[1]葛春雨,唐雪海,孔令瑗,等.基于无人机高光谱的长林系列油茶品种的识别[J].江苏农业学报,2026,42(02):337-348.[doi:doi:10.3969/j.issn.1000-4440.2026.02.012]
　GE Chunyu,TANG Xuehai,KONG Lingyuan,et al.Identification of Changlin series Camellia oleifera cultivars using UAV-based hyperspectral remote sensing[J].,2026,42(02):337-348.[doi:doi:10.3969/j.issn.1000-4440.2026.02.012]
点击复制

基于无人机高光谱的长林系列油茶品种的识别()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
42
期数:
2026年02期
页码:
337-348
栏目:
农业信息工程
出版日期:
2026-02-28

文章信息/Info

Title:
Identification of Changlin series Camellia oleifera cultivars using UAV-based hyperspectral remote sensing
作者:
葛春雨1; 2; 唐雪海1; 2; 孔令瑗1; 2; 汪春霞1; 2; 王佩1; 2
(1.安徽农业大学林学与园林学院,安徽合肥230036；2.安徽省林木资源培育重点实验室,安徽合肥230036)
Author(s):
GE Chunyu1; 2; TANG Xuehai1; 2;  KONG Lingyuan1; 2; WANG Chunxia1; 2; WANG Pei1; 2
(1.School of Forestry and Landscape Architecture, Anhui Agricultural University, Hefei 230036, China;2.Anhui Provincial Key Laboratory of Forest Resources and Silviculture, Hefei 230036, China)
关键词:
油茶; 无人机; 高光谱; 品种识别; 机器学习
Keywords:
Camellia oleifera; unmanned aerial vehicle; hyperspectral; cultivar identification; machine learning
分类号:
O657.3
DOI:
doi:10.3969/j.issn.1000-4440.2026.02.012
文献标志码:
A
摘要:
油茶是中国重要的木本油料树种之一,快速、准确地识别不同油茶品种,对油茶的合理种植、产量提升具有重要意义。本研究以长林系列油茶的5个品种(27号、40号、4号、53号、166号)作为研究对象,首先利用无人机搭载高光谱传感器获取试验样株的光谱图像；其次,采用标准正态变量变换(SNV)、标准正态变量变换结合去趋势(SNVDT)、标准正态变量变换结合一阶导数(SNVFD)、Savitzky-Golay卷积平滑(SG)、Savitzky-Golay卷积平滑结合一阶导数(SGFD)5种方式进行光谱预处理,进一步采取全波段、结合3种特征处理方式[递归特征消除(RFE)、偏最小二乘法(PLS)、连续投影算法(SPA)]筛选的特征波段；最后,构建线性判别模型(LDA)、人工神经网络模型(ANN)、支持向量机模型(SVM)3种分类模型的品种最优识别模型。结果表明,以全波段为变量构建分类模型的最佳组合是SGFD-ANN,分类准确率和Kappa系数分别达到92.22%、0.90。联合特征处理的最佳组合是SNVDT-RFE-SVM,准确率和Kappa系数提升至94.44%、0.93。5个品种中,对长林166号和长林4号油茶的识别结果最优。本研究结果可为油茶林精准识别与种植经营提供理论依据,也为其他经济林树种的精细分类提供参考。
Abstract:
Camellia oleifera is a key woody oil-producing tree in China. The rapid and accurate identification of different Camellia oleifera cultivars is of great significance for their rational cultivation and yield improvement. This study focused on five cultivars of the Changlin series Camellia oleifera (No.27, No.40, No.4, No.53, and No.166) as the research subjects. First, spectral images of the experimental sample plants were acquired using a UAV-mounted hyperspectral sensor. Subsequently, five spectral preprocessing methods were applied: standard normal variate (SNV), SNV combined with detrending (SNVDT), SNV combined with first derivative (SNVFD), Savitzky-Golay convolution smoothing (SG), and SG combined with first derivative (SGFD). Furthermore, feature bands were selected based on the full wavelength range and in combination with three feature processing methods: recursive feature elimination (RFE), partial least squares (PLS), and successive projections algorithm (SPA). Finally, linear discriminant analysis (LDA), artificial neural network (ANN), and support vector machine (SVM) were constructed to develop the optimal identification model for the cultivars. The results showed that the optimal combination for constructing a classification model using full-band data was SGFD-ANN, achieving a classification accuracy of 92.22% and a Kappa coefficient of 0.90. The optimal combination that involved feature processing was SNVDT-RFE-SVM, which increased the classification accuracy and Kappa coefficient to 94.44% and 0.93, respectively. Among the five cultivars, Changlin 166 and Changlin 4 showed the most accurate identification results. These findings provide a theoretical basis for the precise identification and cultivation management of oil-tea camellia forests, and also offer a reference for the fine classification of other economic forest tree species.

参考文献/References:

[1]罗汉东,王华,付艳秋,等. 油茶果实性状、养分含量和产油量对磷水平的响应[J]. 江苏农业学报,2016,32(4):898-903.
[2]唐雪海,燕李鹏,傅根深,等. 基于机器学习的油茶叶片钾含量估算模型构建[J]. 中国油料作物学报,2025,47(2):488-501.
[3]孟桂元,韩杰铖,詹兴国,等. 我国油茶产业分析与发展对策[J]. 中国油脂,2021,46(7):104-108,113.
[4]王金凤,谭新建,吴喜昌,等. 我国油茶产业发展现状与对策建议[J]. 世界林业研究,2020,33(6):80-85.
[5]李婕,李毅,张瑞杰,等. 无人机遥感影像在油菜品种识别中的应用[J]. 江苏农业学报,2022,38(3):675-684.
[6]LI Y S, CHANG C Y, WANG Z R, et al. Identification of cultivated land quality grade using fused multi-source data and multi-temporal crop remote sensing information[J]. Remote Sensing,2022,14(9):2109.
[7]周湘山,杨武年,罗可,等. 基于机器学习算法和空间分辨率调整的无人机高光谱树种分类研究[J]. 遥感技术与应用,2024,39(4):880-896.
[8]宋恩泽,张颖,邵光成,等. 基于无人机多光谱遥感的农业园区地物分类研究[J]. 江苏农业学报,2023,39(9):1862-1871.
[9]WU H B, ZHOU H M, WANG A L, et al. Precise crop classification of hyperspectral images using multi-branch feature fusion and dilation-based MLP[J]. Remote Sensing,2022,14(11):2713.
[10]肖斌,何宏昌,窦世卿,等. UAV高光谱影像联合SULOV＿XGBoost算法的柑橘果树精细分类方法[J]. 光谱学与光谱分析,2024,44(2):548-557.
[11]高峰,邢雅阁,罗华平,等. 基于可见/近红外光谱与化学计量学的杏品种无损鉴别方法[J]. 光谱学与光谱分析,2024,44(1):44-51.
[12]WU H R, SONG Z Y, NIU X Y, et al. Classification of Toona sinensis young leaves using machine learning and UAV-borne hyperspectral imagery[J]. Frontiers in Plant Science,2022,13:940327.
[13]居雷,于洁,吴炎淼,等. 高光谱预处理方法与多模型在分类判别中的对比研究[J]. 光谱学与光谱分析,2025,45(1):125-132.
[14]SETHY P K, BARPANDA N K, RATH A K, et al. Deep feature based rice leaf disease identification using support vector machine[J]. Computers and Electronics in Agriculture,2020,175:105527.
[15]FURLANETTO R H, MORIWAKI T, FALCIONI R, et al. Hyperspectral reflectance imaging to classify lettuce varieties by optimum selected wavelengths and linear discriminant analysis[J]. Remote Sensing Applications:Society and Environment,2020,20:100400.
[16]OLANIYI E, KUCHA C, DAHIYA P, et al. Precision variety identification of shelled and in-shell pecans using hyperspectral imaging with machine learning[J]. Infrared Physics & Technology,2024,142:105570.
[17]吴永清,李明,贺媛媛,等. 基于高光谱成像技术的小麦籽粒品种鉴别方法研究[J]. 中国粮油学报,2021,36(4):133-138.
[18]张红涛,张亮,谭联,等. 基于近红外高光谱成像的单籽粒小麦品种分类研究[J]. 粮食与油脂,2022,35(12):59-62.
[19]李国厚,李泽旭,金松林,等. 混合卷积神经网络用于高光谱小麦品种鉴别[J]. 光谱学与光谱分析,2024,44(3):807-813.
[20]杜洋文,程军勇,邓先珍,等. 油茶不同品种树冠内外果实性状差异及综合评价[J]. 森林与环境学报,2022,42(6):655-662.
[21]曹永庆,王开良,汪舍平,等. 基于叶片表型和矿质元素含量特征的油茶品种判别分析[J]. 中国农学通报,2024,40(19):12-18.
[22]TANG X Y, JIANG Y, GUAN J H, et al. Characterization and discrimination of Camellia oil varieties according to fatty acid,squalene,tocopherol,and volatile substance contents by chromatography and chemometrics[J]. European Food Research and Technology,2024,250(1):151-165.
[23]毛英伍,郭颖,张王菲,等. 联合LiDAR、高光谱数据及3D-CNN方法的树种分类[J]. 林业科学,2023,59(3):73-83.
[24]姜玉峰,齐建国,陈博伟,等. 基于无人机高光谱影像和机器学习的红树林树种精细分类[J]. 遥感技术与应用,2021,36(6):1416-1424.
[25]曹永庆,姚小华,任华东,等. 不同油茶品种冠层光合有效辐射和结实特性分析[J]. 经济林研究,2020,38(4):17-21,51.
[26]WANG C, LUO X, GUO Z M, et al. Influence of the peel on online detecting soluble solids content of pomelo using Vis-NIR spectroscopy coupled with chemometric analysis[J]. Food Control,2025,167:110777.
[27]JOHN R, BARTWAL A, JEYASEELAN C, et al. Rice bean-adzuki bean multitrait near infrared reflectance spectroscopy prediction model:a rapid mining tool for trait-specific germplasm[J]. Frontiers in Nutrition,2023,10:1224955.
[28]袁伟东,鞠皓,姜洪喆,等. 基于高光谱成像技术的油茶果不同成熟阶段判别[J]. 光谱学与光谱分析,2023,43(11):3419-3426.
[29]KUANG L L, TIAN X C, SU Y, et al. Rapid identification of horse oil adulteration based on deep learning infrared spectroscopy detection method[J]. Spectrochimica Acta Part A:Molecular and Biomolecular Spectroscopy,2025,330:125604.
[30]吴双,涂斌,郑晓,等. 基于特征波长提取的激光近红外光谱快速鉴别食用植物油种类[J]. 中国油脂,2017,42(4):72-75.
[31]蒲姗姗,郑恩让,陈蓓. 基于1D-CNN的近红外光谱分类算法研究[J]. 光谱学与光谱分析,2023,43(8):2446-2451.
[32]ZHU S S, ZHOU L, GAO P, et al. Near-infrared hyperspectral imaging combined with deep learning to identify cotton seed varieties[J]. Molecules,2019,24(18):3268.
[33]孙一丹,杨晓楠,张海涛,等. 基于无人机高光谱遥感的太行山经济林树种识别研究[J]. 林业与生态科学,2024,39(2):123-133.

相似文献/References:

[1]佚名 佚名 佚名.三才期刊采编系统文章正在整理中…[J].江苏农业学报,2005,(01):61.
　XU De Bing,CHEN Fu,ZHANG Lin tao,et al.三才期刊采编系统文章正在整理中…[J].,2005,(02):61.
[2]佚名 佚名 佚名.三才期刊采编系统文章正在整理中…[J].江苏农业学报,2006,(01):61.
　XU De Bing,CHEN Fu,ZHANG Lin tao,et al.三才期刊采编系统文章正在整理中…[J].,2006,(02):61.
[3]罗汉东,王华,付艳秋,等.油茶果实性状、养分含量和产油量对磷水平的响应[J].江苏农业学报,2016,(04):898.[doi:10.3969/j.issn.100-4440.2016.04.029]
　LUO Han-dong,WANG Hua,FU Yan-qiu,et al.Fruit traits, nutrient content and oil content of Camellia oleifera in response to phosphorus levels[J].,2016,(02):898.[doi:10.3969/j.issn.100-4440.2016.04.029]
[4]于堃,单捷,王志明,等.无人机遥感技术在小尺度土地利用现状动态监测中的应用[J].江苏农业学报,2019,(04):853.[doi:doi:10.3969/j.issn.1000-4440.2019.04.015]
　YU Kun,SHAN Jie,WANG Zhi ming,et al.Land use status monitoring in small scale by unmanned aerial vehicles (UAVs) observations[J].,2019,(02):853.[doi:doi:10.3969/j.issn.1000-4440.2019.04.015]
[5]陶惠林,冯海宽,徐良骥,等.基于无人机高光谱遥感数据的冬小麦生物量估算[J].江苏农业学报,2020,(05):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
　TAO Hui-lin,FENG Hai-kuan,XU Liang-ji,et al.Winter wheat biomass estimation based on hyperspectral remote sensing data of unmanned aerial vehicle(UAV)[J].,2020,(02):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
[6]张先洁,孙国祥,汪小旵,等.基于超像素特征向量的果树冠层分割方法[J].江苏农业学报,2021,(03):724.[doi:doi:10.3969/j.issn.1000-4440.2021.03.023]
　ZHANG Xian-jie,SUN Guo-xiang,WANG Xiao-chan,et al.Segmentation method of fruit tree canopy based on super pixel feature vector[J].,2021,(02):724.[doi:doi:10.3969/j.issn.1000-4440.2021.03.023]
[7]郭松,常庆瑞,郑智康,等.基于无人机高光谱影像的玉米叶绿素含量估测[J].江苏农业学报,2022,38(04):976.[doi:doi:10.3969/j.issn.1000-4440.2022.04.014]
　GUO Song,CHANG Qing-rui,ZHENG Zhi-kang,et al.Estimation of maize chlorophyll content based on unmanned aerial vehicle (UAV) hyperspectral images[J].,2022,38(02):976.[doi:doi:10.3969/j.issn.1000-4440.2022.04.014]
[8]龚志远,李雪梅,李秋萍,等.兰州植物园植被春季物候无人机监测[J].江苏农业学报,2023,(08):1707.[doi:doi:10.3969/j.issn.1000-4440.2023.08.010]
　GONG Zhi-yuan,LI Xue-mei,LI Qiu-ping,et al.Unmanned aerial vehicle (UAV) monitoring of spring vegetation phenology in Lanzhou Botanical Garden[J].,2023,(02):1707.[doi:doi:10.3969/j.issn.1000-4440.2023.08.010]
[9]李瑞鑫,张宝林,潘丽杰,等.不同无人机飞行高度下玉米叶片叶绿素相对含量的无人机遥感反演及其指示叶位的识别[J].江苏农业学报,2024,(07):1234.[doi:doi:10.3969/j.issn.1000-4440.2024.07.010]
　LI Ruixin,ZHANG Baolin,PAN Lijie,et al.Unmanned aerial vehicle remote sensing inversion of relative chlorophyll content of maize leaves and identification of their indicator leaf at different flight altitudes[J].,2024,(02):1234.[doi:doi:10.3969/j.issn.1000-4440.2024.07.010]
[10]王江英,葛金涛,邵小斌,等.筛选白花油茶胚性愈伤组织诱导成苗的关键激素通路及相关基因[J].江苏农业学报,2025,(03):599.[doi:doi:10.3969/j.issn.1000-4440.2025.03.019]
　WANG Jiangying,GE Jintao,SHAO Xiaobin,et al.Screening of key hormone pathways and related genes for the induction of plantlets from embryogenic callus of Camellia oleifera[J].,2025,(02):599.[doi:doi:10.3969/j.issn.1000-4440.2025.03.019]

备注/Memo

备注/Memo:
收稿日期：2025-05-14基金项目：安徽省教育厅科研项目——重大项目(2024AH040081)；国家自然科学基金项目(32171783)作者简介：葛春雨(2001-),女,贵州贵阳人,硕士研究生,主要从事林业定量遥感研究。(E-mail)chunyuge@stu.ahau.edu.cn通讯作者：唐雪海,(E-mail)tangxuehai@ahau.edu.cn
更新日期/Last Update: 2026-03-16