan,et al.Feasibility analysis on methodology of terraced extraction by using Fourier transformation based on domestic hi-resolution remote sensing images of GF-1 satellite[J].Soil and water conservation in China,2016(1):63-65.
• [11]黄艳艳,赵红莉,杨树文,等.HJ-1B卫星遥感影像的积雪识别[J].测绘科学,2016,41(8):129-133.HUANG Yanyan,ZHAO Hongli,YANG Shuwen,et al.A method of snow identification based on HJ-1B satellite remote sensing data[J].Science of surveying and mapping,2016,41(8):129-133.
• [12]李粉玲,常庆瑞,申健,等.基于GF-1卫星数据的冬小麦叶片氮含量遥感估算[J].农业工程学报,2016,32(9):157-164.LI Fenling,CHANG Qingrui,SHEN Jian,et al.Remotesensing estimation of winter wheat leaf nitrogen content basedon GF-1 satellite data[J].Transactions of the Chinese Societyof Agricultural Engineering,2016,32(9):157-164.
• [13]黄帅,丁建丽,李艳华.面向对象的国产GF-1遥感影像水体信息提取研究[J].人民长江,2016,47(5):23-28.HUANG Shuai,DING Jianli,LI Yanhua.Study of water in-formation extraction based on domestic GF-1 remote sensingimage by using object-oriented method[J].Yangtze river,2016,47(5):23-28.
• [14]郭玉宝,池天河,彭玲,等.利用随机森林的高分一号遥感数据进行城市用地分类[J].测绘通报,2016(5):73-76.GUO Yubao,CHI Tianhe,PENG Ling,et al.Classificationof GF-1 remote sensing image based on random forests for ur-ban land-use[J].Bulletin of surveying and mapping,2016(5):73-76.
• [15]陈玲,梁树能,周艳,等.国产高分卫星数据在高海拔地区地质调查中的应用潜力分析[J].国土资源遥感,2015,27(1):140-145.CHEN Ling,LIANG Shuneng,ZHOU Yan,et al.Potentialof applying domestic high-resolution remote sensing data togeological survey in high altitudes[J].Remote sensing forland and resources,2015,27(1):140-145.
• [16]刘佳.国产高分卫星数据的农业应用[J].卫星应用,2015(3):31-33.LIU Jia.Agricultural applications of domestic Gaofen satellitedata[J].Satellite application,2015(3):31-33.
• [17]付帅,艾波,高小明,等.基于资源三号卫星影像的水深反演:以永兴岛为例[J].海洋信息,2015(1):55-58.FU Shuai,AI Bo,GAO Xiaoming,et al.Water depth inver-sion based on ZY-3 satellite image-a case study of YongxingIsland[J].Marine information,2015(1):55-58.
• [18]MA Ligang,DENG Jinsong,YANG Huai,et al.Urban Landscape classification using Chinese advanced high-resolutionsatellite imagery and an object-oriented multi-variable model[J].Frontiers of information technology&electronic engineer-ing,2015,16(3):238-248.
• [19]官尚碧,刘智华,马泽忠,等.基于国产环境一号卫星的土地生态安全评价[J].安徽农业科学,2015(17):357-359.GUAN Shangbi,LIU Zhihua,MA Zezhong,et al.Evaluationon land ecological safety based on HJ-1 satellite[J].Journalof Anhui agricultural sciences,2015(17):357-359.
• [20]张馨蓓.高分二号影像融合方法比较与评价[J].黑龙江科技信息,2016(17):86-87.ZHANG Xinbei.Comparison and evaluation of GF-2 image fu-sion methods[J].Heilongjiang science and technology informa-tion,2016(17):86-87.
• [21]胡茂莹.基于高分二号遥感影像面向对象的城市房屋信息提取方法研究[D].长春:吉林大学,2016.HU Maoying.Research on the object-oriented method of ur-ban building extraction with GF-2 remote-sensing imagery[D].Changchun:Jilin University,2016.
• [22]王爱芸.山地GF-2卫星遥感图像融合方法优选研究[D].昆明:云南大学,2016.WANG Aiyun.The research of remote sensing image fusion method optimization based on the GF-2 satellite in the mountain area[D].Kunming:Yunnan University,2016.
• [23]任金铜,杨武年,杨鑫,等.国产高分二号PMS数据融合效果评价研究[C]//资源环境与地学空间信息技术新进展学术会议论文集.北京:科学出版社,2016:223-225.REN Jintong,YANG Wunian,YANG Xin,et al.Research on the evaluation of domestic GF-2 PMS data fusion[C]//Proceedings of the Academic Conference on New Progress of Resources Environment and Geomatics Spatial Information Technology.Beijing:Science Press,2016:223-225.
• [24]China Center for Resources Satellite Data and Application.History data statistics of satellites[EB/OL].[2017-03-15].http://218.247.138.119:7777/DSSPlatform/reportbysatellite.html?satellite=GF2&is History=yes.
• [25]杜挺.Landsat8 OLI遥感影像融合算法比较及其土地利用分类适应性分析[D].西安:西北大学,2015.DU Ting.The comparison among fusion algorithms of Landsat8 OLI remote-sensing imagery and the analysis on adaptability of the classification of land use[D].Xi’an:Northwest University,2015.
• [26]庄喜阳,赵书河,陈诚,等.面向对象的遥感影像最优分割尺度监督评价[J].国土资源遥感,2016,28(4):49-58.ZHUANG Xiyang,ZHAO Shuhe,CHEN Cheng,et al.Supervised evaluation of optimal segmentation scale with object-oriented method in remote sensing image[J].Remote sensing for land and resources,2016,28(4):49-58.
• [27]刘丽雅.基于国产GF-1的高寒山区土地利用/覆盖分类研究[D].杭州:浙江大学,2016.LIU Liya.Research on land use/cover classification of high cold mountain areas based on China-made GF-1[D].Hangzhou:Zhejiang University,2016.
• [28]刘兆祎,李鑫慧,沈润平,等.高分辨率遥感图像分割的最优尺度选择[J].计算机工程与应用,2014,50(6):144-147.LIU Zhaoyi,LI Xinhui,SHEN Runping,et al.Selection of the best segmentation scale in high-resolution image segmentation[J].Computer engineering and applications,2014,50(6):144-147.
• [29]周亦,张亚亚.利用e Cognition进行高分一号卫星数据土地利用现状解译能力测试[J].测绘通报,2016(8):77-80.ZHOU Yi,ZHANG Yaya.Test of land use interpretation ability with satellite data of GF-1 using the e Cognition[J].Bulletin of surveying and mapping,2016(8):77-80.
• [30]朱红春,蔡丽杰,刘海英,等.高分辨率影像分类的最优分割尺度计算[J].测绘科学,2015,40(3):71-75.ZHU Hongchun,CAI Lijie,LIU Haiying,et al.Optimal segmentation scale calculation for high-resolution remote sensing image[J].Science of surveying and mapping,2015,40(3):71-75.
• [31]DR?GU?L,CSILLIK O,EISANK C,et al.Automated parameterisation for multi-scale image segmentation on multiple layers[J].ISPRS Journal of photogrammetry&remote sensing,2014,88:119-127.