农作物叶片病害迁移学习分步识别方法

doi:10.13474/j.cnki.11-2246.2021.0205

测绘通报 ›› 2021, Vol. 0 ›› Issue (7): 34-38.doi: 10.13474/j.cnki.11-2246.2021.0205

农作物叶片病害迁移学习分步识别方法

赵恒谦^1,2, 杨屹峰¹, 刘泽龙¹, 宋瑞¹

1. 中国矿业大学(北京)地球科学与测绘工程学院, 北京 100083;
2. 农业生态大数据分析与应用技术国家地方联合工程研究中心, 安徽合肥 230601

收稿日期:2021-05-13 修回日期:2021-05-21 出版日期:2021-07-25 发布日期:2021-08-04
通讯作者: 刘泽龙。E-mail:bxlzl0077@163.com
作者简介:赵恒谦(1986-),男,博士,副教授,主要研究方向为遥感智能信息提取与应用等。E-mail:zhaohq@cumtb.edu.cn
基金资助:
国家自然科学基金（41701488）；中国矿业大学（北京）越崎青年学者（2020QN07）；农业生态大数据分析与应用技术国家地方联合工程研究中心开放课题（AE201901）；中央高校基本科研业务费专项资金（2021YJSDC16）

Step-by-step identification method of crop leaf diseases based on transfer learning

ZHAO Hengqian^1,2, YANG Yifeng¹, LIU Zelong¹, SONG Rui¹

1. College of Geoscience and Surveying Engineering, China University of Mining & Technology-Beijing, Beijing 100083, China;
2. National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, Hefei 230601, China

Received:2021-05-13 Revised:2021-05-21 Online:2021-07-25 Published:2021-08-04

摘要/Abstract

摘要： 农作物病害的准确识别有助于提高农作物的产量与质量。针对作物病害图像训练样本数据量较少的情况，本文采用迁移学习方法结合分步识别模型对多种农作物病害种类进行了识别。将PlantVillage公开数据集中3种农作物的10类作物叶片图像作为训练样本，利用直接识别方法分别对VGG16和ResNet的原始模型和迁移学习模型进行训练，得到模型的分类结果；提出分步识别方法，将训练样本按作物种类和病害类型归类，分别进行模型训练并构建分步识别模型。试验结果表明：利用迁移学习方法能够在原始模型的基础上将识别精度提高20%以上；在其基础上引入分步识别方法并与直接识别方法对比，能够将VGG16和ResNet模型精度再分别提高14%和8%。本文提出的迁移学习分步识别方法能够实现在小样本训练数据情况下的作物病害准确识别，可为作物病害防治提供有效的技术支持。

关键词: 迁移学习, 小样本学习, 卷积神经网络, 分步识别, 作物病害

Abstract: Accurate identification of crop diseases can help improve the yield and quality of crops. As image training sample data of crop disease is limited, this paper adopts the transfer learning method combine with the step-by-step identification model to identify a host of crop disease types. Taking PlantVillage public data set of ten types of crop leaf images of three crops as training samples, the paper uses the direct recognition method to train the original model of VGG16 and ResNet and the model of transfer learning respectively, and obtain the classification results of the model. This paper proposes a step-by-step identification method, the training samples are classified according to the types of crops and disease types, the models are trained separately, and a step-by-step identification model is constructed. The experimental results show that the transfer learning method can increase the recognition accuracy by more than 20% on the basis of the original model. On the basis of this, the step-by-step identification method is introduced and compared with the direct recognition method, the accuracy of the VGG16 and ResNet models is increased by 14% and 8%, respectively. The transfer learning step-by-step identification method proposed in this research can realize the accurate identification of crop diseases in the case of small samples of training data, and can provide effective technical support for crop disease prevention and control.

Key words: transfer learning, few-shot learning, convolutional neural network, step-by-step identification, crop diseases

中图分类号:

P237

赵恒谦, 杨屹峰, 刘泽龙, 宋瑞. 农作物叶片病害迁移学习分步识别方法[J]. 测绘通报, 2021, 0(7): 34-38.

ZHAO Hengqian, YANG Yifeng, LIU Zelong, SONG Rui. Step-by-step identification method of crop leaf diseases based on transfer learning[J]. Bulletin of Surveying and Mapping, 2021, 0(7): 34-38.

参考文献 16

[1]	赵春江.智慧农业发展现状及战略目标研究[J].智慧农业,2019,1(1):1-7.
[2]	贾少鹏,高红菊,杭潇.基于深度学习的农作物病虫害图像识别技术研究进展[J].农业机械学报,2019,50(S1):313-317.
[3]	周俊宇,赵艳明.卷积神经网络在图像分类和目标检测应用综述[J].计算机工程与应用,2017,53(13):34-41.
[4]	KERKECH M, HAFIANE A, CANALS R, et al. Deep learning approach with colorimetric spaces and vegetation indices for vine diseases detection in UAV images[J]. Computers and Electronics in Agriculture,2018,155(12):237-243.
[5]	AMARA J, BOUAZIZ B, ALGERGAWY A. A deep learning-based approach for banana leaf diseases classification[C]//Datenbanksysteme für Business, Technologie und Web (BTW 2017). Stuttgart:[s.n.], 2017.
[6]	许景辉,邵明烨,王一琛,等.基于迁移学习的卷积神经网络玉米病害图像识别[J].农业机械学报,2020,51(2):230-236.
[7]	ZHAO Y, ZHENG Y L,SHI H L, et al. Transfer learning-based convolutional neural network image recognition method for plant leaves[J]. International Journal of Circuits, Systems and Signal Processing,2020,14:56-62.
[8]	张瑞青,李张威,郝建军,等.基于迁移学习的卷积神经网络花生荚果等级图像识别[J].农业工程学报,2020,36(23):171-180.
[9]	赵立新,侯发东,吕正超,等.基于迁移学习的棉花叶部病虫害图像识别[J].农业工程学报,2020,36(7):184-191.
[10]	张善文,黄文准,尤著宏.基于物联网和深度卷积神经网络的冬枣病害识别方法[J].浙江农业学报,2017,29(11):1868-1874.
[11]	FERENTINOS K P.Deep learning models for plant disease detection and diagnosis[J].Computers and Electronics in Agriculture,2018,145:311-318.
[12]	李炳臻,刘克,顾佼佼,等.卷积神经网络研究综述[J].计算机时代,2021(4):8-12.
[13]	TÜRKOǦLU M,HANBAY D. Plant disease and pest detection using deep learning-based features[J]. Turkish Journal of Electrical Engineering and Computer Science,2019(3):1636-1651.
[14]	LEONG K K, TZE L L. Plant leaf diseases identification using convolutional neural network with treatment handling system[C]//IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS).[S.l.]:IEEE, 2020.
[15]	MOHANTY S P, HUGHES D P, SALATHE M. Using deep learning for image-based plant disease detection[J]. Frontiers in Plant Science, 2016, 7:1-10.
[16]	ELSKEN T, METZEN J H, HUTTER F, et al. Neural architecture search:a survey[J]. Journal of Machine Learning Research, 2019, 20(55):1-21.

农作物叶片病害迁移学习分步识别方法

Step-by-step identification method of crop leaf diseases based on transfer learning

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 16

相关文章 15

编辑推荐

Metrics

本文评价

[1]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[2]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[3]	滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.
[4]	文奴, 郭仁忠, 贺彪, 万远. YOLO v4框架下Multi-Patch多帧增量式交通视频目标检测[J]. 测绘通报, 2022, 0(5): 38-44.
[5]	段晨阳, 冯建中, 全斌, 白林燕, 王盼盼. 利用深度学习进行GF-6影像枣园检测识别[J]. 测绘通报, 2022, 0(3): 54-59.
[6]	王胜利, 朱寿红, 蒋毅. 基于CNN模型迁移的OLI影像光伏电池板场景识别[J]. 测绘通报, 2022, 0(2): 5-9.
[7]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.
[8]	贾文翰, 刘越岩. 基于卷积神经网络的高分遥感影像内陆盐沼湿地信息提取[J]. 测绘通报, 2021, 0(6): 89-92.
[9]	段雅鸣, 张锦水, 朱爽. 基于深度卷积神经网络的云检测方法[J]. 测绘通报, 2021, 0(4): 33-39.
[10]	马林飞, 倪欢, 周子涵. 基于注意力机制的高分遥感图像采石场识别[J]. 测绘通报, 2021, 0(11): 96-100.
[11]	彭述刚, 王大成, 谭军辉, 敖旋峰, 俞佳颖. 基于改进卷积神经网络的城市地下排水管道视频智能识别[J]. 测绘通报, 2021, 0(10): 132-135,167.
[12]	王大成, 谭军辉, 彭述刚, 钟镇声, 陈国强, 李国桥. 利用深度学习模型智能识别地下排水管道缺陷[J]. 测绘通报, 2021, 0(10): 141-145.
[13]	杨泽宇, 张洪艳, 明金, 冷伟, 刘海启, 游炯. 深度学习在高分辨率遥感影像冬油菜提取中的应用[J]. 测绘通报, 2020, 0(9): 110-113.
[14]	马超. 融合卷积神经网络和循环神经网络的车轮目标检测[J]. 测绘通报, 2020, 0(8): 139-143.
[15]	何肖娜, 宋斌斌, 余敏. 融合上下文感知的地标检测辅助WiFi-PDR室内定位[J]. 测绘通报, 2020, 0(6): 7-11,16.