基于轻量化VGG的植物病虫害识别  

Plant disease detection based on lightweight VGG

作　　者：王江晴[1,2] 冀星 莫海芳 帖军[1,2] 刘畅 Wang Jiangqing;Ji Xing;Mo Haifang;Tie Jun;Liu Chang(College of Computer Science,South-Central University for Nationalities,Wuhan,430074,China;Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises,Wuhan,430074,China)

机构地区：[1]中南民族大学计算机科学学院,武汉市430074 [2]湖北省制造企业智能管理工程技术研究中心,武汉市430074

出　　处：《中国农机化学报》2022年第4期25-31,共7页Journal of Chinese Agricultural Mechanization

基　　金：湖北省技术创新专项重大项目(2019ABA101);武汉市科技计划应用基础前沿项目(2020020601012267)。

摘　　要：深度神经网络模型被广泛应用在植物病虫害识别任务中,并取得巨大成功。同时,这些网络的计算复杂度和参数量也在不断增加,这将对神经网络的部署提出重大挑战,尤其是在硬件资源有限的设备或实时应用上。针对该问题,提出一种轻量化的病虫害识别模型,结合Ghost模块对VGG16进行改进,同时减少模型卷积层的卷积核个数,并引入Ranger优化器。试验结果表明,该模型在PlantVillage数据集上准确率为99.37%,FLOPs为88.45 M,比VGG16下降71.86%,有较快的收敛速度,在复杂环境下,模型的准确率为92.40%,识别时间为VGG16的50%。The deep neural network model is widely used in the identification of plant diseases and insect pests and has achieved great success.At the same time,the computational complexity and parameter quantities of these networks are also increasing,which will pose a major challenge to the deployment of neural networks,especially on devices with limited hardware resources or real-time applications.Aiming to solve this problem,a lightweight pest identification model with Ranger optimizer is proposed,in which the VGG16 is improved by using the Ghost module and reducing the number of convolution kernels in the convolution layer.Experimental results show that the accuracy of the model on the PlantVillage dataset is 99.37%,and the FLOPs is 88.45 M,which is 71.86%lower than VGG16,and it has a faster convergence rate.In a complex environment,the accuracy of the model is 92.40%,and the time is 50%of VGG16.

关 键 词：轻量化 病虫害识别 Ghost模块 VGG网络 Ranger优化器 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]