[1]杜海顺,安文昊,张春海,等.基于综合判别特征学习和中层特征监督的农作物病害识别[J].江苏农业科学,2025,53(14):208-216.
 Du Haishun,et al.Recognition of crop disease based on comprehensive discriminant feature learning and middle feature supervision[J].Jiangsu Agricultural Sciences,2025,53(14):208-216.
点击复制

基于综合判别特征学习和中层特征监督的农作物病害识别()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第53卷
期数:
2025年第14期
页码:
208-216
栏目:
农业工程与信息技术
出版日期:
2025-07-20

文章信息/Info

Title:
Recognition of crop disease based on comprehensive discriminant feature learning and middle feature supervision
作者:
杜海顺12安文昊1张春海1周毅12
1.河南大学人工智能学院,河南郑州 450046; 2.河南省车联网协同技术国际联合实验室,河南郑州 450046
Author(s):
Du Haishunet al
关键词:
农作物病害识别综合判别特征学习中层特征监督卷积神经网络
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
准确识别农作物病害有助于提高农作物的产量和质量,促进农业的可持续发展。大多数基于深度神经网络的农作物病害识别方法没有充分利用网络不同层次的特征对病害进行综合分析,且对病害的细节信息关注不足。为了有效利用深度神经网络提取的不同层次的特征来更准确地识别农作物病害,提出了一种基于综合判别特征学习和中层特征监督的农作物病害识别网络。具体地,该网络由1个主干ResNet50、1个综合判别特征学习模块以及1个中层特征监督分支组成。其中,主干ResNet50负责提取农作物病害图像的浅层、中层以及深层特征;综合判别特征学习模块通过对主干ResNet50提取的不同层次的特征进行分析与综合,得到综合判别特征;中层特征监督分支用于确保含有丰富细节信息的中层特征的判别力。在公共农作物病害数据集AI challenger 2018和Cassava以及自制农作物病害数据集RCP-Crops上,所提出网络识别准确率分别达89.76%、87.95%、98.19%,F1分数分别达89.57%、8777%、98.18%。
Abstract:
-

参考文献/References:

[1]曾伟辉,李淼,李增,等. 基于高阶残差和参数共享反馈卷积神经网络的农作物病害识别[J]. 电子学报,2019,47(9):1979-1986.
[2]郭小燕,于帅卿,沈航驰,等. 基于全局特征提取的农作物病害识别模型 [J]. 农业机械学报,2022,53(12):301-307,379.
[3]李淼,王敬贤,李华龙,等. 基于CNN和迁移学习的农作物病害识别方法研究[J]. 智慧农业,2019,1(3):46-55.
[4]鲍文霞,孙庆,胡根生,等. 基于多路卷积神经网络的大田小麦赤霉病图像识别[J]. 农业工程学报,2020,36(11):174-181.
[5]叶中华,赵明霞,贾璐. 复杂背景农作物病害图像识别研究[J]. 农业机械学报,2021,52(增刊1):118-124,147.
[6]张净,李进,刘晓梅. 基于多尺度注意力残差网络MSA-ResNet的农作物病害识别[J]. 软件导刊,2023,22(4):148-155.
[7]杜甜甜,南新元,黄家興,等. 改进RegNet识别多种农作物病害受害程度[J]. 农业工程学报,2022,38(15):150-158.
[8]龚安,井晓萌. 多卷积神经网络模型融合的农作物病害图像识别[J]. 计算机技术与发展,2020,30(8):134-139.
[9]李昊,王斌. 深度特征融合方法及其在叶片病害识别中的应用[J]. 计算机系统应用,2022,31(7):349-355.
[10]孙俊,朱伟栋,罗元秋,等. 基于改进MobileNet v2的田间农作物叶片病害识别[J]. 农业工程学报,2021,37(22):161-169.
[11]温长吉,王启锐,陈洪锐,等. 面向大规模多类别的病虫害识别模型[J]. 农业工程学报,2022,38(8):169-177.
[12]宋余庆,谢熹,刘哲,等. 基于多层EESP深度学习模型的农作物病虫害识别方法[J]. 农业机械学报,2020,51(8):196-202.
[13]Zhao Y,Sun C,Xu X,et al. RIC-Net:a plant disease classification model based on the fusion of Inception and residual structure and embedded attention mechanism[J]. Computers and Electronics in Agriculture,2022,193:106644.
[14]Lin S,Xiu Y C,Kong J L,et al. An effective pyramid neural network based on graph-related attentions structure for fine-grained disease and pest identification in intelligent agriculture[J]. Agriculture,2023,13(3):567.
[15]杜海顺,张春海,安文昊,等. 基于多层信息融合和显著性特征增强的农作物病害识别[J]. 农业机械学报,2023,54(7):214-222.
[16]王昌龙,张远东,缪宏,等. 双通道卷积神经网络在南瓜病害识别上的应用[J]. 计算机工程与应用,2021,57(5):183-189.
[17]王等准,李飞,严春雨,等. 基于多尺度特征融合的轻量化苹果叶部病理识别[J]. 激光与光电子学进展,2023,60(2):89-97.
[18]张红旗,刘宇,王春光. 改进田间杂草识别图像预处理方法的研究[J]. 农机化研究,2015,37(6):70-73.
[19]Roy A,Bhaduri J. A deep learning enabled multi-class plant disease detection model based on computer vision[J]. AI,2021,2(3):413-428.
[20]He K M,Zhang X Y,Ren S Q,et al. Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,2016:770-778.
[21]Shi X J,Chen Z R,Wang H,et al. Convolutional LSTM network:a machine learning approach for precipitation nowcasting[J]. Advances in Neural Information Processing Systems,2015:802-810.
[22]Huang S L,Wang X C,Tao D C. Stochastic partial swap:enhanced model generalization and interpretability for fine-grained recognition[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal,2021:600-609.
[23]张家瑜,朱锐,邱威,等. 基于选择性注意力神经网络的木薯叶病害检测算法[J]. 农业机械学报,2024,55(5):254-262,272.
[24]Geetharamani G,Arun Pandian J. Identification of plant leaf diseases using a nine-layer deep convolutional neural network[J]. Computers & Electrical Engineering,2019,76:323-338.
[25]Deng J,Dong W,Socher R,et al. ImageNet:a large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition.Miami,2009:248-255.
[26]Liu Z,Mao H Z,Wu C Y,et al. A ConvNet for the 2020s[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).New Orleans,2022:11966-11976.
[27]王东方,汪军. 基于迁移学习和残差网络的农作物病害分类[J]. 农业工程学报,2021,37(4):199-207.
[28]王泽钧,马凤英,张瑜,等. 基于注意力机制和多尺度轻量型网络的农作物病害识别[J]. 农业工程学报,2022,38(增刊1):176-183.
[29]Dosovitskiy A,Beyer L,Kolesnikov A,et al. An image is worth 16×16 words:transformers for image recognition at scale[EB/OL]. (2021-06-03)[2024-03-23]. https://doi.org/10.48550/arXiv.2010.11929.
[30]Zhu K,Wu J X. Residual attention:a simple but effective method for multi-label recognition[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal,2021:184-193.

相似文献/References:

[1]徐凯宏,米雅婷,谷志新.基于GA-BP神经网络的温室番茄病害诊断[J].江苏农业科学,2016,44(04):387.
 Xu Kaihong,et al.Diagnosis of tomato disease in greenhouse based on GA-BP network[J].Jiangsu Agricultural Sciences,2016,44(14):387.
[2]苏世伟,朱文,聂影.农作物秸秆资源生态转化方式分析[J].江苏农业科学,2015,43(11):452.
 Su Shiwei,et al.Comparative analysis of ecological transformation way of crop straw resources[J].Jiangsu Agricultural Sciences,2015,43(14):452.
[3]阴国富,朱创录.基于物联网的精密温室环境管控系统研究[J].江苏农业科学,2015,43(10):491.
 Yin Guofu,et al.Study on precision greenhouse environment control system based on internet of things[J].Jiangsu Agricultural Sciences,2015,43(14):491.
[4]王永昌,田景文.基于离散脊波变换的农作物图像去噪算法[J].江苏农业科学,2015,43(05):425.
 Wang Yongchang,et al.Study on crop image denoising algorithm based on ridgelet transform[J].Jiangsu Agricultural Sciences,2015,43(14):425.
[5]李文凤,房翠翠,霍英芝.不同农作物根际自生固氮菌分离及固氮酶活性[J].江苏农业科学,2014,42(07):385.
 Li Wenfeng,et al.Isolation and nitrogenase activities of rhizosphere azotobacter from different crops[J].Jiangsu Agricultural Sciences,2014,42(14):385.
[6]张会敏,张云龙,张善文,等.基于区分矩阵的属性约简算法的作物病害识别方法[J].江苏农业科学,2015,43(01):387.
 Zhang Huimin,et al.A crop disease recognition method based on attribute reduction of discernibility matrix[J].Jiangsu Agricultural Sciences,2015,43(14):387.
[7]赵盼盼,王丽,袁园园,等.提高CRISPR/Cas9系统靶向编辑效率方法的研究进展[J].江苏农业科学,2017,45(01):12.
 Zhao Panpan,et al.Research progress on methods of enhancing CRISPR/Cas9 system target editing effects[J].Jiangsu Agricultural Sciences,2017,45(14):12.
[8]杨海婧,田丰,马永清,等.小麦、蚕豆和油菜浸提液对秦艽种子萌发的影响[J].江苏农业科学,2017,45(05):145.
 Yang Haijing,et al.Effects of wheat,broad bean and oilseed rape extracts on seed germination of Gentianae macrophylla[J].Jiangsu Agricultural Sciences,2017,45(14):145.
[9]张云龙,袁浩,张晴晴,等.基于颜色特征和差直方图的苹果叶部病害识别方法[J].江苏农业科学,2017,45(14):171.
 Zhang Yunlong,et al.Apple leaf disease recognition based on color characteristics and differential histogram[J].Jiangsu Agricultural Sciences,2017,45(14):171.
[10]刁智华,刁春迎,魏玉泉,等.机器人系统中小麦病害识别与施药算法研究[J].江苏农业科学,2017,45(17):192.
 Diao Zhihua,et al.Study on wheat disease identification and spraying algorithm in robot system[J].Jiangsu Agricultural Sciences,2017,45(14):192.

备注/Memo

备注/Memo:
收稿日期:2024-06-27
基金项目:国家自然科学基金(编号:62176088);河南省科技发展计划(编号:222102110135)。
作者简介:杜海顺(1977—),男,河南延津人,博士,教授,硕士生导师,研究方向为机器学习、模式识别。E-mail:jddhs@vip.henu.edu.cn。
更新日期/Last Update: 2025-07-20