摘要
以提高药用植物红花种植面积估算精度为目标,选取种植面积较集中的塔城地区裕民县农业区作为研究区,对研究区资源3号卫星影像进行主成分分析(PCA)分析,然后对其第一主分量进行适宜的纹理特征提取来提高分类精度,并对比分析了基于单纯光谱特征方法和基于PCA和纹理特征的分类方法在估算红花种植面积中的精度。研究结果表明:基于PCA和纹理特征的分类方法分类精度达到了87.519 1%,Kappa系数达到了0.810 1,比单纯基于光谱特征的分类方法分类精度提高了4.835 5%,Kappa系数提高了0.080 7。因此本文采取的基于PCA和纹理特征的分类方法提取资源三号卫星影像中的种植红花并估算其种植面积,进而作为药用植物红花蕴藏量调查的技术方案具有可行性。
To improve accuracy of estimation in planted safflower acreage,we selected agricultural area in Yumin County,Xinjiang as the study area. There safflower was concentrated planted. Supervised classification based on Principal Component Analysis （PCA） and texture feature were used to obtain the safflower acreage from image captured by ZY-3. The classification result was compared with only spectral feature and spectral feature with texture feature. The research result shows that this method can effectively solve the problem of low accuracy and fracture classification result in single data source classification. The overall accuracy is 87.519 1%, which increases by 7.117 2% compared with single data source classification. Therefore, the classification method based on PCA and texture features can be adapted to RS image classification and estimate the acreage of safflower. This study provides a feasible solution for estimation of planted safflower acreage by image captured by ZY-3 satellite.keywords：safflower
出处
《中国中药杂志》
CAS
CSCD
北大核心
2013年第21期3681-3686,共6页
China Journal of Chinese Materia Medica
基金
中医药公共卫生专项(财社[2011]76号)
中医药行业科研专项(201207002)
关键词
红花
种植面积
主成分分析
纹理特征
safflower
acreage
principal component analysis （PCA）
texture features
作者简介
娜仁花，硕士研究生，E-mail：499361608@qq．com
[通信作者]郑江华，博士，硕士生导师，E—mail：itslbs@126．com
