首页|期刊导航|智慧农业(中英文)|基于无人机多光谱图像和VGG21模型的小麦渍害调控效果识别方法

基于无人机多光谱图像和VGG21模型的小麦渍害调控效果识别方法OA

Recognition of Wheat Waterlogging Stress and Regulation Effect Based on UAV Multispectral Images and VGG21 Model

中文摘要英文摘要

[目的/意义]为实现科学、精准的小麦渍害防控,提高小麦产量,本研究提出一个快速、准确、无损的小麦渍水胁迫和调控效果识别方法.[方法]在小麦拔节-抽穗和抽穗-灌浆两个生长阶段进行对照、渍水胁迫、硅肥调控和氨基酸调控控制试验.试验期间,利用大疆精灵4多光谱无人机采集小麦冠层多光谱图像.试验结束对各处理测产,并利用产量指标评估调控效果.多光谱图像经过预处理,分类整理后建立包含对照、渍水胁迫、硅肥调控、氨基酸调控4个类别的数据集.采用分层抽样方法对数据集划分,即每个类别分别按7:1.5:1.5的比例随机划分为训练、验证和测试集.以VGG(Visual Geometry Group)19模型为基础,通过增加卷积层、调整卷积块和卷积层数、更换激活函数及优化模型超参等方法建立VGG21小麦渍水胁迫和调控效果识别模型.[结果和讨论]与ResNet(Residual Network)50和Swin-Transformer(Shifted Window Transformer)模型对比结果表明,VGG模型在多光谱图像数据识别方面性能更好,其中VGG21综合性能最突出.模型识别性能综合分析结果表明,VGG21模型对硅肥调控和胁迫的识别正确率达到91%以上,对硅肥调控样本的识别精度、召回率和F1分别达到96.42%、89.53%和92.85%.硅肥调控和胁迫识别模型用于氨基酸调控样本识别,识别正确率、精度等各项指标与构建的氨基酸调控和胁迫识别模型性能相当.利用VGG21构建的对照、胁迫和硅肥调控多分类识别模型,对调控样本的识别精度、召回率和F1分别达到95.13%、88.71%和91.80%.对比模型识别性能与产量评估的调控效果发现:硅肥调控效果较好,调控后的小麦光谱和图像特征显著,识别精度最高.[结论]基于无人机多光谱图像和VGG21模型构建的小麦渍水胁迫和调控效果识别模型,对调控效果较好的硅肥调控样本识别性能最好,具有很好的鲁棒性和可扩展性.此项技术可为小麦渍害综合防控,及小麦精细化、智能化管理提供理论和技术支持.

[Objective]In recent years,global warming and increasingly frequent extreme precipitation events have intensified waterlog-ging stress in agriculture,establishing it as a major abiotic threat to food security.To achieve scientific and precise control of wheat wa-terlogging disaster and increase yield,a rapid,accurate,and non-destructive method for identifying wheat waterlogging stress and reg-ulation effect was proposed.[Methods]Field trials of control(CK),waterlogging stress,silicon-fertilizer regulation,and amino-acid regulation were conducted during the jointing-booting and flowering-filling stages of wheat.During the experiments,unmanned aerial vehicle(UAV)multispectral images of the wheat canopy were collected using DJI P4 Multispectral.The multispectral image had five bands,namely blue(B),green(G),red(R),red-edge(RE)and near-infrared(NIR),with reflectivity values of(450±16),(560±16),(650±16),(730±16),and(840±26)nm,respectively.At the end of the experiments,grain yield was measured for each treatment and used to evaluate the effectiveness of the regulation measures.The multispectral images were processed,which included radiometric correction,geometric correction,image alignment,segmentation,etc.Then a dataset was established that includes four categories:CK,waterlogging stress,silicon fertilizer regulation,and amino acid regulation.The stratified sampling was used for dataset partition-ing.According to the ratio of 7:1.5:1.5,all original multispectral images of each category were randomly divided into the training,val-idation and testing set,respectively.Then,the original images were segmented into data blocks of 48×48 pixel size for model training and testing.A wheat waterlogging stress and regulation effect recognition model using visual geometry group(VGG)21 was estab-lished by adding convolutional layers,adjusting the convolutional layers of convolutional block,replacing activation functions,and optimizing model hyperparameters based on VGG19.The VGG21 model included 4 convolutional blocks and the convolutional layers were 3,3,6,and 6,respectively.To verify the performance of the VGG21 model,the accuracy,precision,recall and F1-Score of the ResNet50,Swin-Transformer,VGG19,VGG21,and VGG23 models were compared under the same conditions,and the confusion ma-trix and Grad-CAM(Gradient-Weighted Class Activation Mapping)were employed to evaluate the CK,waterlogging stress,and sili-con fertilizer regulation model.[Results and Discussions]The performance comparison results showed that the VGG model performed better on multispectral image data recognition than the ResNet50 and Swin-Transformer model,and the VGG21 model demonstrated the most favorable overall performance.The comprehensive analysis of model recognition performance showed that the accuracy of the VGG21 model was more than 91%for silicon fertilizer regulation and waterlogging stress.And the precision,recall,and F1-Score for silicon fertilizer regulation samples reached 96.42%,89.53%,and 92.85%,respectively.When the silicon fertilizer regulation and stress recognition model was used for amino acid regulation sample identification,the accuracy,precision,recall,F1-Score were com-parable to the amino acid regulation and stress recognition model.A recognition model for CK,waterlogging stress,and silicon fertil-izer regulation was constructed using VGG21,and the precision,recall,and F1-Score for silicon fertilizer regulated samples achieved 95.13%,88.71%,and 91.80%,respectively.The confusion matrix of the CK,waterlogging stress,and silicon fertilizer regulation mod-el indicated that there was a high proportion of misclassifications between CK and waterlogging stress samples,resulting in a low ac-curacy of model,which only reached 77.45%.The heatmap analysis results of the CK,waterlogging stress,and silicon fertilizer regu-lation model indicated that after passing through the fourth convolutional block,the concentrated regions of the output features for misclassified CK and waterlogging stress samples became more dispersed,and even disappear.The CK and waterlogging stress sam-ples with unfocused region heatmap accounted for a large proportion in the dataset,which led to poor recognition of these two types of samples by the regulation model.The comparison between recognition results of VGG21 model and the yield of regulation experi-ment showed that the silicon fertilizer had a better regulation effect,and the wheat regulated by silicon fertilizer had significant spec-tral and image features with high recognition accuracy.[Conclusions]The results demonstrated that UAV multispectral imaging tech-nology and VGG21 model were feasible and useful for recognizing waterlogging stress and the regulatory effect of wheat.This tech-nique could provide theory and technical support for integrated waterlogging management of wheat and for refined,intelligent wheat production management.However,the quantitative relationship between the identification results of regulation effect and yield was still unclear.In future research,it will be necessary to quantify the increased yield of regulation measures,and then use statistical methods to quantify the quantitative relationship between the yield-increasing regulation effect and identification indicators of recogni-tion model.

梁万杰;刘晓君;吴茜;孙传亮;雷添杰;徐得泽;郑兴飞;朱广龙;汤泉

江苏省农业科学院农业信息研究所,江苏 南京 210014,中国||南京信息工程大学生态与应用气象学院,江苏 南京 210044,中国江苏省农业科学院农业信息研究所,江苏 南京 210014,中国||南京信息工程大学生态与应用气象学院,江苏 南京 210044,中国江苏省农业科学院农业信息研究所,江苏 南京 210014,中国江苏省农业科学院农业信息研究所,江苏 南京 210014,中国中国农业科学院农业环境与可持续发展研究所,北京 100081,中国湖北省农业科学院粮食作物研究所,湖北 武汉 430064,中国湖北省农业科学院粮食作物研究所,湖北 武汉 430064,中国扬州大学教育部农业与农产品安全国际合作联合实验室,江苏 扬州 225009,中国江苏省农业科学院农业信息研究所,江苏 南京 210014,中国

农业科技

小麦渍水胁迫渍害调控无人机多光谱图像深度学习视觉几何组模型

wheat waterlogging stressregulation and control of waterloggingunmanned aerial vehiclemultispectral imagesdeep learningvisual geometry group model

《智慧农业(中英文)》 2026 (4)

60-69,10

国家重点研发计划项目(2023YFD2300300)江苏省重点研发计划项目(BE2023302) National Key R&D Program(2023YFD2300300)Key Research and Development Program of Jiangsu Province(Modern Agriculture)(BE2023302)

10.12133/j.smartag.SA202601017

评论