|本期目录/Table of Contents|

[1]王忠培,董伟,朱静波,等.简单三维注意力机制水稻病害识别模型[J].江苏农业科学,2023,51(20):186-193.
 Wang Zhongpei,et al.Simple 3D attention mechanism model for rice disease identification[J].Jiangsu Agricultural Sciences,2023,51(20):186-193.
点击复制

简单三维注意力机制水稻病害识别模型(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20期
页码:
186-193
栏目:
农业工程与信息技术
出版日期:
2023-10-20

文章信息/Info

Title:
Simple 3D attention mechanism model for rice disease identification
作者:
王忠培1董伟1朱静波1谢成军2
1.安徽省农业科学院农业经济与信息研究所,安徽合肥 230001; 2.中国科学院合肥智能机械研究所,安徽合肥 230031
Author(s):
Wang Zhongpeiet al
关键词:
水稻病害识别三维注意力注意力机制
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
准确、快速地识别水稻病害并及时采取防治措施,是减少水稻产量损失和提高水稻质量的有效途径之一。以生产上常见的6种水稻病害为研究对象,提出一种简单的三维注意力机制水稻识别模型。不同于通道注意力或空间注意力方法将研究对象特征分开考虑而导致研究对象本身固有的三维特性丢失的现象,本研究借鉴人类观察物体时将观察主体作为三维整体考虑的特点,提出算法。不同于SimAM算法将输入图像中的激活像素人为设置+1作为正样本、不激活像素设置-1作为负样本的假定,本研究不对输入图像的每个像素作人为硬性阈值的设定,而是保留其本身输入特征大小;这种设定不会破坏研究对象本身的固有属性,更符合研究主题自身的特性。研究结果表明,在自建水稻病害识别数据集达到的最高准确率为98.6%,比SimAM算法提高0.84百分点;相比经典网络模型ResNet50、MobileNetV2、EfficientNet_B0、DenseNet分别提高1.71、1.93、1.93、0.84百分点;相比通道注意力机制模型 SENe、ECA模型分别提高1.20、1.28百分点,表明本模型能够为自然环境下水稻病害的智能识别提供技术支持。
Abstract:
-

参考文献/References:

[1]刘杰,曾娟,杨清坡,等. 2023年全国农作物重大病虫害发生趋势预报[J]. 中国植保导刊,2023,43(1):32-35.
[2]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.
[3]樊湘鹏,许燕,周建平,等. 基于迁移学习和改进CNN的葡萄叶部病害检测系统[J]. 农业工程学报,2021,37(6):151-159.
[4]刘斌,贾润昌,朱先语,等. 面向移动端的苹果叶部病虫害轻量级识别模型[J]. 农业工程学报,2022,38(6):130-139.
[5]张善文,许新华,齐国红,等. 基于可形变VGG-16模型的田间作物害虫检测方法[J]. 农业工程学报,2021,37(18):188-194.
[6]Espejo-Garcia B,Malounas I,Mylonas N,et al. Using EfficientNet and transfer learning for image-based diagnosis of nutrient deficiencies[J]. Computers and Electronics in Agriculture,2022,196:106868.
[7]Peng H X,Li Z H,Zhou Z Y,et al. Weed detection in paddy field using an improved RetinaNet network[J]. Computers and Electronics in Agriculture,2022,199:107179.
[8]Hu J,Shen L,Sun G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.June 18-23,2018,Salt Lake City,UT,USA.IEEE,2018:7132-7141.
[9]Zhao X ,Li K Y,Li Y X,et al. Identification method of vegetable diseases based on transfer learning and attention mechanism[J]. Computers and Electronics in Agriculture,2022,193:106703.
[10]Zhao Y,Sun C D,Xu X,et al. RIC-Net:a plant disease classification model based on the fusion of Inception and residual structure and embedded attention mechanism[J]. Computers and Electronics in Agriculture,2022,193:106644.
[11]赵辉,曹宇航,岳有军,等. 基于改进DenseNet的田间杂草识别[J]. 农业工程学报,2021,37(18):136-142.
[12]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.
[13]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.
[14]甘雨,郭庆文,王春桃,等. 基于改进EfficientNet模型的作物害虫识别[J]. 农业工程学报,2022,38(1):203-211.
[15]Hou Q B,Zhou D Q,Feng J S. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 20-25,2021.Nashville,TN,USA.IEEE,2021:13713-13722.
[16]宋怀波,江梅,王云飞,等. 融合卷积神经网络与视觉注意机制的苹果幼果高效检测方法[J]. 农业工程学报,2021,37(9):297-303.
[17]Wang X L,Girshick R,Gupta A,et al. Non-local neural networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.June 18-23,2018.Salt Lake City,UT,USA.IEEE,2018:7794-7803.
[18]Yang L,Zhang R Y,Li L,et al. Simam:a simple,parameter-free attention module for convolutional neural networks[C]//International conference on machine learning. PMLR,2021:11863-11874.
[19]Webb B S,Dhruv N T,Solomon S G,et al. Early and late mechanisms of surround suppression in striate cortex of macaque[J]. The Journal of Neuroscience,2005,25(50):11666-11675.
[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 (CVPR).June 27-30,2016.Las Vegas,NV,USA.IEEE,2016:770-778.
[21]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.June 18-23,2018.Salt Lake City,UT.IEEE,2018:4510-4520.
[22]Huang G,Liu Z A,van Der Maaten L,et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).July 21-26,2017.Honolulu,HI.IEEE,2017:4700-4708.
[23]Tan M,Le Q. Efficientnet:rethinking model scaling for convolutional neural networks[C]//International conference on machine learning. PMLR,2019:6105-6114.

相似文献/References:

[1]王怀宇,李景丽.基于纹理特征的玉米苗期田间杂草识别[J].江苏农业科学,2014,42(07):143.
 Wang Huaiyu,et al.Weed identification in field during seedling stage of maize based on textural features[J].Jiangsu Agricultural Sciences,2014,42(20):143.
[2]朱景福,李雪.聚类算法在玉米叶片病斑降维识别中的应用[J].江苏农业科学,2015,43(01):405.
 Zhu Jingfu,et al.Application of clustering algorithm in recognition of corn leaf disease dimensionality reduction image[J].Jiangsu Agricultural Sciences,2015,43(20):405.
[3]朱景福,李雪.玉米叶片病害彩色图像识别的降维和聚类方法[J].江苏农业科学,2016,44(07):350.
 Zhu Jingfu,et al.Dimensionality reduction and clustering method for recognition of corn leaf disease color image[J].Jiangsu Agricultural Sciences,2016,44(20):350.
[4]牛冲,牛昱光,李寒,等.基于像灰度直方图特征图的草莓病虫害识别[J].江苏农业科学,2017,45(04):169.
 Niu Chong,et al.Recognition of diseases and insect pests of strawberry based on image gray histogram feature[J].Jiangsu Agricultural Sciences,2017,45(20):169.
[5]李妍,朱景福,罗文博,等.玉米叶片病斑多光谱特征提取及识别方法[J].江苏农业科学,2017,45(09):184.
 Li Yan,et al.Extraction and recognition method of multi spectral feature of corn leaf spot[J].Jiangsu Agricultural Sciences,2017,45(20):184.
[6]李婷,吴克宁.基于遥感技术的耕地质量评价研究进展与展望[J].江苏农业科学,2018,46(15):5.
 Li Ting,et al.Research progress and prospects of cultivated land quality evaluation based on remote sensing technology[J].Jiangsu Agricultural Sciences,2018,46(20):5.
[7]杨新周,杨兰芬,田孟华,等.不同产地白花蛇舌草傅里叶红外光谱识别[J].江苏农业科学,2019,47(15):212.
 Yang Xinzhou,et al.Identification of Hedyotis diffusa from different habitats by Fourier infrared spectrum[J].Jiangsu Agricultural Sciences,2019,47(20):212.
[8]赵子娟,刘东,杭中桥.作物遥感识别方法研究现状及展望[J].江苏农业科学,2019,47(16):45.
 Zhao Zijuan,et al.Research status and prospect of crop remote sensing identification methods[J].Jiangsu Agricultural Sciences,2019,47(20):45.
[9]王松,谢银燕,张成彬,等.荔枝病虫害及其防治研究进展[J].江苏农业科学,2019,47(17):120.
 Wang Song,et al.Research progress on prevention and control of Litchi chinensis pests and diseases[J].Jiangsu Agricultural Sciences,2019,47(20):120.
[10]叶佳英,邓飞,王佩欣,等.基于机器视觉的珍珠颜色特征提取与识别[J].江苏农业科学,2019,47(20):226.
 Ye Jiaying,et al.Pearl color feature extraction and recognition based on machine vision[J].Jiangsu Agricultural Sciences,2019,47(20):226.

备注/Memo

备注/Memo:
收稿日期:2023-01-31
基金项目:国家自然科学基金(编号:32171888)。
作者简介:王忠培(1981—),男,安徽金寨人,博士,助理研究员,研究方向为智能农业技术。E-mail:wangzhongpei@aaas.org.cn。
通信作者:董伟,硕士,副研究员,研究方向为植物保护信息化技术。E-mail:dongwei@ aaas.org.cn。
更新日期/Last Update: 2023-10-20