排序方式： 共有6条查询结果，搜索用时 15 毫秒
1
1.
面向对象的多光谱图像特征遗传选优方法 总被引：1，自引：0，他引：1
为了有效提高作物遥感识别过程中对作物分类的精度,需要对光谱图像特征进行合理选择,得到最佳波段组合.该文在对多光谱数据的光谱信息特征进行全面分析基础上,针对目标地物,提出面向对象的多光谱图像特征遗传选优算法模型.在模型中,先根据最佳指数因子法计算比较,得出最佳识别组合的特征数量:然后,以最大最小距离作为理论基础,对Jeffries-Matusita(J-M)距离改进,得到加权J-M距离,作为衡量特征对分类有效性的判据,并以此构建适应度函数,运用遗传算法对结果优化处理,选择出对分类敏感的波段组合.以吉林德惠县内的Landsat-5数据为例,进行波段选择实验,取得较好的成效. 相似文献
2.
Salinity Inversion of Severe Saline Soil in the Yellow River Estuary Based on UAV Multi-Spectra 总被引：2，自引：0，他引：2
WANG DanYang CHEN HongYan WANG GuiFeng CONG JinQiao WANG XiangFeng WEI XueWen 《中国农业科学》2019,52(10):1698-1709
3.
应用多光谱图像技术进行锦橙叶片氮含量监测 总被引：1，自引：0，他引：1
以蓬安100号锦橙为试材,运用多光谱图像技术建立快速监测叶片氮含量的方法。利用多光谱相机MS3100采集蓬安100号锦橙叶片图像,运用Adobe Photoshop软件提取叶片图像的颜色特征参数,对其进行数学变换和归一化处理后的颜色特征参数与叶片氮含量值进行相关分析,并建立二者回归模型。结果表明:6个颜色特征参数G-B、G/(R+B)、(G-B)/(G+B)、G/(R+G+B)、g-b值与叶片氮含量的相关较好,综合评价得出G-B、(G-B)/(G+B)、g-b值所建立的蓬安100号锦橙叶片氮含量监测模型较好,其相关系数均为0.84,决定系数为0.70,预测误差为3.7%。研究结果表明,利用计算机视觉技术进行锦橙叶片氮含量监测是可行的。 相似文献
4.
Cotton Nitrogen Nutrition Diagnosis Based on Spectrum and Texture Feature of Images from Low Altitude Unmanned Aerial Vehicle 总被引：3，自引：1，他引：3
【Objective】 Based on the high spatial resolution images of unmanned aerial vehicle (UAV), the effects of removing soil background information and increasing image texture information on the inversion of cotton plant nitrogen concentration were investigated, in order to provide new technology for accurate estimation of cotton nitrogen nutrition status. 【Method】 Cotton water and nitrogen coupling experiment was conducted, and UAV images and plant nitrogen concentration data were measured during different cotton growth stages. Based on the above data, the effect of soil background on cotton canopy spectrum was firstly investigated. Secondly, the correlations between image texture parameters and plant nitrogen concentration were analyzed. Finally, the obtained data was divided into calibration dataset and validation dataset. Different scenarios, including before and after removing the soil background, and adding texture features, were set. The inversion models of plant nitrogen concentration under various scenarios were designed by using the coupled method of spectral indexes and principal component regression, and the performances of the models were compared. 【Result】 The soil background had an effect on the cotton canopy spectrum, and the trends were not the same at different growth stages. There existed significant correlations between image texture parameters and plant nitrogen concentration. For the scenarios before removal soil background, the plant nitrogen concentration prediction model had determination coefficient (R 2) value of 0.33 and root mean square error (RMSE) value of 0.21% during model calibration, and R 2 value of 0.19 and RMSE value of 0.23% during validation. For the scenarios after removing soil background, the plant nitrogen concentration prediction model had R 2 value of 0.38 and RMSE value of 0.20% during model calibration, and R 2 value of 0.30 and RMSE value of 0.21% during validation. For the scenarios adding image texture information, the plant nitrogen concentration prediction model had R 2 value of 0.57 and RMSE value of 0.17% during model calibration, and R 2 value of 0.42 and RMSE value of 0.19% during validation. 【Conclusion】 Based on high spatial resolution images of low-altitude UAVs, both removing soil background and adding image texture information could improve the inversion accuracy of cotton plant nitrogen concentration. Image texture could be considered as important information to support prediction of crop nitrogen nutrition status using UAV images. 相似文献
5.
无人机多光谱反演黄河口重度盐渍土盐分的研究 总被引：2，自引：0，他引：2
【目的】为提高土壤盐分信息定量遥感提取精度,准确掌握土壤盐渍化程度与分布。【方法】选择垦利区黄河口镇集中连片的重度盐渍土区域为试验区,于2018年4月26日—28日采用搭载Sequoia多光谱相机的无人机进行试验区近地遥感图像采集,并进行图像拼接、辐射校正、正射校正和几何校正等预处理;然后基于相关性分析、灰色关联度分析筛选土壤盐分的敏感波段,构建并筛选光谱参量;进而分别采用多元线性回归（multivariable linear regression,MLR）、支持向量机（support vector machine,SVM）及偏最小二乘（partial least square,PLS）方法构建土壤盐分定量反演模型,并进行验证与评价;最后基于最佳模型进行试验区土壤盐分的分布反演与分析,并与反距离加权插值结果进行精度比较。【结果】相较相关性分析,通过灰色关联度分析的反演模型精度及显著性均有所提高;对比3种建模方法,SVM模型精度最高,PLS模型次之,MLR模型最低,最佳模型为基于灰色关联度分析筛选变量的支持向量机模型,其建模R 2、RMSE分别为0.820、3.626,验证R 2、RMSE、RPD分别为0.773、4.960、2.200;据此模型反演得到该区域土壤盐分含量为0.323—21.210 g·kg -1,平均值为6.871 g·kg -1,重度盐渍土占58.094%,与实地调查结果较为一致;反演结果与反距离加权插值结果的误差80%控制在样本盐分含量平均值的20%以内,亦较为相近。 【结论】基于无人机多光谱可实现重度盐渍土盐分信息的准确提取。 相似文献
6.
基于低空无人机影像光谱和纹理特征的棉花氮素营养诊断研究 总被引：5，自引：1，他引：4
【目的】基于无人机高空间分辨率影像,探讨剔除土壤背景信息及增加纹理信息对棉花植株氮浓度反演的影响,为棉花氮素营养精准探测提供新技术手段。【方法】开展棉花水、氮耦合试验,分别在棉花的不同生育期获取无人机多光谱影像和植株氮浓度信息。基于以上数据,首先探讨了土壤背景对棉花冠层光谱的影响;其次,分析了影像纹理特征与植株氮浓度间的相关性;最后,将获得的数据分为建模样本和检验样本,设置剔除土壤背景前、剔除土壤背景后、增加纹理特征等不同情景,采用光谱指数与主成分分析耦合建模的方法,来建立各种情景下植株氮浓度的反演模型,并对模型反演效果进行比较。【结果】土壤背景对棉花冠层光谱有影响,且不同生育期趋势不同;影像纹理特征参数与植株氮浓度间有显著相关关系;剔除土壤背景前植株氮浓度反演模型的建模决定系数为0.33,标准误差为0.21%,验证决定系数为0.19,标准误差为0.23%;剔除土壤背景后模型的建模决定系数为0.38,标准误差为0.20%,验证决定系数为0.30,标准误差为0.21%;增加纹理信息后模型的建模决定系数为0.57,标准误差为0.17%,验证决定系数为0.42,标准误差为0.19%。【结论】基于低空无人机高空间分辨率影像,剔除土壤背景和增加纹理特征均可提高棉花植株氮浓度的反演精度;影像纹理可以作为一种重要信息来支撑无人机遥感技术反演作物氮素营养状况。 相似文献
1