基于无人机多光谱技术的田间烟叶成熟度判别研究

打开文本图片集

中图分类号：S572 文献标志码：A 文章编号：2096-9902（2025）08-0001-05

Abstract：Inordertoacuratelydeterminethematurityoftobaccoleavesinthefieldbasedondronemulti-spectral technology，multi-spectralequipmentmountedbydroneswasusedtocolectdataonthematurityoftobaccoleavesintobacco fieldsatdiferentperiods.SpearmancorrelationanalysisandmRMRmethodwereusedtoscreenoutvegetationindices（RBRI， NDRE，GCI，ARVI）thatweresignificantlyrelatedtotobaccofieldmaturity.Subsequently，basedonthescreeningresults，a diseriminantmodelfortobaccomaturityintobaccofieldswasconstructedusingrandomforestmethodTheresearchresultsshow thatdronemulti-spectraltechnologycanaccuratelycapturethecharacteristicsoftobaccomaturityinthefield.Theaccuracyrates ofthe training set and test set of the discriminant model reach 95.72% and 93.89 % respectively.This research helps accurately graspthebestharvestoportunityoftobacco leaves，improvesthequalityofcuredtobacco leaves，andprovidesnewtechnical support for field agricultural monitoring and precise management.

Keywords：dronemultispectral；vegetationindex；tobaccomaturitydiscrimination；corelationanalysis；randomforest

烟叶的田间成熟度是衡量其生长发育达到可采收状态的综合指标。（剩余6765字）