|本期目录/Table of Contents|

[1]王洪波,杨永政,谢志成,等.基于Res-Inception的农作物病虫害识别技术[J].江苏农业科学,2024,52(20):181-189.
 Wang Hongbo,et al.Crop diseases and pests identification technology based on Res-Inception[J].Jiangsu Agricultural Sciences,2024,52(20):181-189.
点击复制

基于Res-Inception的农作物病虫害识别技术(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第52卷
期数:
2024年第20期
页码:
181-189
栏目:
病虫害智能检测
出版日期:
2024-10-20

文章信息/Info

Title:
Crop diseases and pests identification technology based on Res-Inception
作者:
王洪波 杨永政 谢志成 郁志宏 王春光
内蒙古农业大学机电工程学院,内蒙古呼和浩特 010018
Author(s):
Wang Hongboet al
关键词:
农作物病虫害迁移学习ResNetInception图像识别
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
针对现有视觉识别技术对于农作物病虫害识别存在实际农业生产中识别效果不佳的问题,研究提出了一种结合ResNet和Inception 2种模型优点的新构架Res-Inception块。Res-Inception块中采取了ResNet中的残差结构使得模型可以有效应对深度过深造成的过拟合和模型退化的问题;Res-Inception块中的卷积层采用Inception模型中的并行联结策略,将传统的3×3卷积核由并行的1×3、3×1卷积核代替,在简化模型参数量的同时使得模型获得了更强的多尺度特征提取能力;最后通过迁移学习使模型拥有高效的学习能力。在训练过程中将公开数据集PlantVillage中的多种作物病虫害作为预训练样本,通过迁移学习后对PlantVillage中6种番茄病虫害图像进行识别,模型对于训练集中病虫害的检测准确率达到99.1%,验证集的检测准确率达到98.9%,平均F1分数达到98.82%。通过与VGG-16、ResNet34、ResNet50等检测模型在PlantVillage数据集中的6种番茄病虫害识别测试中,本模型的检测准确率远高于这些模型;并且通过对比采用迁移学习前后的模型检测能力,验证了本研究提出的模型可以有效解决模型过拟合问题。本研究提出的Res-Inception块在有效解决了现有模型过拟合及模型退化问题的同时提高了模型的实际检测效果,该模块可为农业生产中病虫害识别模型的轻量化提供新思路,助力模型在实际农业生产中的应用。
Abstract:
-

参考文献/References:

[1]张玉婷. 农作物病虫害防治工作存在的问题与对策[J]. 乡村科技,2022,13(2):83-85.
[2]2022年全国农作物重大病虫害发生趋势预报[J]. 中国植保导刊,2022,42(4):107-108.
[3]武保华. 农作物病虫害防治中存在的问题及对策[J]. 河北农机,2023(10):91-93.
[4]李爱芳. 农业种植中病虫危害特点及应对方法[J]. 农业科技与信息,2021,8(8):46-47.
[5]Xin M Y,Wang Y. Image recognition of crop diseases and insect pests based on deep learning[J]. Wireless Communications and Mobile Computing,2021,2021(1):1-15.
[6]Li D S,Wang R J,Xie C J,et al. A recognition method for rice plant diseases and pests video detection based on deep convolutional neural network[J]. Sensors,2020,20(3):578.
[7]Rahman C R,Arko P S,Ali M E,et al. Identification and recognition of rice diseases and pests using convolutional neural networks[J]. Biosystems Engineering,2020,194:112-120.
[8]Liu J,Wang X W. Tomato diseases and pests detection based on improved YOLO v3 convolutional neural network[J]. Frontiers in Plant Science,2020,11:898.
[9]范春全,何彬彬. 基于迁移学习的水稻病虫害识别[J]. 中国农业信息,2020,32(2):36-44.
[10]吴健宇. 基于深度卷积神经网络的农作物病虫害识别及实现[D]. 哈尔滨:哈尔滨工业大学,2019:20-25.
[11]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.
[12]黄双萍,孙超,齐龙,等. 基于深度卷积神经网络的水稻穗瘟病检测方法[J]. 农业工程学报,2017,33(20):169-176.
[13]刘永波,雷波,曹艳,等. 基于深度卷积神经网络的玉米病害识别[J]. 中国农学通报,2018,34(36):159-164.
[14]龙满生,欧阳春娟,刘欢,等. 基于卷积神经网络与迁移学习的油茶病害图像识别[J]. 农业工程学报,2018,34(18):194-201.
[15]Jiang F,Lu Y,Chen Y,et al. Image recognition of four rice leaf diseases based on deep learning and support vector machine[J]. Computers and Electronics in Agriculture,2020,179:105824.
[16]Beyer L,Hénaff O J,Kolesnikov A,et al. Are we done with ImageNet?[EB/OL]. 2020:arXiv:2006.07159.http://arxiv.org/abs/2006.07159.
[17]Recht B,Roelofs R,Schmidt L,et al. Do ImageNet classifiers generalize to ImageNet?[EB/OL]. 2019:arXiv:1902.10811.http://arxiv.org/abs/1902.10811.
[18]He K M,Zhang X Y,Ren S Q,et al. Identity mappings in deep residual networks[C]//European Conference on Computer Vision.Cham:Springer,2016:630-645.
[19]Shafiq M,Gu Z Q. Deep residual learning for image recognition:a survey[J]. Applied Sciences,2022,12(18):8972.
[20]刘晓锋,高丽梅. 基于改进空间残差收缩网络模型的农作物病虫害识别[J]. 山东农业大学学报(自然科学版),2022,53(2):259-264.
[21]刘冬寒. 基于改进深度残差网络的农作物病害识别研究[D]. 杭州:浙江农林大学,2021:17-20.
[22]Szegedy C,Ioffe S,Vanhoucke V,et al. Inception-v4,inception-ResNet and the impact of residual connections on learning[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2017,31(1):4278-4284.
[23]Szegedy C,Vanhoucke V,Ioffe S,et al. Rethinking the inception architecture for computer vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,NV,USA.IEEE,2016:2818-2826.
[24]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.
[25]余小东,杨孟辑,张海清,等. 基于迁移学习的农作物病虫害检测方法研究与应用[J]. 农业机械学报,2020,51(10):252-258.
[26]王东方,汪军. 基于迁移学习和残差网络的农作物病害分类[J]. 农业工程学报,2021,37(4):199-207.
[27]仝卫国,李敏霞,张一可. 深度学习优化算法研究[J]. 计算机科学,2018,45(增刊2):155-159.
[28]贾桐. 深度学习常用优化算法研究[J]. 信息技术与网络安全,2019,38(7):42-46.
[29]李明,来国红,常晏鸣,等. 深度学习算法中不同优化器的性能分析[J]. 信息技术与信息化,2022(3):206-209.
[30]Tammina S.Transfer learning using VGG-16 with deep convolutional neural network for classifying images[J]. International Journal of Scientific and Research Publications,2019,9(10):143-150.

相似文献/References:

[1]陈光绒,李小琴.基于物联网技术的农作物病虫害自动测报系统[J].江苏农业科学,2015,43(04):406.
 Chen Guangrong,et al.Automatic measuring and reporting system for crop diseases and insect pests based on internet of things[J].Jiangsu Agricultural Sciences,2015,43(20):406.
[2]郑颖,金松林,张自阳,等.基于领域本体的农作物病虫害问题分类研究[J].江苏农业科学,2016,44(09):145.
 Zheng Ying,et al.Study on crop diseases and insect pests question classification based on domain ontology[J].Jiangsu Agricultural Sciences,2016,44(20):145.
[3]刘嘉政.基于深度迁移学习模型的花卉种类识别[J].江苏农业科学,2019,47(20):231.
 Liu Jiazheng.Flower species identification based on deep transfer learning model[J].Jiangsu Agricultural Sciences,2019,47(20):231.
[4]康飞龙,李佳,刘涛,等.多类农作物病虫害的图像识别应用技术研究综述[J].江苏农业科学,2020,48(22):22.
 Kang Feilong,et al.Application technology of image recognition for various crop diseases and insect pests: a review[J].Jiangsu Agricultural Sciences,2020,48(20):22.
[5]徐振南,王建坤,胡益嘉,等.基于MobileNetV3的马铃薯病害识别[J].江苏农业科学,2022,50(10):176.
 Xu Zhennan,et al.Potato disease recognition based on MobileNetV3[J].Jiangsu Agricultural Sciences,2022,50(20):176.
[6]徐重新,张江兆,胡晓丹,等.农药联合复配在农作物病虫害防治上的研究进展[J].江苏农业科学,2023,51(4):8.
 Xu Chongxin,et al.Research progress of pesticide combination in crop diseases and insect pests control[J].Jiangsu Agricultural Sciences,2023,51(20):8.
[7]李子涵,周省邦,赵戈,等.基于卷积神经网络的农业病虫害识别研究综述[J].江苏农业科学,2023,51(7):15.
 Li Zihan,et al.Study on agricultural pest identification based on convolutional neural network: a review[J].Jiangsu Agricultural Sciences,2023,51(20):15.
[8]温艳兰,陈友鹏,王克强,等.基于迁移学习和改进残差网络的复杂背景下害虫图像识别[J].江苏农业科学,2023,51(8):171.
 Wen Yanlan,et al.Recognition of pest images under complex background based on transfer learning and improved residual network[J].Jiangsu Agricultural Sciences,2023,51(20):171.
[9]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(20):215.
[10]章广传,李彤,何云,等.基于迁移模型集成的马铃薯叶片病害识别方法[J].江苏农业科学,2023,51(15):216.
 Zhang Guangchuan,et al.A method for identifying potato leaf diseases based on migration model integration[J].Jiangsu Agricultural Sciences,2023,51(20):216.
[11]黎振,陆玲,熊方康.基于k-means分割和迁移学习的番茄病理识别[J].江苏农业科学,2021,49(12):156.
 Li Zhen,et al.Tomato pathological recognition based on k-means segmentation and transfer learning[J].Jiangsu Agricultural Sciences,2021,49(20):156.

备注/Memo

备注/Memo:
收稿日期:2023-11-18
基金项目:内蒙古自治区科技创新引导项目(编号:Kcj1-202205)。
作者简介:王洪波(1978—),男,内蒙古呼和浩特人,博士,教授,硕士生导师,从事智能农业装备研究。E-mail:wanghb@imau.edu.cn。
更新日期/Last Update: 2024-10-20