无人机高光谱成像技术在作物生长信息监测中的应用  

Application of UAV hyperspectral imaging technology in crop growth information monitoring

作　　者：姜妍[1] 王琳 杨月 蔡雨彤 张喜海[2] 王惠中 王绍东[1] JIANG Yan;WANG Lin;YANG Yue;CAI Yutong;ZHANG Xihai;WANG Huizhong;WANG Shaodong(School of Agriculture/National Soybean Engineering Technology Research Center,Northeast Agricultural University,Harbin 150030,China;School of Electrical and Information,Northeast Agricultural University,Harbin 150030,China;School of Life Science,Northeast Agricultural University,Harbin 150030,China)

机构地区：[1]东北农业大学农学院/国家大豆工程技术研究中心,哈尔滨150030 [2]东北农业大学电气与信息学院,哈尔滨150030 [3]东北农业大学生命科学学院,哈尔滨150030

出　　处：《东北农业大学学报》2022年第3期88-96,共9页Journal of Northeast Agricultural University

基　　金：国家现代农业技术产业体系(CARS-04-PS06);国家重点研发计划(2021YFD1201103-01-04)。

摘　　要：随着高效精准无损检测技术发展与应用,精准农业发展趋势明显,高光谱遥感作为该领域前沿技术,应用广泛。高光谱成像(Hyperspectral imaging,HSI)技术具有波段多、光谱窄、数据量大优点,利用光谱特征研究作物生长信息、各种光谱模型及精细分类和识别。文章重点论述近5年国内外HSI技术在无人机(Unmanned aerial system,UAS)遥感系统中对作物生长信息快速无损检测应用的研究进展,通过数据集扩充与注释、最佳波段组合和利用,配合反演方案开发与训练,以及精确图像处理技术评估作物氮素营养、生物量和产量、病害或胁迫、表型及植物功能特征等生长信息,该技术精准快速反映农业生产中许多具体问题,为现代化精细化农业发展提供有力保障。With the development and application of efficient and accurate nondestructive testing technology, the trend of precision agriculture replacing traditional agriculture is becoming more and more obvious. Hyperspectral remote sensing has become a cutting-edge technology in the current field with a wide range of applications. Hyperspectral imaging(HSI) technology has the advantages of multi band, narrow spectrum and large amount of data. It is conducive to the use of spectral feature analysis to study crop growth information, various spectral models, fine classification and recognition. The application of HSI technology at home and abroad was focused on the rapid and nondestructive detection of crop growth information in unmanned aerial system(UAS) remote sensing system in recent five years. Through the expansion and annotation of data set, the combination and utilization of optimal wave band, the development and training of inversion scheme, and accurate image processing technology, crop growth information such as nitrogen nutrition, biomass and yield disease or stress,phenotype and plant functional characteristics were evaluated accurately and quickly, which reflected the specific problems in agricultural production. A strong guarantee for the development of modern fine agriculture was provided.

关 键 词：HSI UAS 植物表型 功能特性 机器算法 

分 类 号：S126[农业科学—农业基础科学]