|本期目录/Table of Contents|

[1]黄铝文,郑梁,黄煜,等.基于多尺度卷积与通道域增强的草莓病害识别方法[J].江苏农业科学,2023,51(10):202-210.
 Huang Lyuwen,et al.Strawberry disease recognition method based on multi-scale convolution and channel domain enhancement[J].Jiangsu Agricultural Sciences,2023,51(10):202-210.
点击复制

基于多尺度卷积与通道域增强的草莓病害识别方法(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:
202-210
栏目:
农业工程与信息技术
出版日期:
2023-05-20

文章信息/Info

Title:
Strawberry disease recognition method based on multi-scale convolution and channel domain enhancement
作者:
黄铝文12郑梁1黄煜1谦博1关非凡1
1.西北农林科技大学信息工程学院,陕西杨凌 712100; 2.农业农村部农业物联网重点实验室,陕西杨凌 712100
Author(s):
Huang Lyuwenet al
关键词:
草莓病害识别多尺度卷积算子特征增强残差模块
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
为提高草莓病害图像的分类准确性,提出一种基于通道域增强的深度超参数化金字塔卷积残差网络(CEM-DOPConv-ResNet18)。首先,针对草莓病害的多尺度特点,基于金字塔卷积与深度超参数化卷积提出深度超参数化金字塔卷积(DOPConv),在提取多尺度病害特征的同时,缓解参数量增加导致的收敛干扰;其次,提出基于双重池化的通道增强模块,用以提高模型的特征选择能力,增强有用尺度下的特征;最后,将上述方法与ResNet18结合,将原本的 3×3 卷积替换为DOPConv,同时在残差块中加入通道增强模块,构建出草莓病害分类网络。为验证模型识别性能与模块有效性,在草莓病害图像数据集上进行对比试验和消融试验。对比试验结果表明,与原有ResNet18模型相比,CEM-DOPConv-ResNet18的准确率达97.867%,提高3.045百分点,同时内存占用量下降16.6%;消融试验结果表明,相较于原始金字塔卷积,DOPConv可以优化模型收敛,对通道增强模块具有更高的兼容度。该模型提高了草莓病害的分类准确率,降低了网络复杂度,为病害的精准识别提供了一种有效解决模型。
Abstract:
-

参考文献/References:

[1]王鸣谦,薛莉,赵珺,等. 世界草莓生产及贸易现状[J]. 中国果树,2021(2):104-108.
[2]Thakur P S,Khanna P,Sheorey T,et al. Trends in vision-based machine learning techniques for plant disease identification:a systematic review[J]. Expert Systems With Applications,2022,208:118117.
[3]翟肇裕,曹益飞,徐焕良,等. 农作物病虫害识别关键技术研究综述[J]. 农业机械学报,2021,52(7):1-18.
[4]Ngugi L C,Abelwahab M,Abo-Zahhad M. Recent advances in image processing techniques for automated leaf pest and disease recognition-A review[J]. Information Processing in Agriculture,2021,8(1):27-51.
[5]Ma L,Guo X L,Zhao S K,et al. Algorithm of strawberry disease recognition based on deep convolutional neural network[J]. Complexity,2021,2021:1-10.
[6]Kim B,Han Y K,Park J H,et al. Improved vision-based detection of strawberry diseases using a deep neural network[J]. Frontiers in Plant Science,2021,11:559172.
[7]Zhuang F Z,Qi Z Y,Duan K Y,et al. A comprehensive survey on transfer learning[J]. Proceedings of the IEEE,2021,109(1):43-76.
[8]丁永军,张晶晶,李民赞. 基于卷积胶囊网络的百合病害识别研究[J]. 农业机械学报,2020,51(12):246-251,331.
[9]张会敏,谢泽奇,张善文. 基于注意力胶囊网络的作物病害识别方法[J]. 江苏农业科学,2022,50(6):101-106.
[10]Kwabena Patrick M,Felix Adekoya A,Abra Mighty A,et al. Capsule networks-A survey[J]. Journal of King Saud University-Computer and Information Sciences,2022,34(1):1295-1310.
[11]李书琴,陈聪,朱彤,等. 基于轻量级残差网络的植物叶片病害识别[J]. 农业机械学报,2022,53(3):243-250.
[12]王美华,吴振鑫,周祖光. 基于注意力改进CBAM的农作物病虫害细粒度识别研究[J]. 农业机械学报,2021,52(4):239-247.
[13]Niu Z Y,Zhong G Q,Yu H. A review on the attention mechanism of deep learning[J]. Neurocomputing,2021,452:48-62.
[14]Shi H,Cao G,Ge Z X,et al. Double-branch network with pyramidal convolution and iterative attention for hyperspectral image classification[J]. Remote Sensing,2021,13(7):1403.
[15]Yang X H,Yang Y,Yang J,et al. Image multi-label classification based on pyramid convolution and split-attention mechanism[C]//2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP).December 17-19,2021,Chengdu,China.IEEE,2022:534-538.
[16]Li C Y,Fan Y X,Cai X D. PyConvU-Net:a lightweight and multiscale network for biomedical image segmentation[J]. BMC Bioinformatics,2021,22(1):14.
[17]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.
[18]Cao J M,Li Y Y,Sun M C,et al. DO-conv:depthwise over-parameterized convolutional layer[J]. IEEE Transactions on Image Processing,2022,31:3726-3736.
[19]Gao H M,Chen Z H,Li C M. Shallow network based on depthwise overparameterized convolution for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters,2022,19:1-5.
[20]Wang Y Y,Zhang W S,Zhang L M,et al. Depthwise over-parameterized Siamese network for visual tracking[C]//2021 International Conference on Information Technology and Biomedical Engineering (ICITBE). December 24-26,2021,Nanchang,China.IEEE,2022:58-62.
[21]Liu Y H,Shen J,Yang L,et al. ResDO-UNet:a deep residual network for accurate retinal vessel segmentation from fundus images[J]. Biomedical Signal Processing and Control,2023,79:104087.
[22]Afzaal U,Bhattarai B,Pandeya Y R,et al. An instance segmentation model for strawberry diseases based on mask R-CNN[J]. Sensors,2021,21(19):6565.
[23]Shorten C,Khoshgoftaar T M. A survey on image data augmentation for deep learning[J]. Journal of Big Data,2019,6(1):1-48.
[24]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).June 27-30,2016,Las Vegas,NV,USA.IEEE,2016:770-778.
[25]Chollet F. Xception:deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).July 21-26,2017,Honolulu,HI,USA.IEEE,2017:1800-1807.
[26]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).June 13-19,2020.Seattle,WA,USA.IEEE,2020:11531-11539.
[27]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.
[28]史加荣,王丹,尚凡华,等. 随机梯度下降算法研究进展[J]. 自动化学报,2021,47(9):2103-2119.
[29]Zhou B L,Khosla A,Lapedriza A,et al. Learning deep features for discriminative localization[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).June 27-30,2016.Las Vegas,NV,USA.IEEE,2016:2921-2929.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2022-12-15
基金项目:国家重点研发计划(编号:2020YFD1100601);国家级大学生创新创业训练计划(编号:202210712195)。
作者简介:黄铝文(1976—),男,湖南湘乡人,博士,副教授,博士生导师,主要从事生物图像处理、机器人控制技术研究。E-mail:huanglvwen@nwsuaf.edu.cn。
更新日期/Last Update: 2023-05-20