基于机器视觉的病虫害检测综述  

An Overview of Plant Diseases and Insect Pests Detection Based on Machine Vision

作　　者：温艳兰 陈友鹏[2] 王克强[1] 刘展眉 林钦永 蔡肯[1] 马佳佳 孔翰博 Wen Yanlan;Chen Youpeng;Wang Keqiang;Liu Zhanmei;Lin Qinyong;Cai Ken;Ma Jiajia;Kong Hanbo(Zhongkai University of Agriculture and Engineering,Guangzhou 510225;Guangzhou Nanyang Polytechnic College,Guangzhou 510980)

机构地区：[1]仲恺农业工程学院,广州510225 [2]广州南洋理工职业学院,广州510980

出　　处：《中国粮油学报》2022年第10期271-279,共9页Journal of the Chinese Cereals and Oils Association

基　　金：广东省科技计划项目(KA1721404);广东省普通高校重点领域专项(2019GZDXM007)。

摘　　要：作物病虫害直接影响作物的代谢过程,是降低作物的产量和品质的主要威胁之一,给农民造成了大量的经济损失。实现快速、准确的病虫害检测和分类识别,对农民及时采取有效的防治措施具有重要意义。目前,利用机器视觉技术实现农作物病虫害检测具有很好的前景,可以有效的克服人工识别速度慢、误判率高的不足,对于加快农业产业智能化,以及病虫害防治的智能化水平的提高都有很好的借鉴价值。结合近年来国内外学者研究进展情况,本文就病虫害检测方面的应用进展进行综述,并展望了未来的研究方向,以期为后续研究工作提供参考。Crop diseases and insect pests directly affect the metabolic process of crops,being one of the main threats reducing crop yield and quality,and causing a lot of economic losses to farmers.It is of great significance for farmers to take effective control measures in time to achieve rapid and accurate detection and classification of diseases and pests.At present,using machine vision technology to detect crop diseases and pests has a good prospect,which can effectively overcome the shortcomings of slow manual recognition and high misjudgment rate.It has a good reference value for accelerating the intellectualization of agricultural industry and improving the intelligent level of disease and pest control.Combined with the research progress of scholars at home and abroad in recent years.In the present paper,the application progress of pest detection was summarized,and the future research direction was prospected to provide basic theoretical reference for follow-up research work.

关 键 词：机器视觉 图像分割 特征提取 深度学习 分类识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]