基于深度学习的水下机器人视觉污染物检测与清洗

He Xu, Siqing Chen, Chen Yang, Xin Li
{"title":"基于深度学习的水下机器人视觉污染物检测与清洗","authors":"He Xu, Siqing Chen, Chen Yang, Xin Li","doi":"10.1109/ROBIO55434.2022.10011807","DOIUrl":null,"url":null,"abstract":"At present, underwater robots are increasingly widely used in the fields of ocean exploration and resource extraction. However, the development of related technologies is not comprehensive enough. Due to the defects of visual algorithm and results, the accuracy and safety of operation under different working conditions cannot be guaranteed. Many researchers pay attention to the development and design of underwater vision technology. In this paper, based on deep learning and binocular vision technology, the underwater tar-get object detection algorithm and the underwater ranging algorithm are established to achieve visual recognition and positioning. Visual decontamination structure are designed to prevent visual occlusion in case of emergency. The accuracy and feasibility of the related techniques are verified by experiments.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Contaminants detection and Cleaning of Underwater Robot Vision Based on Deep Learning\",\"authors\":\"He Xu, Siqing Chen, Chen Yang, Xin Li\",\"doi\":\"10.1109/ROBIO55434.2022.10011807\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"At present, underwater robots are increasingly widely used in the fields of ocean exploration and resource extraction. However, the development of related technologies is not comprehensive enough. Due to the defects of visual algorithm and results, the accuracy and safety of operation under different working conditions cannot be guaranteed. Many researchers pay attention to the development and design of underwater vision technology. In this paper, based on deep learning and binocular vision technology, the underwater tar-get object detection algorithm and the underwater ranging algorithm are established to achieve visual recognition and positioning. Visual decontamination structure are designed to prevent visual occlusion in case of emergency. The accuracy and feasibility of the related techniques are verified by experiments.\",\"PeriodicalId\":151112,\"journal\":{\"name\":\"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)\",\"volume\":\"39 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-12-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ROBIO55434.2022.10011807\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROBIO55434.2022.10011807","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

目前,水下机器人在海洋勘探和资源开采领域的应用越来越广泛。然而,相关技术的发展还不够全面。由于可视化算法和结果的缺陷,无法保证不同工况下操作的准确性和安全性。水下视觉技术的开发与设计受到了众多研究者的关注。本文基于深度学习和双目视觉技术,建立了水下目标物体检测算法和水下测距算法,实现了视觉识别和定位。视觉去污结构的设计是为了防止紧急情况下的视觉阻塞。通过实验验证了相关技术的准确性和可行性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Contaminants detection and Cleaning of Underwater Robot Vision Based on Deep Learning
At present, underwater robots are increasingly widely used in the fields of ocean exploration and resource extraction. However, the development of related technologies is not comprehensive enough. Due to the defects of visual algorithm and results, the accuracy and safety of operation under different working conditions cannot be guaranteed. Many researchers pay attention to the development and design of underwater vision technology. In this paper, based on deep learning and binocular vision technology, the underwater tar-get object detection algorithm and the underwater ranging algorithm are established to achieve visual recognition and positioning. Visual decontamination structure are designed to prevent visual occlusion in case of emergency. The accuracy and feasibility of the related techniques are verified by experiments.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
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