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 > 基于无人机多光谱遥感的农业园区地物分类研究 江苏农业学报 2023,39 (9) 1862-1871
Position: Home > Articles > Classification of geological features in agricultural parks based on multi-spectral remote sensing by unmanned aerial vehicle Jiangsu Journal of Agricultural Sciences 2023,39 (9) 1862-1871

基于无人机多光谱遥感的农业园区地物分类研究

作  者：
宋恩泽;张颖;邵光成;刘杰;王羿;朱雪颖
单  位：
关键词：
无人机遥感;农业园区;地物分类
摘  要：
复杂地物的快捷精准监测是遥感的热点和难点.为实现农业园区复杂地物的快捷准确分类监测,本研究以河海大学江宁校区节水园区为例,基于无人机多光谱遥感影像,分别采用支持向量机模型(SVM)、随机森林模型(RF)和人工神经网络模型(ANN)对试验区内地物进行精细分类,构建验证集混淆矩阵,并根据总体分类精度、Kappa系数等指标筛选出中小型农业园区的最适地物分类模型,并利用TensorFlow训练深度学习算法对最适分类模型的分类结果进行进一步优化.结果表明:SVM分类模型对试验农业园区的总体分类精度为 97.4%,Kappa系数为 0.96,优于RF、ANN分类模型;与原始SVM分类模型的分类结果相比,通过TensorFlow训练深度学习算法优化,将试验农业园区图像裁剪为a、b两区,a、b两区的分类精度分别为 97.54%和 99.12%,获得了较高的优化结果.研究结果可为中小型农业园区地物分类提供技术支持.
译  名：
Classification of geological features in agricultural parks based on multi-spectral remote sensing by unmanned aerial vehicle
关键词：
unmamed aerial vehicle remote sensing%agricultural park%classification of features
摘  要：
Fast and accurate monitoring of complex objects is a hot and difficult point in remote sensing.In order to realize the fast and accurate monitoring of complex feature classification in agricultural parks,this study took the water-sav-ing park of Jiangning Campus of Hohai University as an example.Based on the multi-spectral remote sensing image of un-manned aerial vehicle(UAV),the support vector machine model(SVM),random forest model(RF)and artificial neural network model(ANN)were used to classify the objects in the test area,and the confusion matrix of the validation set was constructed.According to the overall classification accuracy,Kappa coefficient and other indicators,the optimal feature classification model of small and medium-sized agricultural parks was selected,and the TensorFlow training deep learning algorithm was used to further optimize the classification results of the optimal classification model.The results showed that the overall classification accuracy of SVM classification model was 97.4%,and the Kappa coefficient was 0.96,which was better than those of RF and ANN classification models.Compared with the original SVM classification model,the images of the experimental agricultural park were cut into a and b areas by TensorFlow training deep leaming algorithm optimization,and the classification accuracy of a and b ar-eas was 97.54%and 99.12%,respectively and higher op-timization results were obtained.The research results could provide technical support for the classification of small and me-dium-sized agricultural parks.

相似文章

导出引用
计量
文章访问数: 13
HTML全文浏览量: 0
PDF下载量: 0

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