Comparative Performance Evaluation of One-Stage and Two-Stage Object Detectors for Screw Head Detection and Classification in Disassembly Processes

Bsher Karbouj , Garabet A. Topalian-Rivas , Jörg Krüger
{"title":"Comparative Performance Evaluation of One-Stage and Two-Stage Object Detectors for Screw Head Detection and Classification in Disassembly Processes","authors":"Bsher Karbouj ,&nbsp;Garabet A. Topalian-Rivas ,&nbsp;Jörg Krüger","doi":"10.1016/j.procir.2024.01.077","DOIUrl":null,"url":null,"abstract":"<div><p>The process of manually detecting and removing screws during disassembly can be time-consuming and demanding. Automated systems utilizing imaging and deep learning can rapidly and accurately identify screws based on features like head shape and size. Different deep learning methods have varying screw detection capabilities. Choosing the right method significantly impacts system effectiveness, robustness and efficiency. Several generic deep learning architectures have been proposed to address this problem. However, there is little guidance on their suitability for specific scenarios. This paper aims to provide qualified guidance for selecting suitable deep learning methods for screw head detection. The proposed approach involves researching existing object detection methods and choosing two representatives – one employing a one-stage approach, the other using two-stage. These selected methods will be implemented identically and their performance evaluated via rigorous analysis and comparison. The dataset comprises synthetic and real images of 6 screw types across 3 products. YOLOv5 was selected for one-stage detectors, Faster R-CNN for two-stage. Results show the one-stage YOLOv5 generally outperforms Faster R-CNN in precision, recall, speed and training times, while Faster R-CNN delivered superior recall with smaller training datasets.</p></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2212827124001021/pdf?md5=2dcc3c2afc721c91c94469c20a4f1de1&pid=1-s2.0-S2212827124001021-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Procedia CIRP","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212827124001021","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

The process of manually detecting and removing screws during disassembly can be time-consuming and demanding. Automated systems utilizing imaging and deep learning can rapidly and accurately identify screws based on features like head shape and size. Different deep learning methods have varying screw detection capabilities. Choosing the right method significantly impacts system effectiveness, robustness and efficiency. Several generic deep learning architectures have been proposed to address this problem. However, there is little guidance on their suitability for specific scenarios. This paper aims to provide qualified guidance for selecting suitable deep learning methods for screw head detection. The proposed approach involves researching existing object detection methods and choosing two representatives – one employing a one-stage approach, the other using two-stage. These selected methods will be implemented identically and their performance evaluated via rigorous analysis and comparison. The dataset comprises synthetic and real images of 6 screw types across 3 products. YOLOv5 was selected for one-stage detectors, Faster R-CNN for two-stage. Results show the one-stage YOLOv5 generally outperforms Faster R-CNN in precision, recall, speed and training times, while Faster R-CNN delivered superior recall with smaller training datasets.

用于拆卸过程中螺钉头检测和分类的一级和二级物体检测器的性能比较评估
在拆卸过程中,手动检测和移除螺丝的过程既耗时又费力。利用成像和深度学习的自动化系统可以根据头部形状和尺寸等特征快速准确地识别螺丝。不同的深度学习方法具有不同的螺钉检测能力。选择正确的方法会极大地影响系统的有效性、鲁棒性和效率。为了解决这个问题,已经提出了几种通用的深度学习架构。然而,关于这些方法是否适用于特定场景的指导却很少。本文旨在为选择合适的深度学习方法进行螺钉头检测提供合格的指导。建议的方法包括研究现有的物体检测方法,并选择两种代表方法--一种采用单阶段方法,另一种采用双阶段方法。这些选定的方法将以相同的方式实施,并通过严格的分析和比较对其性能进行评估。数据集包括 3 种产品中 6 种螺钉类型的合成和真实图像。单级检测器选用 YOLOv5,双级检测器选用 Faster R-CNN。结果表明,单级 YOLOv5 在精确度、召回率、速度和训练时间方面普遍优于 Faster R-CNN,而 Faster R-CNN 在较小的训练数据集上也能提供出色的召回率。
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
CiteScore
3.80
自引率
0.00%
发文量
0
×
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