基于不同空间分辨率无人机多光谱遥感影像的小麦倒伏区域识别方法  

Wheat Lodging Area Recognition Method Based on Different Resolution UAV Multispectral Remote Sensing Images

作　　者：魏永康 杨天聪 丁信尧 高越之 袁鑫茹 贺利 王永华[1,3] 段剑钊 冯伟 WEI Yongkang;YANG Tiancong;DING Xinyao;GAO Yuezhi;YUAN Xinru;HE Li;WANG Yonghua;DUAN Jianzhao;FENG Wei(Agronomy College of Henan Agriculture University,Zhengzhou 450046,China;Key Laboratory of Regulating and Controlling Crop Growth and Development Ministry of Education,Zhengzhou 450046,China;State Key Laboratory of Wheat and Maize Crop Science,Zhengzhou 450046,China)

机构地区：[1]河南农业大学农学院,河南郑州450046 [2]教育部作物生长发育调控重点实验室,河南郑州450046 [3]省部共建小麦玉米作物学国家重点实验室,河南郑州450046

出　　处：《智慧农业（中英文）》2023年第2期56-67,共12页Smart Agriculture

基　　金：河南省科技研发计划联合基金优势学科培育类项目(222301420104)。

摘　　要：[目的/意义]快速准确评估作物倒伏灾情状况,需及时获取倒伏发生位置及面积等信息。目前基于无人机遥感识别作物倒伏缺乏相应的技术标准,不利于规范无人机数据获取流程和提出问题解决方案。本研究旨在探讨不同空间分辨率无人机遥感影像及特征优化方法对小麦倒伏区域识别精度的影响。[方法]在小麦倒伏后设置3个飞行高度(30、60和90 m),获取不同空间分辨率(1.05、2.09和3.26 cm)的数字正射影像图(Digital Orthophoto Map,DOM)和数字表面模型(Digital Surface Model,DSM),从不同空间分辨率影像中分别提取5个光谱特征、2个高度特征、5个植被指数以及40个纹理特征构建全特征集,并选择3种特征选择方法(ReliefF算法、RFRFE算法、Boruta-Shap算法)筛选构建特征子集,进而利用3种面向对象监督分类方法——支持向量机(Support Vector Machine,SVM)、随机森林(Random Forest,RF)和K最近邻(K Nearest Neighbor,KNN)构建小麦倒伏分类模型,明确适宜的分类策略,确立倒伏分类技术路径。[结果和讨论]结果表明,SVM的分类效果整体优于RF和KNN,当影像空间分辨率在1.05~3.26 cm范围内变化时,全特征集和3种优化特征子集均以1.05 cm分辨率的分类精度最高,优于2.09和3.26 cm。比较发现,Boruta-Shap特征优化方法既能实现降维和提高分类精度的目标,又能适应空间分辨率的变化,当影像分辨率为3.26 cm时,总体分类精度相较1.05和2.09 cm分别降低了1.81%和0.75%;当影像分辨率为2.09 cm时,总体分类精度相较1.05 cm降低了1.06%,表现为不同飞行高度下的分类精度相对差异较小,90 m总体分类精度可达到95.6%,Kappa系数达到0.914,满足了对分类精度的需求。[结论]通过选择适宜的特征选择方法,不仅可以兼顾分类精度,还能有效缩小影像空间分辨率变化引起的倒伏分类差异,有助于提升飞行高度,扩大小麦倒伏监测面积,降低作业成本,为确立作物�[Objective] To quickly and accurately assess the situation of crop lodging disasters,it is necessary to promptly obtain information such as the location and area of the lodging occurrences.Currently,there are no corresponding technical standards for identifying crop lodging based on UAV remote sensing,which is not conducive to standardizing the process of obtaining UAV data and proposing solutions to problems.This study aims to explore the impact of different spatial resolution remote sensing images and feature optimization methods on the accuracy of identifying wheat lodging areas.[Methods] Digital orthophoto images(DOM) and digital surface models(DSM) were collected by UAVs with high-resolution sensors at different flight altitudes after wheat lodging.The spatial resolutions of these image data were 1.05,2.09,and 3.26 cm.A full feature set was constructed by extracting 5 spectral features,2 height features,5 vegetation indices,and 40 texture features from the pre-processed data.Then three feature selection methods,ReliefF algorithm,RF-RFE algorithm,and Boruta-Shap algorithm,were used to construct an optimized subset of features at different flight altitudes to select the best feature selection method.The ReliefF algorithm retains features with weights greater than 0.2 by setting a threshold of 0.2;the RF-RFE algorithm quantitatively evaluated the importance of each feature and introduces variables in descending order of importance to determine classification accuracy;the Boruta-Shap algorithm performed feature subset screening on the full feature set and labels a feature as green when its importance score was higher than that of the shaded feature,defining it as an important variable for model construction.Based on the above-mentioned feature subset,an object-oriented classification model on remote sensing images was conducted using eCognition9.0 software.Firstly,after several experiments,the feature parameters for multi-scale segmentation in the object-oriented classification were determined,namely a segmentat

关 键 词：小麦倒伏 无人机 飞行高度 特征选择 分类模型 支持向量机 随机森林 K最近邻 

分 类 号：S512.1[农业科学—作物学] S127