基于掩码自编码的农作物病虫害分类方法  

Research on Agricultural Crop Diseases and Pests Classification Based on Masked Autoencoding

作　　者：鞠萍 宋岩[1] 张英杰 徐一夫 邵杭 JU Ping;SONG Yan;ZHANG Yingjie;XU Yifu;SHAO Hang(School of Economics and Management,Yantai University,Yantai 264005,China;Befar Group Co.,Ltd.,Binzhou 256600,China;Qingzhou Cigarette Factory,China Tobacco Shandong Industrial Co.,Ltd.,Weifang 2625000,China;School of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]烟台大学经济管理学院,山东烟台264005 [2]滨化集团股份有限公司,山东滨州256600 [3]山东中烟工业有限责任公司青州卷烟厂,山东潍坊262500 [4]南京理工大学计算机科学与工程学院,江苏南京210094

出　　处：《电子科技》2024年第10期23-29,共7页Electronic Science and Technology

基　　金：国家自然科学基金(61806094);山东省社会科学规划重点项目(18BGLJ04)。

摘　　要：作物病虫害使农业生产遭受损失,但仅依靠人工调查难以满足田间需求。基于机器视觉可实现病虫害自动分类,为农业精准高效生产提供保障。然而现有利用深度学习的方法易受刚性卷积感受野影响,数据增强手段低效且样本量匮乏。针对这些问题,文中提出一种基于掩码自编码学习范式的农业经济作物病虫害分类方法,来弥补现有技术在识别准确率方面的不足。通过对作物图像随机掩蔽、特征提取和依高维映射的全局重建,所提算法能充分挖掘输入的高阶语义隐式表征,建模同一图像内远距离上下文关系,从而训练鲁棒性更强的模型。通过相对总变分变换消除了高频噪声对预训练特征提取过程的干扰。所提方法与当前基于主流卷积网络的方法的对比结果表明,所提方法可显著提升现有方法的性能,准确率由基于ResNet50基准网络的90.48%提升至95.24%。Crop diseases and insect pests cause a large amount of economic losses in agricultural production activities,and it is difficult to meet field production requirements of the current society if only relying on manual surveys by agronomist staffs.Applications of the machine vision technology can realize the automatic classification and detection of crop diseases and insect pests,and provide the guarantee for accurate and efficient agricultural productions.However,existing detection methods based on the deep learning framework and convolutional neural networks are constrained by factors such as rigid convolutional receptive field,inefficient data enhancement operator,and small sample size.In order to make up for the above shortcomings of existing detection technologies in term of recognition accuracy,a method for the classification of agricultural economic crop diseases and insect pests based on the masked autoencoding learning paradigm is proposed in this study.Through local random content masking,semantic feature extraction,and global context reconstruction of high-dimensional mapping of input crop images,the proposed algorithm can fully mine implicit representations of high-level semantics of images and model the long-distance contextual relationship in the same map,so as to train a more robust model with less data samples.Moreover,the model eliminates the interference of the high-frequency noise on the pre-training feature extraction processing by the relative total variational transformation.The results of comparison between the proposed method and current methods based on mainstream convolutional networks show that the proposed method can significantly improve the performance of existing methods,and the accuracy rate is improved from 90.48%to 95.24%based on ResNet50 benchmark network.

关 键 词：机器视觉 深度学习 农业经济作物 病虫害检测 掩码自编码 相对总变分 神经网络 卷积感受野 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]