中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 基于时变特征的多时相PolSAR农作物分类方法 农业机械学报 2017 (12) 174-182
Position: Home > Articles > Crop Classification Method with Differential Characteristics Based on Multi-temporal PolSAR Images Transactions of the Chinese Society for Agricultural Machinery 2017 (12) 174-182

基于时变特征的多时相PolSAR农作物分类方法

作  者：
郭交;尉鹏亮;周正舒;苏宝峰
关键词：
农作物分类;极化合成孔径雷达;多时相;散射特性
摘  要：
获取农作物分类信息是极化合成孔径雷达(Polarimetric synthetic aperture radar,PolSAR)的重要应用之一,然而单时相PolSAR数据能够提供的信息十分有限,而且单时相数据的获取时间也会影响农作物分类精度。随着技术的发展,出现了大量的机载和星载PolSAR系统,这些系统能够获取目标重复观测的PolSAR数据,这为多时相PolSAR的数据分析和应用提供了可能。本文以多时相PolSAR农作物分类为出发点,通过利用不同农作物的极化散射特性的变化特性来提高分类精度。首先,基于极化散射特性分解原理分析了不同农作物在生长过程不同时期所呈现的散射特性变化规律,在此基础上定义了一个新的参数描述其散射特性的变化特性。其次,基于这一新参数提出了一种多时相PolSAR农作物监督分类算法。最后,通过对欧洲空间局所提供的基于Radarsat-2实测仿真生成的Sentinel-1数据处理结果表明,相比于基于复Wishart分布的监督分类算法,农作物的整体分类精度提高了约4个百分点,当农作物种类合并为4类时,整体分类精度提高了约6个百分点。
译  名：
Crop Classification Method with Differential Characteristics Based on Multi-temporal PolSAR Images
作  者：
GUO Jiao;WEI Pengliang;ZHOU Zhengshu;SU Baofeng;College of Mechanical and Electronic Engineering,Northwest A&F University;Key Laboratory of Agricultural Internet of Things,Ministry of Agriculture;Data 61,Commonwealth Scientific and Industrial Research Organization (CSIRO);
关键词：
crop classification;;polarimetric synthetic aperture radar;;multi-temporal;;scattering characteristics
摘  要：
Crop type classification is one of the most significant applications in polarimetric synthetic aperture radar( PolSAR) imagery. As an advanced remote-sensing technique,PolSAR has been proved to provide high-resolution information,including the intensity and polarization of illustrated land surface.However, single-temporal PolSAR data are restricted to provide sufficient information for crop classification and identification. With the increase of number of airborne and spaceborne PolSAR systems,a large number of real PolSAR data are generated,and thus provides opportunities for multitemporal data analysis. The potential of improving crop classification accuracy by introducing the differential characteristics of H/α parameters for multi-temporal PolSAR images was investigated. Firstly,by analyzing the characteristics of several typical crops in different growing stages,a new parameter was defined for the first time to describe the differential characteristics of H/α distribution. Therefore,a new supervised classification method with the newly defined parameter was proposed to classify different crop types. The main idea of the proposed method was to apply various features of classical H/α parameters to improve the accuracy of crop classification. A validation test for the new approach was performed with Sentinel-1 data sets which were simulated by Radarsat-2 data sets and provided by ESA. The results showed that the mean accuracy of the proposed method was improved by 4 percentage points compared with the supervised complex Wishart classifier when the six kinds of crops were classified. Furthermore,the number of classes was reduced to 4 and the accuracy was almost improved by 6 percentage points.

相似文章

导出引用
计量
文章访问数: 9
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46