|本期目录/Table of Contents|

[1]温钊发,蒲智,程曦,等.基于轻量级MIE_Net的田间农作物病害识别[J].江苏农业科学,2023,51(10):176-184.
 Wen Zhaofa,et al.Field crop disease identification based on lightweight MIE_Net[J].Jiangsu Agricultural Sciences,2023,51(10):176-184.
点击复制

基于轻量级MIE_Net的田间农作物病害识别(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第51卷
期数:
2023年第10期
页码:
176-184
栏目:
农业工程与信息技术
出版日期:
2023-05-20

文章信息/Info

Title:
Field crop disease identification based on lightweight MIE_Net
作者:
温钊发蒲智程曦赵昀杰张泽宇
新疆农业大学计算机与信息工程学院,新疆乌鲁木齐 830052
Author(s):
Wen Zhaofaet al
关键词:
病害识别轻量级网络注意力机制多尺度特征
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
为实现农作物病害的快速精准识别,降低病害对农业安全生产的影响,本研究针对现有病害识别模型参数量大、鲁棒性低、泛化性弱等问题提出了轻量级MIE_Net农作物病害识别网络。该网络以MobileNetV2为基础网络结构,首先使用多尺度特征提取模块替换原网络的初始卷积层,提高网络对不同面积病斑的特征提取能力,增加网络中的特征复杂度;其次在主模块中添加ECA注意力机制,提高网络对叶片病害区域的关注程度,降低复杂背景对小病斑特征提取过程的影响;最后使用Swish激活函数增加网络的表达能力,使网络性能达到最优。结果表明,多尺度特征提取模块提高了模型对不同病斑大小的识别准确率,ECA注意力模块提高了网络对小病斑的识别准确率,最终网络模型对复杂环境中2种作物11种病害类别的最低识别精确率达到91.2%,总体病害识别准确率达到95.79%,比原网络提高1.84百分点,参数量为2.24 M,权重文件大小为8.78 MB。MIE_Net网络在保证模型轻量化的同时提高了模型的准确性、泛化性以及鲁棒性,整体性能优于其他现有网络模型,为以后的轻量级作物病害识别方法提供了参考。
Abstract:
-

参考文献/References:

[1]Food and Agriculture Organization of the United Nation. Plant health and food security[EB/OL]. (2020-06-04)[2022-03-03]. https://www.fao.org/3/i7829en/I7829EN.pdf.
[2]刘杰,姜玉英,黄冲,等. 2021年全国粮食作物重大病虫害发生趋势预报[J]. 中国植保导刊,2021,41(1):37-39,42.
[3]2021年其他一类农作物病虫害全国发生趋势预报[J]. 农民文摘,2021(3):47.
[4]蒲秀夫,宁芊,雷印杰,等. 基于二值化卷积神经网络的农业病虫害识别[J]. 中国农机化学报,2020,41(2):177-182.
[5]Tang Z,Yang J L,Li Z,et al. Grape disease image classification based on lightweight convolution neural networks and channelwise attention[J]. Computers and Electronics in Agriculture,2020,178:105735.
[6]Ni P,Chen Z,Cao M Y. Research on crop disease recognition based on uniting multi-layer features[J]. Journal of Physics,2021,1961(1):012030.
[7]Huang G,Liu Z,van der Maaten L,et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu:IEEE,2017.
[8]胡玲艳,周婷,许巍,等. 面向番茄病害识别的改进型SqueezeNet轻量级模型[J]. 郑州大学学报(理学版),2022,54(4):71-77.
[9]孙文斌,王荣,高荣华,等. 基于可见光谱和改进注意力的农作物病害识别[J]. 光谱学与光谱分析,2022,42(5):1572-1580.
[10]李昊,刘海隆,刘生龙. 基于深度学习的柑橘病虫害动态识别系统研发[J]. 中国农机化学报,2021,42(9):195-201,208.
[11]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.
[12]黄林生,罗耀武,杨小冬,等. 基于注意力机制和多尺度残差网络的农作物病害识别[J]. 农业机械学报,2021,52(10):264-271.
[13]林建吾,张欣,陈孝玉龙,等. 基于轻量化卷积神经网络的番茄病害图像识别[J]. 无线电工程,2022,52(8):1347-1353.
[14]牛学德,高丙朋,南新元,等. 基于改进DenseNet卷积神经网络的番茄叶片病害检测[J]. 江苏农业学报,2022,38(1):129-134.
[15]Sandler M,Howard A,Zhu M L,et al. MobileNetV2:inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:4510-4520.
[16]Howard A G,Zhu M L,Chen B,et al. MobileNets:efficient convolutional neural networks for mobile vision applications[EB/OL]. (2017-04-17)[2022-03-05]. https://arxiv.org/abs/1704.04861
[17]He K M,Zhang X Y,Ren S Q,et al. Deep residual learning for image recognition[EB/OL]. (2015-12-10)[2022-03-05]. https://arxiv.org/pdf/1512.03385.pdf.
[18]Szegedy C,Liu W,Jia Y Q,et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston:IEEE,2015.
[19]Hu J,Shen L,Albanie S,et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023.
[20]Wang Q L,Wu B G,Zhu P F,et al. ECA-net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle:IEEE,2020.

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(10):387.
[2]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(10):387.
[3]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(10):171.
[4]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(10):192.
[5]刁智华,袁万宾,刁春迎,等.病害特征在作物病害识别中的应用研究综述[J].江苏农业科学,2019,47(05):71.
 Diao Zhihua,et al.Application of disease characteristics in crop disease identification:a review[J].Jiangsu Agricultural Sciences,2019,47(10):71.
[6]林彬彬,邱新法,何永健,等.茶树病害智能诊断识别算法研究[J].江苏农业科学,2019,47(06):85.
 Lin Binbin,et al.Study on intelligent diagnosis and recognition algorithm for tea diseases[J].Jiangsu Agricultural Sciences,2019,47(10):85.
[7]何前,郭峰林,方皓正,等.基于改进LeNet-5模型的玉米病害识别[J].江苏农业科学,2022,50(20):35.
 He Qian,et al.Study on maize disease recognition based on improved LeNet-5 model[J].Jiangsu Agricultural Sciences,2022,50(10):35.
[8]孙长兰,林海峰.一种基于集成学习的苹果叶片病害检测方法[J].江苏农业科学,2022,50(20):41.
 Sun Changlan,et al.An apple tree leaf disease detection method based on ensemble learning[J].Jiangsu Agricultural Sciences,2022,50(10):41.
[9]王慧,李康顺,蔡铁,等.基于约束性多目标优化算法的柑橘黄龙病识别算法[J].江苏农业科学,2023,51(6):159.
 Wang Hui,et al.Citrus Huanglongbing recognition algorithm based on constrained multi-objective optimization algorithm[J].Jiangsu Agricultural Sciences,2023,51(10):159.
[10]王哲豪,范丽丽,何前.基于MobileNet V2和迁移学习的番茄病害识别[J].江苏农业科学,2023,51(9):215.
 Wang Zhehao,et al.Recognition of tomato disease based on transfer learning and MobileNet V2[J].Jiangsu Agricultural Sciences,2023,51(10):215.

备注/Memo

备注/Memo:
收稿日期:2022-07-07
基金项目:国家自然科学基金(编号:62161048)。
作者简介:温钊发(1996—),男,陕西宝鸡人,硕士研究生,主要从事计算机视觉研究。E-mail:320203315@xjau.edu.cn。
通信作者:蒲智,博士,副教授,主要从事计算机应用研究。E-mail:869831699@qq.com。
更新日期/Last Update: 2023-05-20