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Landsat8和高分一号影像的沙湾县作物种类识别研究 山东农业科学 2020 (2) 156-162
Position: Home > Articles > Identification of Crop Species in Shawan County Based on Landsat8 and GF-1 Remote Sensing Images Shandong Agricultural Sciences 2020 (2) 156-162

基于Landsat8和高分一号影像的沙湾县作物种类识别研究

作  者：
白雪;武红旗;吕昱;范燕敏
单  位：
新疆农业大学草业与环境科学学院
关键词：
沙湾县;Landsat8;高分一号;作物识别
摘  要：
本研究探讨了如何利用中分辨率遥感影像实现县域作物快速识别的方法。以沙湾县为研究区,基于Landsat8和高分一号遥感影像,利用实地调查的2016年沙湾县作物种植信息,建立解译标志,加入耕地掩膜,选取不同的监督分类方法,对沙湾县作物识别的最佳识别时相、最佳识别方法以及最佳数据源进行研究。结果表明:Landsat8影像与高分一号影像分别在7月与9月可分离度与总体精度最高;通过六种分类方法对比,均为支持向量机分类法分类精度最高,Landsat8影像总体精度91. 22%,Kappa系数0. 916,高分一号影像总体精度88. 23%,Kappa系数0. 876,Landsat8影像分类整体精度略高于高分一号影像;对于两种数据源,棉花、玉米、小麦和其它作物分类总体精度均达到88. 23%以上,证明使用中分辨率遥感影像对县域作物进行识别是可行的。
译  名：
Identification of Crop Species in Shawan County Based on Landsat8 and GF-1 Remote Sensing Images
作  者：
Bai Xue;Wu Hongqi;Lü Yu;Fan Yanmin;College of Pratacultural and Environmental Sciences,Xinjiang Agricultural University;
关键词：
Shawan County;;Landsat8;;GF-1;;Crop identification
摘  要：
In this article,the method how to achieve rapid identification of crops using mid-resolution remote sensing images was discussed. Taking Shawan County as the research area,based on the Landsat8 and GF-1 remote sensing images and the field survey data of the crop cultivation information in 2016,the interpretation signs were established,and the optimal time phase,method and data source for crop identification were studied by different supervision and classification methods and adding cultivated land masks. The results showed that the separability and overall accuracy of Landsat8 and GF-1 images were the highest in July and September,respectively. The SVM method was selected with the highest classification accuracy based on the two data sources through comparing the six classification methods. The overall accuracy of Landsat8 and GF-1 images was 91. 22% and 88. 23%,respectively,and their Kappa coefficient was 0. 916 and 0. 876,respectively. The overall classification accuracy of Landsat8 image was slightly higher than that of GF-1 image. The overall classification accuracies of cotton,corn,wheat and other crops reached more than 88. 23% for both data sources. In conclusion,it was feasible to use the medium-resolution remote sensing images to identify crops in the county.

相似文章

导出引用
计量
文章访问数: 8
HTML全文浏览量: 0
PDF下载量: 1

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