基于病虫害声音识别的自动混药系统研究  

Study on the Automatic Pesticide Mixed System Based on the Acoustic Recognition of Pests

作　　者：陈爱武[1] 郭丙琴[2] 李荣[1] 

机构地区：[1]湖南科技学院电子与信息工程学院,湖南永州425199 [2]湖南科技学院教学质量管理处,湖南永州425199

出　　处：《广西职业技术学院学报》2016年第5期11-14,23,共5页Journal of Guangxi Vocational and Technical College

基　　金：湖南省科学技术厅科技计划项目:变量喷雾系统嵌入式实施中的关键问题研究(2014FJ3143);2015年永州市科技计划项目(永科发〔2015〕9号;No.22)

摘　　要：近年来,中国的农业机械化技术有了明显的进步,农业自动喷雾技术从常量喷雾转变为变量喷雾,实现了自动混药和减少了农药残余问题。但目前的自动在线混药技术主要集中在机械设备和精度方面的研究,如微流量计设计、流量精度控制等,很少考虑病虫害。在此基础上,该文提出了一种基于声学事件识别方法的在线变量喷雾系统,该方法运用了匹配追踪(Matching Pursuit,MP)算法实现病虫害及自然背景等事件的识别,并通过识别结果进行在线混药的技术。实验结果证明了该方法的可行性。China＇s agriculture mechanization technology has made a significant progress in recent years. To achieve the on-line pesticide-mixture technology and reduce pesticide residues, the spray technology has been changed from the constant one to the variable one. However, the researches of the automatic liquid-mixture systems are mainly concentrated in the mechanical equipment currently, such as the research of micro-flow meter design and the flow accuracy control and so on while there is little concern on the distribution of the pests. On this basis, this paper proposes a new idea of pesticide- mixture based on the recognition of acoustic events of pests, and the Matching Pursuit algorithm is also proposed to identify the pests and the environment sound in the study. The results show the feasibility of the proposed method.

关 键 词：声学事件 变量喷雾 MP算法 

分 类 号：S49[农业科学—植物保护] S126