首页 | 本学科首页   官方微博 | 高级检索  
   检索      

基于植保大数据的病虫害移动智能采集新设备
作者姓名:刘万才  陆明红  黄冲  张炜  陈天娇  谢成军
作者单位:全国农业技术推广服务中心;安徽中科智能感知产业技术研究院有限责任公司;中国科学院合肥物质科学研究院/中国科学院合肥智能机械研究所
基金项目:国家重点研发计划(2018YFD0200300);粮食丰产增效科技创新专项(2016YFD0300700).
摘    要:为提高农作物重大病虫害发生信息自动化、智能化采集能力,全面提升监测预警水平,笔者基于大数据、人工智能和深度学习技术,研发了一款农作物病虫害移动智能采集设备——智宝,主要实现了3个方面的功能:一是病虫害发生信息自动采集上报.通过该产品进行人工拍照,可实现对田间农作物重大病虫害发生图像、发生位置、发生数量、微环境因子等数据的实时采集和上报.二是自动识别计数.基于植保大数据与人工智能技术,通过构建病虫害自动识别系统,可实现重大病虫害精准识别与分析,只要拍摄照片,即可快速、精确地识别病虫害种类,并自动计数、上报到指定的测报系统.三是自动分析判别分级.针对拍摄采集上报的重大病虫害发生信息,系统可在自动识别和计数的基础上,进一步对病虫害发生严重程度进行智能判别分级,甚至根据相关预测模型,对病虫害的发生趋势进行辅助分析预测,提出预测建议.通过2016—2019年组织多地植保机构进行试验改进,该技术产品日趋成熟,有望在未来的农作物病虫害发生信息采集和预测预报工作中推广使用.

关 键 词:植保大数据  人工智能  深度学习  监测预警  信息采集  智宝

ZPro:A New Mobile Intelligent Pest and Disease Information Collection Device Based on Plant Protection Big Data
Authors:LIU Wan-cai  LU Ming-hong  HUANG Chong  ZHANG Wei  CHEN Tian-jiao  XIE Cheng-jun
Institution:(National Agro-Tech Extension and Service Center,Beijing 100125,China;Anhui Zhongke Sense Industrial Technology Research Institute Co.Ltd.,Wuhu Anhui 241000,China;Institute of Intelligent Machines,Hefei Institute of of Physical Science,Chinese Academy of Sciences,Hefei 230031,China)
Abstract:In order to improve the ability of automatic and intelligent collection of monitoring and early warning of major crop pests and diseases,we have developed a new mobile intelligent device named ZPro for pest and disease occurrence collection based on big data,artificial intelligence and deep learning techniques.The device focuses on three functionalities.The first functionality is automatic pest and disease occurrence collection and reporting.Through manual photographing by the equipment,real-time collection and reporting of information can be realized such as the occurrence image,occurrence location,occurrence quantity,and micro environmental factors in the field.The second is automatic recognition and population counting.Based on plant protection big data and artificial intelligence techniques,major pests and diseases can be precisely identified and analyzed by constructing an automatic recognition system.Pests and diseases on the photographed images can be fast and precisely identified and counted,and the results are reported to a designated monitoring system.Finally,the third functionality is automatic analysis and discrimination.Based on the reported information such as identification and population counting,the system can further estimate the severity of pest and disease occurrence intelligently,predict the occurrence trend based on relevant prediction models,and give recommendations.With improvements in experiments made by plant protection agencies at many sites during 2016 and 2019,ZPro has become increasingly applicable and is expected to be popularized in future crop pest and disease monitoring and forecasting.
Keywords:plant protection big data  artificial intelligence  deep learning  monitoring and warning  information collection  ZPro
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号