An Automatic Classification Grading of Spinach Seedlings Water Stress Based on N-MobileNetXt  

作　　者：Yanlei Xu Xue Cong Yuting Zhai Zhiyuan Gao Helong Yu 

机构地区：[1]School of Information Technology,Jilin Agricultural University,Changchun,130118,China

出　　处：《Intelligent Automation & Soft Computing》2023年第9期3019-3037,共19页智能自动化与软计算（英文）

基　　金：supported in part by the Science and Technology Development Plan Project of Changchun[Grant Number 21ZGN28];the Jilin Provincial Science and Technology Development Plan Project[Grant Number 20210101157JC];the Jilin Provincial Science and Technology Development Plan Project[Grant Number 20230202035NC].

摘　　要：To solve inefficient water stress classification of spinach seedlings under complex background,this study proposed an automatic classification method for the water stress level of spinach seedlings based on the N-MobileNetXt(NCAM+MobileNetXt)network.Firstly,this study recon-structed the Sandglass Block to effectively increase the model accuracy;secondly,this study introduced the group convolution module and a two-dimensional adaptive average pool,which can significantly compress the model parameters and enhance the model robustness separately;finally,this study innovatively proposed the Normalization-based Channel Attention Module(NCAM)to enhance the image features obviously.The experimental results showed that the classification accuracy of N-MobileNetXt model for spinach seedlings under the natural environment reached 90.35%,and the number of parameters was decreased by 66%compared with the original MobileNetXt model.The N-MobileNetXt model was superior to other net-work models such as ShuffleNet and GhostNet in terms of parameters and accuracy of identification.It can provide a theoretical basis and technical support for automatic irrigation.

关 键 词：Deep learning water stress grade classification image processing complex background 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]