摘要
为了深入研究遥感数据及提取方法对估算水稻种植面积的可行性,以Landsat 8 OLI影像为数据源,运用ENVI5.1的软件平台,对沈阳市2015年6—9月水稻长势进行监测,并最终提取其种植面积。根据实地调查样本,通过分析各地物的光谱特性曲线、归一化植被指数均值特征及遥感影像成像特点,确定了以波段6、波段5、波段2对图像进行伪彩色合成。对合成后的图像,分时段设计了三组不同样本点数量的对比实验,样本数量分别为100、150、200个,采用混合像元的方式,确定了水稻的采集样本点,用变换分散度和J-M距离对各个样本间的可分离性进行检验,采用支持向量机的分类方法对各样本进行分类,最后以Majority/Minority分析方法对提取的结果进行分类后处理,建立了不同的水稻面积提取模型。结果显示,6月、7月、9月中200个样本点的实验提取结果均较为准确,提取面积分别为1 032.044 8、1 201.125 9和1 180.685 5 km2,参考《沈阳统计年鉴2015》对提取结果进行评价,精度分别为94.73%、89.75%和91.62%。试验表明,Landsat 8OLI遥感数据可准确提取沈阳市水稻种植面积,为综合多源数据对水稻进行种植监测奠定基础。
In order to study the feasibility of remote sensing data and extraction method to estimate the area of rice planting,this paper used Landsat 8 OLI image as the data source and ENVI5. 1 as software platform to monitor rice growth situation in June-September 2015 in Shenyang city,and extracted its acreage eventually. Based on the field survey samples,by analyzing the spectral characteristics,the normalized differential vegetation index and the characteristics of remote sensing images,this paper determined the false color synthesis by band 6,band 5 and band 2.The sampling points of the rice were selected by the mixed pixels,and the number of samples was 100,150 and 200 respectively. The transformed divergence and Jeffries-Matusita were used to test the separability among the samples.The samples were classified by the support vector machine. The classification results were sorted by Majority/Minority analysis method,and the extraction model of different rice areas were established finally. The results showed thatthe sample number of 200 was most accurate in June,July and September,and the extraction area was 1 032. 044 8,1 201. 125 9 and 1 180. 685 5 km2. According to the results from Shenyang Agricultural Statistics（ 2015）,the evaluation was 94. 73%,89. 75% and 91. 62% respectively. The experimental results showed that the Landsat 8 OLI remote sensing data can accurately extract the rice planting area in Shenyang,and lay the foundation for the rice planting monitoring for the multi-source data.
出处
《浙江农业学报》
CSCD
北大核心
2017年第10期1749-1758,共10页
Acta Agriculturae Zhejiangensis
基金
国家重点研发计划(2016YFD020060307)
作者简介
郑璐悦（1993-）,女,河北唐山人,硕士研究生,从事计算机应用方面研究.E-mail：153413544@qq.com
通信作者,许童羽,E-mail：yatongmu@163.com
