基于小样本学习的马铃薯叶片病害检测-《江苏农业科学》

文章信息/Info

Title:: Potato leaf disease detection based on small sample learning

作者:: 邢鹏康¹; 2; 李久朋²; 3; 1. 河南省工业物联网应用工程技术研究中心，河南南阳 473000； 2.河南工业职业技术学院电子信息工程学院，河南南阳 473000；3. 中山大学电子与信息工程学院，广东广州 510275

Author(s):: Xing Pengkang; et al

关键词:: 马铃薯叶片; 病害检测; 卷积块注意力机制; 小样本学习; 任务感知注意力

Keywords:: -

分类号:: TP391.41

DOI:: -

文献标志码:: A

摘要:: 马铃薯叶片的病害将直接导致马铃薯产量和质量的下降，为实现马铃薯叶片病害的精确检测并及时预防病变，提出了一种基于小样本学习的马铃薯叶片病害检测算法。首先，利用一组共享权重的特征提取器将输入图片映射到深度特征空间；然后，提出一种任务感知注意力模块用于融合小样本学习网络中的双分支输入特征，强化目标任务的特定表达能力；最后，引入一种动态卷积模块提高卷积核的建模能力，并将卷积块注意力机制(CBAM)嵌入到该卷积网络中，构造特征强化学习模块，细粒度地捕获病害区域的细节特征。通过在开源马铃薯叶片病害检测数据集上进行测试，所提出模型分别实现了93.92%的准确率、93.81%的精准率、93.85%的召回率和93.63%的F₁值；此外，在自建数据集上与当前经典马铃薯叶片病害检测模型相比，同样具有较好的竞争力。

Abstract:: -

参考文献/References:

［1］Chen J D，Chen J X，Zhang D F，et al. Using deep transfer learning for image-based plant disease identification［J］. Computers and Electronics in Agriculture，2020，173：105393.
［2］赵建敏，芦建文. 基于字典学习的马铃薯叶片病害图像识别算法［J］. 河南农业科学，2018，47(4)：154-160.
［3］Tiwari D，Ashish M，Gangwar N，et al. Potato leaf diseases detection using deep learning［C］//2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS).Madurai，India.IEEE，2020：461-466.
［4］Mahum R，Munir H，Mughal Z U N，et al. A novel framework for potato leaf disease detection using an efficient deep learning model［J］. Human and Ecological Risk Assessment，2023，29(2)：303-326.
［5］Lee T Y，Lin I A，Yu J Y，et al. High efficiency disease detection for potato leaf with convolutional neural network［J］. SN Computer Science，2021，2(4)：297.
［6］赵越，赵辉，姜永成，等. 基于深度学习的马铃薯叶片病害检测方法［J］. 中国农机化学报，2022，43(10)：183-189.
［7］Rashid J，Khan I，Ali G，et al. Multi-level deep learning model for potato leaf disease recognition［J］. Electronics，2021，10(17)：2064.
［8］赵建敏，李艳，李琦，等. 基于卷积神经网络的马铃薯叶片病害识别系统［J］. 江苏农业科学，2018，46(24)：251-255.
［9］Li J W，Qiao Y L，Liu S，et al. An improved YOLOv5-based vegetable disease detection method［J］. Computers and Electronics in Agriculture，2022，202：107345.
［10］Afzaal H，Farooque A A，Schumann A W，et al. Detection of a potato disease (early blight) using artificial intelligence［J］. Remote Sensing，2021，13(3)：411.
［11］Saeed F，Khan M A，Sharif M，et al. Deep neural network features fusion and selection based on PLS regression with an application for crops diseases classification［J］. Applied Soft Computing，2021，103：107164.
［12］Chen J D，Deng X F，Wen Y X，et al. Weakly-supervised learning method for the recognition of potato leaf diseases［J/OL］. Artificial Intelligence Review，(2022-12-21)［2023-01-08］.https://doi.org/10.1007/s/0462-022-10374-3.
［13］Abdallah A. Plant village dataset［EB/OL］. (2022-11-26)［2023-01-05］. https：//www.kaggle.com/abdallahalidev/plantvillage-dataset.
［14］Zhang L B，Zhang J，Ma J，et al. SC-PNN：saliency cascade convolutional neural network for pansharpening［J］. IEEE Transactions on Geoscience and Remote Sensing，2021，59(11)：9697-9715.
［15］Wang S H，Zhou Q，Yang M，et al. ADVIAN：Alzheimers disease VGG-inspired attention network based on convolutional block attention module and multiple way data augmentation［J］. Frontiers in Aging Neuroscience，2021，13：687456.
［16］Shuai Y Z，Yuan Q，Zhao S S.A spatial-channel attention-based convolutional neural network for remote sensing image classification［C］//IGARSS 2022—2022 IEEE International Geoscience and Remote Sensing Symposium.Kuala Lumpur，Malaysia.IEEE，2022：3628-3631.

相似文献/References:

[1]马驰,吴华瑞,于会山.基于YOLOX的穴盘甘蓝病害检测方法[J].江苏农业科学,2023,51(8):193.
　Ma Chi,et al.Detection method of cabbage disease based on YOLOX[J].Jiangsu Agricultural Sciences,2023,51(15):193.
[2]黄贻望,王国帅,毛志,等.KMeans++与注意力机制融合的苹果叶片病害识别方法[J].江苏农业科学,2024,52(20):190.
　Huang Yiwang,et al.Identification of apple leaf diseases in complex environments through integration of KMeans++ and attention mechanisms[J].Jiangsu Agricultural Sciences,2024,52(15):190.
[3]叶琪,王丽芬,马明涛,等.基于改进YOLO v8的草莓病害检测方法[J].江苏农业科学,2024,52(20):250.
　Ye Qi,et al.Strawberry disease detection method based on improved YOLO v8[J].Jiangsu Agricultural Sciences,2024,52(15):250.
[4]高泉,刘笠溶,张洁,等.基于ActNN-YOLO v5s-RepFPN的番茄病害识别及系统设计[J].江苏农业科学,2024,52(20):220.
　Gao Quan,et al.Tomato disease identification and system design based on ActNN-YOLO v5s-RepFPN[J].Jiangsu Agricultural Sciences,2024,52(15):220.
[5]陈藜韦,古丽娜孜·艾力木江,伊力亚尔·加尔木哈买提,等.基于改进Swin Transformer的番茄和水稻植株病害检测[J].江苏农业科学,2025,53(10):222.
　Chen Liwei,et al.Detection of tomato and rice plant diseases based on improved Swin Transformer[J].Jiangsu Agricultural Sciences,2025,53(15):222.
[6]罗新磊,范菁.基于改进YOLO v8n的自然场景下苹果叶片病害检测[J].江苏农业科学,2025,53(20):288.
　Luo Xinlei,et al.Detection of apple leaf disease in natural environments based on improved YOLO v8n[J].Jiangsu Agricultural Sciences,2025,53(15):288.
[7]曾龙军,卢承方,陈勇,等.基于YOLOFBA的复杂环境下豆叶病害检测研究[J].江苏农业科学,2025,53(20):315.
　Zeng Longjun,et al.Detection of bean leaf disease in complex environment based on YOLOFBA[J].Jiangsu Agricultural Sciences,2025,53(15):315.
[8]江俊辉,龚程杰,陈中举.SATYOLO：复杂环境下的水稻病害轻量化检测模型[J].江苏农业科学,2025,53(23):235.
　Jiang Junhui,et al.SATYOLO：a lightweight detection model for rice diseases in complex environments[J].Jiangsu Agricultural Sciences,2025,53(15):235.

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

文章信息/Info

参考文献/References:

相似文献/References:

备注/Memo

常用功能

导航/Navigate

工具/Tools

统计/Statistics