[1]樊小雪,李德翠,李远,等.基于RGB模型的草莓叶片光合作用指标估测[J].江苏农业学报,2024,(04):675-681.[doi:doi:10.3969/j.issn.1000-4440.2024.04.011]
　FAN Xiao-xue,LI De-cui,LI Yuan,et al.Estimation of photosynthetic indexes in strawberry leaves based on RGB model[J].,2024,(04):675-681.[doi:doi:10.3969/j.issn.1000-4440.2024.04.011]
点击复制

基于RGB模型的草莓叶片光合作用指标估测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年04期
页码:
675-681
栏目:
农业信息工程
出版日期:
2024-04-30

文章信息/Info

Title:
Estimation of photosynthetic indexes in strawberry leaves based on RGB model
作者:
樊小雪1; 2; 李德翠1; 2; 李远1; 2; 任妮1; 2
（1.江苏省农业科学院农业信息研究所,江苏南京210014；2.农业农村部长三角智慧农业技术重点实验室,江苏南京210014）
Author(s):
FAN Xiao-xue1; 2; LI De-cui1; 2; LI Yuan1; 2; REN Ni1; 2
（1.Institute of Agricultural Information, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China；2.Key Laboratory of Smart Agricultural Technology (Yangtze River Delta), Ministry of Agriculture and Rural Affairs, Nanjing 210014, China）
关键词:
草莓叶片; RGB模型; 光合指标; 反向传播（BP）神经网络模型
Keywords:
strawberry leaves; RGB model; photosynthetic index; back propagation (BP) neural network model
分类号:
S668.401
DOI:
doi:10.3969/j.issn.1000-4440.2024.04.011
摘要:
为了研究基于图像红（R）、绿（G）、蓝（B）颜色参数和叶片SPAD值预测光合作用指标的可行性,以草莓叶片为试验材料,构建多元线性回归模型和反向传播（BP）神经网络模型,对叶片蒸腾速率、气孔导度、净光合速率、胞间CO2浓度进行估测,并对其精度进行评价和验证。结果表明,基于BP神经网络模型，使用图像RGB颜色参数和SPAD值对叶片蒸腾速率进行预测的效果较好,其次是气孔导度。BP神经网络模型的估测精度高于多元线性回归模型,蒸腾速率、气孔导度、净光合速率和胞间CO2浓度的模型预测准确率分别达到91.5%、83.3%、74.4%和71.5%。BP神经网络的蒸腾速率模型、气孔导度模型的决定系数（R2）分别为0.922 2、0.842 3,均方根误差（RMSE）分别为0.000 2、0.025 9,平均绝对误差（MAE）分别为0.000 1、0.000 6。由结果可知,通过数码相机采集图像,并构建RGB模型,可简易快速估测草莓叶片蒸腾速率、气孔导度,能用于生产中草莓光合指标的估测。
Abstract:
In order to explore the feasibility of using RGB image feature and SPAD value in photosynthetic indexes prediction, strawberry leaves were selected as experimental materials in this study. Multiple linear regression model and back propagation (BP) neural network model were constructed to estimate leaf transpiration rate, stomatal conductance, net photosynthetic rate and intercellular CO2 concentration, and their accuracy was evaluated and verified. The results showed that the prediction of leaf transpiration rate by using RGB color parameters and SPAD values based on BP neural network model was better, followed by stomatal conductance. The estimation accuracy of BP neural network model was higher than that of multiple linear regression model, and the prediction accuracy of transpiration rate, stomatal conductance, net photosynthetic rate and intercellular CO2 concentration reached 91.5%, 83.3%, 74.4% and 71.5%, respectively. The determination coefficients (R2) of transpiration rate model and stomatal conductance model based on BP neural network were 0.922 2 and 0.842 3, the root mean square errors (RMSE) were 0.000 2 and 0.025 9, and the mean absolute errors (MAE) were 0.000 1 and 0.000 6, respectively. Therefore, the transpiration rate and stomatal conductance of strawberry leaves can be easily and quickly estimated by using digital camera to collect images and construct RGB model, which can be used to predict photosynthetic indexes of strawberry in production.

参考文献/References:

[1]LOU H Q, HU Y, ZHANG L Y, et al. Nondestructive evaluation of the changes of total flavonoid,total phenols,ABTS and DPPH radical scavenging activities,and sugars during mulberry (Morus alba L.) fruits development by chlorophyll fluorescence and RGB intensity values[J]. LWT-Food Science and Technology,2012,47(1):19-24.
[2]李修华,卢显杰,奚金阳,等. 智能手机RGB图像检测植物叶片叶绿素含量的通用方法[J]. 农业工程学报,2021,37(22):145-151.
[3]张沛健,尚秀华,吴志华. 基于图像处理技术的5种红树林叶片形态特征及叶绿素相对含量的估测[J]. 热带作物学报,2020,41(3):496-503.
[4]ZHANG J, WANG R J, XIE C J, et al. Crop pests image recognition based on multi-features fusion[J]. Journal of Computational Information Systems,2014,10(12):5121-5129.
[5]叶春,刘莹,李艳大,等. 基于RGB颜色空间的早稻氮素营养监测研究[J]. 中国农业大学学报,2020,25(8):25-34.
[6]HUMPLK J F, LAZR D, HUSICKOV A, et al. Automated phenotyping of plant shoots using imaging methods for analysis of plant stress responses-a review[J]. Plant Methods,2015,11:29.
[7]王永芳,王克如,王少芬,等. 利用数码相机和成像光谱仪估测棉花叶片叶绿素和氮素含量[J]. 作物学报,2010,36(11):912-915.
[8]史培华,王远,袁政奇,等. 基于冠层RGB图像的冬小麦氮素营养指标监测[J]. 南京农业大学学报,2020,43(5):829-837.
[9]赵阳. 基于番茄叶片图像的叶绿素含量研究[D]. 银川:宁夏大学,2021.
[10]李丽,程灵. 基于RGB模型建立快速检测番茄叶片叶绿素含量的方法[J]. 分子植物育种,2021,19(20):6906-6909.
[11]费丽君,谭峰. 机器视觉技术在大豆叶片叶绿素含量测算上的应用[J]. 农机化研究,2010,32(3):199-201.
[12]徐光辉,虎晓红,熊淑萍,等. 烤烟叶片叶绿素含量与颜色特征的关系[J]. 河南农业大学报,2007,41(6):600-604.
[13]王娟,危常州,王肖娟,等. 采用灰板校正的计算机视觉预测棉花叶绿素含量[J]. 农业工程学报,2013,29(24):173-180.
[14]娄卫东,林宝刚,周洪奎,等. 基于图像特征的油菜叶绿素含量快速估算[J]. 浙江农业科学,2022,63(3):480-484.
[15]龚刚猛,杨珺,何火娇,等. 水稻叶色RGB 组分与SPAD的关系研究[J]. 中国农学通报,2015,31(24):19-24.
[16]GUPUTA S D, IBARAKI Y, PATTANAYAK A K. Development of a digital image analysis method for real-time estimation chlorophyll content in micro propagated potato plants[J]. Plant Biotechnology Reports,2013,7(1):91-97.
[17]程立真,朱西存,高璐璐,等. 基于RGB 模型的苹果叶片叶绿素含量估测[J]. 园艺学报,2017,44(2):381-390.
[18]王诣,闰志勇. 基于图像处理的青冈栎叶绿素含量检测系统研究明[J]. 中国农业科技导报,2017,19(4):59-64.
[19]张若宇,坎杂,马蓉,等. 基于RGB模型的脱绒棉种颜色特征与发芽状况的关系[J]. 农业工程学报,2010,26(10):172-177.
[20]ZHAO K C, YE Y, MA J, et al. Dynamic variation characteristics of rice nitrogen status after anthesis based on the RGB color index[J]. Agronomy,2021,11(9):1739.
[21]SONG Y F, TENG G F, YUAN Y C, et al. Assessment of wheat chlorophyll content by the multiple linear regression of leaf image features[J]. Information Processing in Agriculture,2021,8(2):232-243.
[22]RICCARDI M， MELE G， PULVENTO C， et al. Non-destructive evaluation of chlorophyll content in quinoa and amaranth leaves by simple and multiple regression analysis of RGB image components[J]. Photosynthesis Research，2014，120(3)：263-272.
[23]TAVAKOLI H, GEBBERS R. Assessing nitrogen and water status of winter wheat using a digital camera[J]. Computers and Electronics in Agriculture,2019,157:558-567.
[24]张佩,陈郑盟,刘春伟,等. 冬小麦产量结构要素预报方法[J]. 农业工程学报,2020,36(8):78-87.
[25]BIAN Z H, YANG Q C, LI T, et al. Study of the beneficial effects of green light on lettuce grown under short-term continuous red and blue light-emitting diodes[J].Physiologia Plantarum,2018,164(2):226-240.

备注/Memo

备注/Memo:
收稿日期:2023-03-07基金项目:江苏省农业科技自主创新基金项目[CX(22)5007]作者简介:樊小雪（1983-）,女,山东淄博人,博士,副研究员,研究方向为蔬菜栽培生长调控及相关机理模型。（Tel）025-84391912；(E-mail)fxx@jaas.ac.cn通讯作者:任妮,（Tel）025-84391658；(E-mail)rn@jaas.ac.cn
更新日期/Last Update: 2024-05-22