Sheng Yu, Shangzhu Jin, Jun Peng, Zhishu Zhao, Ming Yang Hou, Wenjun Cheng
{"title":"Pest Identification System based on YOLOv5","authors":"Sheng Yu, Shangzhu Jin, Jun Peng, Zhishu Zhao, Ming Yang Hou, Wenjun Cheng","doi":"10.1109/ICCICC53683.2021.9811296","DOIUrl":null,"url":null,"abstract":"Forest pests and diseases are a global problem. The key to control forestry diseases is to accurately identify the species and severity of pests. How to use artificial intelligence and image recognition technology to detect forestry pests is an important challenge and opportunity. This paper presents a new method for forestry pest identification based on YOLOv5 algorithm. In addition, in order to unify the system and expand the flexibility of the future system, we adopted the B/S/S structure to develop the pest identification system. The system uses the camera to shoot images and transmits the data to the background recognition. The experimental results show that our system can detect the target pests more accurately and conveniently, which is helpful for the actual prevention and control of forestry pests.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCICC53683.2021.9811296","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
Forest pests and diseases are a global problem. The key to control forestry diseases is to accurately identify the species and severity of pests. How to use artificial intelligence and image recognition technology to detect forestry pests is an important challenge and opportunity. This paper presents a new method for forestry pest identification based on YOLOv5 algorithm. In addition, in order to unify the system and expand the flexibility of the future system, we adopted the B/S/S structure to develop the pest identification system. The system uses the camera to shoot images and transmits the data to the background recognition. The experimental results show that our system can detect the target pests more accurately and conveniently, which is helpful for the actual prevention and control of forestry pests.