摘要
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。
GF-2 is a representative of high-resolution remote sensing satellites of China,wThose image datars function to im-prove the quality and accuracy of ground object information extraction is worthy of research and exploration.Optimal waveband combinations are selected by analyzing the characteristics of GF-2rs multispectral data and using the OIF indexes.The ESP opti-mal scale analysis algorithm is selected to obtain the optimal segmentation scales in the research area.On the basis of optimal waveband combinations and optimal segmentation scales,the typical ground objects are extracted and the accuracy of classifica-tion results is verified.The research results show that the optimal waveband combination of GF-2rs multispectral data is 134;the overall classification accuracy of ground object information extracted by means of optimal waveband combinations and opti-mal segmentation scales is larger than 85%,the Kappa coefficient is larger than 0.8,and the accuracy of classification results is high;on the whole,when the selected optimal segmentation scale is 82,the accuracy of the classification results is the highest(the overall accuracy is 93%and the Kappa coefficient is 0.910);when the optimal segmentation scale is 31,the accuracy of the classification results comes to the second(the overall accuracy is 89%and the Kappa coefficient is 0.859);when the opti-mal segmentation scale is 42,the accuracy of the classification results is the lowest(the overall accuracy is 85%and the Kappa coefficient is 0.808).
作者
任金铜
杨武年
邓晓宇
王蕾
王芳
REN Jintong;YANG Wunian;DENG Xiaoyu;WANG Lei;WANG Fang(Key Laboratory of Ministry of Land and Resources for Geoscience Spatial Information Technology,Chengdu University of Technology,Chengdu 610059,China;Key Laboratory of Education Department of Guizhou Province for Biological Resources Development and Ecological Restoration,Guizhou University of Engineering Science,Bijie 551700,China)
出处
《现代电子技术》
北大核心
2018年第8期72-77,82,共7页
Modern Electronics Technique
基金
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)~~
关键词
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
GF-2
OIF
multi-scale segmentation
object-oriented classification
KNN
remote sensing satellite
ground object information extraction