|本期目录/Table of Contents|

[1]肖天赐,陈燕红,李永可,等.基于改进通道注意力机制的农作物病害识别模型研究[J].江苏农业科学,2023,51(24):168-175.
 Xiao Tianci,et al.Study on crop disease identification model based on improved channel attention mechanism[J].Jiangsu Agricultural Sciences,2023,51(24):168-175.
点击复制

基于改进通道注意力机制的农作物病害识别模型研究(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24期
页码:
168-175
栏目:
农业工程与信息技术
出版日期:
2023-12-20

文章信息/Info

Title:
Study on crop disease identification model based on improved channel attention mechanism
作者:
肖天赐1陈燕红123李永可123李雨晴1罗玉峰4
1.新疆农业大学,新疆乌鲁木齐 830052; 2.智能农业教育部工程研究中心,新疆乌鲁木齐 830052;3.新疆农业信息化工程技术研究中心,新疆乌鲁木齐 830052; 4.社旗县中等职业学校,河南社旗 473399
Author(s):
Xiao Tianciet al
关键词:
农作物病害识别通道注意力机制残差网络迁移学习数据增强
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
准确地识别农作物病害种类、病害程度,是能够正确防治病害的基础,对农作物的高质量生产有重要意义。针对传统深度学习模型对图像的细粒度分类不够精准的问题,提出不参与残差计算的通道注意力(efficient channel attention without participating in residual calculation,EWPRC)结构,该结构将改进的通道注意力机制ECANet3放在残差块之后,增加模型对通道维度的权重学习能力,并将EWPRC结构用于骨干网络为ResNet50的迁移学习模型中,通过替换模型中的layer3、layer4层得到了EWPRC-RseNet-t模型。试验使用了AIChallenger 2018数据集,在数据预处理、数据增强、超参数相同的情况下,首先对比了固定核大小为3、5、7、11、13的通道注意力机制对模型准确率的影响,在此试验中,模型的准确率随卷积核变大呈下降趋势,其中一维卷积核大小为3的模型准确率最高,达到了8742%,比核大小为5、7、11、13的模型分别提高了0.03、0.42、0.51、0.64百分点。再将EWPRC-ResNet-t模型与经过微调的迁移学习模型ResNet-t以及GoogLeNet、MobileNet-v3、ResNet50模型进行对比,以准确率、精确率、召回率以及F1值作为评价指标,试验结果证明EWPRC-ResNet-t模型取得了最好的效果,比传统深度学习模型中准确率最高的ResNet50模型提高了0.99百分点,比ResNet-t模型提高了0.75百分点。且相比传统的深度学习模型,EWPRC-ResNet-t模型有更高的精度、召回率与F1得分。
Abstract:
-

参考文献/References:

[1]张珂,冯晓晗,郭玉荣,等. 图像分类的深度卷积神经网络模型综述[J]. 中国图象图形学报,2021,26(10):2305-2325.
[2]Huo M Y,Tan J. Overview:research progress on pest and disease identification[C]//Suen,Ching Y. Pattern recognition and artificial intelligence. Cham:Springer International Publishing,2020:404-415.
[3]Xu W X,Sun L,Zhen C,et al. Deep learning-based image recognition of agricultural pests[J]. Applied Sciences,2022,12(24):12896.
[4]Bondre S,Patil D. Recent advances in agricultural disease image recognition technologies:a review[J]. Concurrency and Computation(Practice and Experience),2023,35(9):e7644.
[5]Yuan Y,Chen L,Wu H R,et al. Advanced agricultural disease image recognition technologies:a review[J]. Information Processing in Agriculture,2022,9(1):48-59.
[6]Huang M L,Chuang T C,Liao Y C. Application of transfer learning and image augmentation technology for tomato pest identification[J]. Sustainable Computing(Informatics and Systems),2022,33:100646.
[7]Kathiresan G,Anirudh M,Nagharjun M,et al. Disease detection in rice leaves using transfer learning techniques[J]. Journal of Physics(Conference Series),2021,1911(1):012004.
[8]Tirkey D,Singh K K,Tripathi S. Performance analysis of AI-based solutions for crop disease identification,detection,and classification[J]. Smart Agricultural Technology,2023,5:100238.
[9]Agarwal M,Gupta S K,Biswas K K. Development of efficient CNN model for tomato crop disease identification[J]. Sustainable Computing(Informatics and Systems),2020,28:100407.
[10]Wang C F,Ni P,Cao M Y. Research on crop disease recognition based on Multi-Branch ResNet-18[J]. Journal of Physics(Conference Series),2021,1961(1):012009.
[11]Thakur P S,Sheorey T,Ojha A. VGG-ICNN:a lightweight CNN model for crop disease identification[J]. Multimedia Tools and Applications,2023,82(1):497-520.
[12]高荣华,白强,王荣,等. 改进注意力机制的多叉树网络多作物早期病害识别方法[J]. 计算机科学,2022,49(增刊1):363-369.
[13]姜红花,杨祥海,丁睿柔,等. 基于改进ResNet18的苹果叶部病害多分类算法研究[J]. 农业机械学报,2023,54(4):295-303.
[14]Hu J,Shen L,Sun G,et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023.
[15]Woo S,Park J,Lee J Y,et al. CBAM:convolutional block attention module[C]//European Conference on Computer Vision.Cham:Springer,2018:3-19.
[16]Fu J,Liu J,Tian H J,et al. Dual attention network for scene segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach,2020:3141-3149.
[17]Chen Y P,Kalantidis Y,Li J S,et al. A2-nets:double attention networks[EB/OL]. [2023-04-12]. https://arxiv.org/abs/1810.11579.
[18]Gao Z L,Xie J T,Wang Q L,et al. Global second-order pooling convolutional networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach,2020:3019-3028.
[19]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. Seattle,2020:11531-11539.
[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. Las Vegas,2016:770-778.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2023-05-09
基金项目:新疆维吾尔自治区重大科技专项(编号:2022A02011)。
作者简介:肖天赐(2000—),男,河南安阳人,硕士研究生,研究方向为计算机视觉。E-mail:2351175028@qq.com。
通信作者:陈燕红,硕士,副教授,研究方向为视觉-语言智能表征学习,E-mail:cyh@xjau.edu.cn;李永可,硕士,副教授,研究方向为智慧农业,E-mail:lyk@xjau.edu.cn。
更新日期/Last Update: 2023-12-20