{"title":"USING A DRONE TO DETECT PLANT DISEASE PATHOGENS","authors":"Jakub Karbowski, Jedrzej Minda","doi":"10.5593/sgem2022v/3.2/s14.53","DOIUrl":null,"url":null,"abstract":"Today, drones are already widely used in agriculture and forestry. Drones can help spray plants, take surface measurements, and estimate the damage caused by adverse weather conditions or wild animals. Drones can also be used in caring for the condition of crops. Traditional methods of detecting threats related to plant disease are time-consuming and ineffective. Thanks to the use of drones equipped with appropriate vision systems, it is possible to carry out quick and precise control of the condition of the plants. The article proposes a system for detecting plant pathogens using a drone. The concept of the proposed solution and the methodology of plant monitoring is described. The use of multiple neural network architectures is presented. Credible model performance metrics are described, thanks to the use of various datasets. In addition, the article presents the results of the developed algorithm on the testing ground. The conducted research confirmed the legitimacy and validity of the use of drones in the monitoring of forest crops and ecosystems.","PeriodicalId":331146,"journal":{"name":"SGEM International Multidisciplinary Scientific GeoConference� EXPO Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"SGEM International Multidisciplinary Scientific GeoConference� EXPO Proceedings","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5593/sgem2022v/3.2/s14.53","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Today, drones are already widely used in agriculture and forestry. Drones can help spray plants, take surface measurements, and estimate the damage caused by adverse weather conditions or wild animals. Drones can also be used in caring for the condition of crops. Traditional methods of detecting threats related to plant disease are time-consuming and ineffective. Thanks to the use of drones equipped with appropriate vision systems, it is possible to carry out quick and precise control of the condition of the plants. The article proposes a system for detecting plant pathogens using a drone. The concept of the proposed solution and the methodology of plant monitoring is described. The use of multiple neural network architectures is presented. Credible model performance metrics are described, thanks to the use of various datasets. In addition, the article presents the results of the developed algorithm on the testing ground. The conducted research confirmed the legitimacy and validity of the use of drones in the monitoring of forest crops and ecosystems.