王卫,李敬,陈晓远,等.基于高分二号影像的粤北地区香芋遥感识别研究[J].广东农业科学,2020,(6-7):- |
PDF
HTML
基于高分二号影像的粤北地区香芋遥感识别研究 |
Study on Remote Sensing Identification of Taro in Northern Guangdong Based on GF-2 Image |
投稿时间:2020-05-20 修订日期:2020-05-29 |
DOI: |
中文关键词: 遥感识别 纹理信息 多光谱特征 粤北地区 香芋 |
英文关键词: remote sensing identification texture information multispectral features northern Guangdong taro |
基金项目:2018年广东省科技创新战略专项资金(韶科2018[118]),韶关市科技计划项目(201644),2015年韶关学院校级课题(2015262) |
|
摘要点击次数: 241 |
全文下载次数: 0 |
中文摘要: |
【目的】高分辨率遥感影像为农作物监测提供高精度的支撑,香芋作物粤北地区的特色作物,是国家地理标志产品,对其监测有助于加强管控和调控。【方法】本文选择香芋关键物候期的高分二号遥感影像,提取归一化植被指数、归一化差异水体指数、纹理信息,构建融合多特征光谱纹理影像,比较多种组合影像,采用支持向量机作为分类器,对香芋的识别精度分析。【结果】结果表明,融合多特征光谱纹理影像的香芋识别精度最高,总体精度达到96.04%,香芋的识别精度达到95.30%,分别比多光谱影像分类精度提高了5%和6.8%,是多光谱全色融合影像分类精度提升幅度的2倍,且各类地物边界轮廓清晰,图像平滑,细碎图斑很少。【结论】高分二号影像是识别粤北地区香芋的理想数据源,分类精度较高,能够满足农作物监测的需求,能为制定病虫害防治措施,调节种植结构提供支持。 |
英文摘要: |
[Objective] The high-resolution remote sensing image provides high-precision support for crop monitoring. The characteristic crop of taro crop in the north of Guangdong Province is a national geographical indication product, and its monitoring is helpful to strengthen control and regulation. [Methods] In this paper, the high-resolution two remote sensing image of the key phenology of taro is selected, the normalized vegetation index, normalized difference water index and texture information are extracted, the multi-feature spectral texture image is constructed and compared, and support vector machine is used as classifier to analyze the identification accuracy of taro. [Results] The results show that the identification accuracy of taro is the highest, the overall accuracy is 96.04%, and the classification accuracy of taro is 95.30%, which is 5% and 6.8% higher than that of multispectral image, respectively, which is twice the improvement of classification accuracy of multispectral panchromatic fusion image, and the boundary outline of all kinds of ground objects is clear, the image is smooth, and there are few fine spots. [Conclusion] GF-2 is an ideal data source for identifying taro in the north of Guangdong Province, with high classification accuracy, which can meet the needs of crop monitoring, and provide support for the formulation of pest control measures and the adjustment of planting structure. |
查看/发表评论 下载PDF阅读器 |
|
|
|