|本期目录/Table of Contents|

[1]雷建云,陈楚,郑禄,等.基于改进残差网络的水稻害虫识别[J].江苏农业科学,2022,50(14):190-198.
 Lei Jianyun,et al.Identification of rice pests based on improved residual network[J].Jiangsu Agricultural Sciences,2022,50(14):190-198.
点击复制

基于改进残差网络的水稻害虫识别(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第50卷
期数:
2022年第14期
页码:
190-198
栏目:
农业工程与信息技术
出版日期:
2022-07-20

文章信息/Info

Title:
Identification of rice pests based on improved residual network
作者:
雷建云陈楚郑禄帖军赵捷
中南民族大学计算机科学学院/湖北省制造企业智能管理工程技术研究中心,湖北武汉 430074
Author(s):
Lei Jianyunet al
关键词:
害虫识别残差网络胶囊网络动态路由水稻
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
水稻害虫是影响水稻产量的因素之一,准确识别水稻害虫对提高水稻产量具有重要意义,针对水稻害虫识别准确率不高的问题,提出一种基于改进残差网络模型的水稻害虫识别方法。该模型是将动态路由胶囊结构嵌入残差网络深度卷积模型中,代替残差网络的全连接层,首先通过4个残差块得到特征图,将特征图进行胶囊化编码,其次进行层间路由,以减少卷积神经网络(CNN)在输出时丢失的大量信息。对水稻的14类害虫进行识别,并分析不同参数(学习率、批量大小、激活函数和优化组合)的影响。结果表明,提出的改进残差网络模型的准确率达到7712%。模型满足水稻害虫图像识别的需求,具有一定的识别准确率及较强的鲁棒性,可为实际农业场景下水稻害虫识别提供可行的方案。
Abstract:
-

参考文献/References:

[1]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.
[2]Xing S L,Lee M,Lee K K. Citrus pests and diseases recognition model using weakly dense connected convolution network[J]. Sensors,2019,19(14):3195.
[3]Pan W Y,Qin J H,Xiang X Y,et al. A smart mobile diagnosis system for citrus diseases based on densely connected convolutional networks[J]. IEEE Access,2019(7):87534-87542.
[4]吴翔. 基于机器视觉的害虫识别方法研究[D]. 杭州:浙江大学,2016.
[5]谢成军,李瑞,董伟,等. 基于稀疏编码金字塔模型的农田害虫图像识别[J]. 农业工程学报,2016,32(17):144-151.
[6]梁万杰,曹宏鑫. 基于卷积神经网络的水稻虫害识别[J]. 江苏农业科学,2017,45(20):241-243,253.
[7]周爱明. 基于深度学习的农业灯诱害虫自动识别与计数技术的研究[D]. 杭州:浙江理工大学,2019.
[8]Song Y Y,Duan X Y,Ren Y,et al. Identification of the agricultural pests based on deep learning models[C]//International Conference on Machine Learning,Big Data and Business Intelligence. Taiyuan:IEEE,2019.
[9]Thenmozhi K,Srinivasulu R U. Crop pest classification based on deep convolutional neural network and transfer learning[J]. Computers and Electronics in Agriculture,2019,164:104906.
[10]Nanni L,Maguolo G,Pancino F. Insect pest image detection and recognition based on bio-inspired methods[J]. Ecological Informatics,2020,57:101089.
[11]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.
[12]李静,陈桂芬,安宇. 基于优化卷积神经网络的玉米螟虫害图像识别[J]. 华南农业大学学报,2020,41(3):110-116.
[13]Wu X P,Zhan C,Lai Y K,et al. IP102:a large-scale benchmark dataset for insect pest recognition[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE,2019.
[14]Iqbal Z,Khan M A,Sharif M,et al. An automated detection and classification of citrus plant diseases using image processing techniques:a review[J]. Computers and Electronics in Agriculture,2018,153:12-32.
[15]He K M,Zhang X Y,Ren S Q,et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016.
[16]谢军,江朝晖,李博,等. 基于二次迁移模型的小样本茶树病害识别[J]. 江苏农业科学,2021,49(6):176-182.
[17]Dong Z Y,Lin S. Research on image classification based on CapsNet[C]//IEEE 4th Advanced Information Technology,Electronic and Automation Control Conference.Chengdu:IEEE,2019.
[18]Choi J,Seo H,Im S,et al. Attention routing between capsules[C]//IEEE/CVF International Conference on Computer Vision Workshop.Seoul:IEEE,2019.
[19]Jampour M,Abbaasi S,Javidi M. CapsNet regularization and its conjugation with ResNet for signature identification[J]. Pattern Recognition,2021,120:107851.
[20]Zomahoun D E. A semantic collaborative clustering approach based on confusion matrix[C]//15th International Conference on Signal-Image Technology & Internet-Based Systems.Sorrento:IEEE,2019.
[21]Malek M A,Reya S S,Hasan M Z,et al. A crop pest classification model using deep learning techniques[C]//2nd International Conference on Robotics,Electrical and Signal Processing Techniques.Dhaka:IEEE,2021.
[22]Stursa D,Dolezel P. Comparison of ReLU and linear saturated activation functions in neural network for universal approximation[C]//22nd International Conference on Process Control (PC19).Strbske Pleso:IEEE,2019.

相似文献/References:

[1]谢军,江朝晖,李博,等.基于二次迁移模型的小样本茶树病害识别[J].江苏农业科学,2021,49(6):176.
 Xie Jun,et al.Image recognition of tea plant disease small samples based on secondary migration model[J].Jiangsu Agricultural Sciences,2021,49(14):176.
[2]戴久竣,马肄恒,吴坚,等.基于改进残差网络的葡萄叶片病害识别[J].江苏农业科学,2023,51(5):208.
 Dai Jiujun,et al.Grape leaf disease identification based on improved residual network[J].Jiangsu Agricultural Sciences,2023,51(14):208.
[3]鲍浩,张艳.基于注意力机制与改进残差模块的豆叶病害识别[J].江苏农业科学,2023,51(16):187.
 Bao Hao,et al.Bean leaf disease identification based on attention mechanism and improved residual module[J].Jiangsu Agricultural Sciences,2023,51(14):187.
[4]吴刚正,蔡成岗,朱瑞瑜.基于注意力机制和残差网络的苹果叶片病害分类[J].江苏农业科学,2023,51(18):177.
 Wu Gangzheng,et al.Apple leaf disease classification based on attention mechanism and residual network[J].Jiangsu Agricultural Sciences,2023,51(14):177.
[5]李军,李志伟,李艳红.基于多原型指导的小样本水稻害虫识别与分类[J].江苏农业科学,2023,51(20):193.
 Li Jun,et al.Recognition and classification of rice pests in small samples based on multi-prototype guidance[J].Jiangsu Agricultural Sciences,2023,51(14):193.
[6]吴子炜,夏芳,陆林峰,等.基于改进YOLO v5的水稻主要害虫识别方法[J].江苏农业科学,2023,51(21):218.
 Wu Ziwei,et al.An identification method for rice major pests based on improved YOLO v5[J].Jiangsu Agricultural Sciences,2023,51(14):218.
[7]江顺,黄红星,莫里楠,等.基于改进AlexNet的岭南水稻虫害识别方法研究[J].江苏农业科学,2023,51(23):187.
 Jiang Shun,et al.Study on identification method of Lingnan rice pests based on improved AlexNet[J].Jiangsu Agricultural Sciences,2023,51(14):187.
[8]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.
 Xiao Tianci,et al.Study on crop disease identification model based on improved channel attention mechanism[J].Jiangsu Agricultural Sciences,2023,51(14):168.
[9]黄英来,王奇,何少聪,等.基于改进ResNet101的黄瓜害虫识别方法研究[J].江苏农业科学,2025,53(5):203.
 Huang Yinglai,et al.Study on identification method for cucumber pests based on improved ResNet101[J].Jiangsu Agricultural Sciences,2025,53(14):203.

备注/Memo

备注/Memo:
收稿日期:2021-08-31
基金项目:湖北省技术创新专项(编号:2019ABA101);教育部科技发展中心高校产学研创新基金“青苔数智融合”协同创新项目(编号:2020QT08);国家民族事务委员会中青年英才培养计划(编号:MZR20007);武汉市科技计划应用基础前沿项目(编号:2020020601012267)。
作者简介:雷建云(1972—),男,浙江文成人,博士,教授,硕士生导师,主要从事图像处理、机器学习研究。E-mail:leijianyun@mail.scuec.edu.cn。
通信作者:郑禄,硕士,讲师,主要从事计算机视觉、深度学习的研究。E-mail:lu2008@mail.scuec.edu.cn。
更新日期/Last Update: 2022-07-20