| 注册
首页|期刊导航|农机化研究|基于多光谱成像技术的玉米氮素营养诊断方法研究

基于多光谱成像技术的玉米氮素营养诊断方法研究

刘奕彤 宋玉柱 马昕宇 郭思琪 冯江 王树文

农机化研究2018,Vol.40Issue(2):148-153,6.
农机化研究2018,Vol.40Issue(2):148-153,6.

基于多光谱成像技术的玉米氮素营养诊断方法研究

Research on Nutrition Diagnosis Method of Maize Nitrogen Based on Multispectral Imaging Technique

刘奕彤 1宋玉柱 1马昕宇 1郭思琪 1冯江 1王树文1

作者信息

  • 1. 东北农业大学 电气与信息学院,哈尔滨 150030
  • 折叠

摘要

Abstract

In order to rapidly acquire maize nutrient information in the field, a non-destructive method of maize nitrogen content index measurement was conducted based on multispectral imaging technique.Firstly, American ADC multi-spectral image monitoring system was available to acquire the canopy images of maize in jointing stage.At the same time, each sample was measured to show the nitrogen content index by AA3 continuous flow analyzer.Secondly, eleven vegetation indices were calculated including AVSR, AVSG, AVSNIR, NDVI, GNDVI, RVIR/G, RVIR/NIR, RVINIR/R, RNR, GNR and NIRNR.And then the method of correlation analysis was used to reduce the dimension of data so as to acquire three sensitive spectral characteristic parameters.Lastly, the nitrogen index detecting model based on simple linear regression method, polynomial regression method and multiple regression method by stepwise regression.The results indicated that, the maximal R2 of simple regression models is 0.854 and the R2 of multiple regression model is 0.870.It was feasible to diagnose nitrogen content of maize based on multi-spectral images.

关键词

玉米/氮素/多光谱图像/定量监测

Key words

maize/nitrogen/multi-spectral image/quantitative monitoring

分类

农业科技

引用本文复制引用

刘奕彤,宋玉柱,马昕宇,郭思琪,冯江,王树文..基于多光谱成像技术的玉米氮素营养诊断方法研究[J].农机化研究,2018,40(2):148-153,6.

基金项目

国家"863计划"项目(AA2013102303) (AA2013102303)

黑龙江省自然科学基金面上项目(C2015006) (C2015006)

哈尔滨市科技创新人才项目(2015RQQXJ020) (2015RQQXJ020)

农机化研究

OA北大核心

1003-188X

访问量0
|
下载量0
段落导航相关论文