An ıntelligent system for detecting Mediterranean fruit fly [Medfly; Ceratitis Capitata (Wiedemann)]

IF 2.4 4区 农林科学 Q2 AGRICULTURAL ENGINEERING
Yusuf Uzun, M. Tolun, H. Eyyuboğlu, Filiz Sari
{"title":"An ıntelligent system for detecting Mediterranean fruit fly [Medfly; Ceratitis Capitata (Wiedemann)]","authors":"Yusuf Uzun, M. Tolun, H. Eyyuboğlu, Filiz Sari","doi":"10.4081/jae.2022.1381","DOIUrl":null,"url":null,"abstract":"Nowadays, the most critical agriculture-related problem is the harm caused in fruit, vegetable, nut, and flower crops by harmful pests, particularly the Mediterranean fruit fly, Ceratitis capitata, named in short as Medfly. Medfly existence in agricultural fields must be monitored systematically for effective combat against it. Special traps are utilized in the field to catch Medflies which will reveal their presence, and applying pesticides at the right time will help reduce their population. A technologically supported automated remote monitoring system should eliminate frequent site visits as a more economical solution. In this paper, a machine learning system that can detect Medfly images on a picture and count their numbers is developed. A special trap equipped with an integrated camera that can take photos of the sticky band where Medflies are caught daily is utilized. Obtained pictures are then transmitted by an electronic circuit containing a SIM card to the central server where the object detection algorithm runs. This study employs a faster region-based convolutional neural network (Faster R-CNN) model in identifying trapped Medflies. When Medflies or other insects stick on the sticky band of the trap, they continue to spend extraordinary effort trying to release themselves in a panic until they die. Therefore, their shape is badly distorted as their bodies, wings, and legs are all buckled. The challenge here is that the machine learning system should detect these Medflies of distorted shape with high accuracy. Therefore, it is crucial to utilize pictures that contain trapped Medfly images that possess distorted shapes for training and validation. In this paper, the success rate in identifying Medflies when other insects are also present is approximately 94% that is achieved by the machine learning system training process, owing to the considerable amount of purpose-specific photographic data. This rate may be seen as quite favorable when compared to the success rates provided in the literature.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"117 1","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Agricultural Engineering","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.4081/jae.2022.1381","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AGRICULTURAL ENGINEERING","Score":null,"Total":0}
引用次数: 2

Abstract

Nowadays, the most critical agriculture-related problem is the harm caused in fruit, vegetable, nut, and flower crops by harmful pests, particularly the Mediterranean fruit fly, Ceratitis capitata, named in short as Medfly. Medfly existence in agricultural fields must be monitored systematically for effective combat against it. Special traps are utilized in the field to catch Medflies which will reveal their presence, and applying pesticides at the right time will help reduce their population. A technologically supported automated remote monitoring system should eliminate frequent site visits as a more economical solution. In this paper, a machine learning system that can detect Medfly images on a picture and count their numbers is developed. A special trap equipped with an integrated camera that can take photos of the sticky band where Medflies are caught daily is utilized. Obtained pictures are then transmitted by an electronic circuit containing a SIM card to the central server where the object detection algorithm runs. This study employs a faster region-based convolutional neural network (Faster R-CNN) model in identifying trapped Medflies. When Medflies or other insects stick on the sticky band of the trap, they continue to spend extraordinary effort trying to release themselves in a panic until they die. Therefore, their shape is badly distorted as their bodies, wings, and legs are all buckled. The challenge here is that the machine learning system should detect these Medflies of distorted shape with high accuracy. Therefore, it is crucial to utilize pictures that contain trapped Medfly images that possess distorted shapes for training and validation. In this paper, the success rate in identifying Medflies when other insects are also present is approximately 94% that is achieved by the machine learning system training process, owing to the considerable amount of purpose-specific photographic data. This rate may be seen as quite favorable when compared to the success rates provided in the literature.
地中海果蝇检测ıntelligent系统[Medfly;头角性角膜炎[
如今,与农业相关的最关键问题是有害害虫对水果、蔬菜、坚果和花卉作物造成的危害,特别是地中海果蝇,Ceratitis capitata,简称Medfly。为有效防治田间蝇类,必须对田间蝇类的存在进行系统监测。在田间使用特殊的捕蝇器捕捉梅德梅蝇,以便发现它们的存在,并在适当的时候施用杀虫剂,有助于减少梅德梅蝇的数量。有技术支持的自动远程监测系统应能消除频繁的实地视察,这是一种更经济的解决办法。本文开发了一种能够检测图像上Medfly图像并对其计数的机器学习系统。一个特殊的陷阱配备了一个集成的相机,可以拍摄粘带的照片,每天捕捉medfly。然后,通过包含SIM卡的电子电路将获得的图像传输到对象检测算法运行的中央服务器。本研究采用更快的基于区域的卷积神经网络(faster R-CNN)模型识别被困medfly。当medfly或其他昆虫粘在捕蝇器的粘带上时,它们会在恐慌中继续花费巨大的努力试图释放自己,直到它们死去。因此,它们的形状严重扭曲,身体、翅膀和腿都被扣住了。这里的挑战是机器学习系统应该以高精度检测这些变形形状的medfly。因此,至关重要的是利用包含被困Medfly图像的图像,这些图像具有扭曲的形状,用于训练和验证。在本文中,当其他昆虫也存在时,识别medfly的成功率约为94%,这是通过机器学习系统的训练过程实现的,因为有相当数量的特定目的的照片数据。与文献中提供的成功率相比,这一比率可能被视为相当有利。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Agricultural Engineering
Journal of Agricultural Engineering AGRICULTURAL ENGINEERING-
CiteScore
2.30
自引率
5.60%
发文量
40
审稿时长
10 weeks
期刊介绍: The Journal of Agricultural Engineering (JAE) is the official journal of the Italian Society of Agricultural Engineering supported by University of Bologna, Italy. The subject matter covers a complete and interdisciplinary range of research in engineering for agriculture and biosystems.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信