No Cover Image

Journal article 598 views 127 downloads

Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking

Wu Yan, Zhihao Xu, Xuefeng Zhou, Qianxing Su, Shuai Li Orcid Logo, Hongmin Wu

IEEE Access, Volume: 8, Pages: 63055 - 63064

Swansea University Author: Shuai Li Orcid Logo

  • 54162.pdf

    PDF | Version of Record

    This work is licensed under a Creative Commons Attribution 4.0 License.

    Download (1.79MB)

Check full text

DOI (Published version): 10.1109/access.2020.2983173

Abstract

Robotic bin-picking is a common process in modern manufacturing, logistics, and warehousing that aims to pick-up known or unknown objects with random poses out of a bin by using a robot-camera system. Rapid and accurate object pose estimation pipelines have become an escalating issue for robot picki...

Full description

Published in: IEEE Access
ISSN: 2169-3536
Published: Institute of Electrical and Electronics Engineers (IEEE) 2020
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa54162
first_indexed 2020-05-07T13:33:58Z
last_indexed 2020-10-21T03:06:01Z
id cronfa54162
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2020-10-20T15:30:21.1922684</datestamp><bib-version>v2</bib-version><id>54162</id><entry>2020-05-07</entry><title>Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking</title><swanseaauthors><author><sid>42ff9eed09bcd109fbbe484a0f99a8a8</sid><ORCID>0000-0001-8316-5289</ORCID><firstname>Shuai</firstname><surname>Li</surname><name>Shuai Li</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2020-05-07</date><deptcode>ACEM</deptcode><abstract>Robotic bin-picking is a common process in modern manufacturing, logistics, and warehousing that aims to pick-up known or unknown objects with random poses out of a bin by using a robot-camera system. Rapid and accurate object pose estimation pipelines have become an escalating issue for robot picking in recent years. In this paper, a fast 6-DoF (degrees of freedom) pose estimation pipeline for random bin-picking is proposed in which the pipeline is capable of recognizing different types of objects in various cluttered scenarios and uses an adaptive threshold segment strategy to accelerate estimation and matching for the robot picking task. Particularly, our proposed method can be effectively trained with fewer samples by introducing the geometric properties of objects such as contour, normal distribution, and curvature. An experimental setup is designed with a Kinova 6-Dof robot and an Ensenso industrial 3D camera for evaluating our proposed methods with respect to four different objects. The results indicate that our proposed method achieves a 91.25% average success rate and a 0.265s average estimation time, which sufficiently demonstrates that our approach provides competitive results for fast objects pose estimation and can be applied to robotic random bin-picking tasks.</abstract><type>Journal Article</type><journal>IEEE Access</journal><volume>8</volume><paginationStart>63055</paginationStart><paginationEnd>63064</paginationEnd><publisher>Institute of Electrical and Electronics Engineers (IEEE)</publisher><issnElectronic>2169-3536</issnElectronic><keywords/><publishedDay>15</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2020</publishedYear><publishedDate>2020-04-15</publishedDate><doi>10.1109/access.2020.2983173</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-10-20T15:30:21.1922684</lastEdited><Created>2020-05-07T10:34:24.6420531</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Wu</firstname><surname>Yan</surname><order>1</order></author><author><firstname>Zhihao</firstname><surname>Xu</surname><order>2</order></author><author><firstname>Xuefeng</firstname><surname>Zhou</surname><order>3</order></author><author><firstname>Qianxing</firstname><surname>Su</surname><order>4</order></author><author><firstname>Shuai</firstname><surname>Li</surname><orcid>0000-0001-8316-5289</orcid><order>5</order></author><author><firstname>Hongmin</firstname><surname>Wu</surname><order>6</order></author></authors><documents><document><filename>54162__17201__56cac41413d447ca840944c074439be2.pdf</filename><originalFilename>54162.pdf</originalFilename><uploaded>2020-05-07T10:38:41.7227470</uploaded><type>Output</type><contentLength>1876472</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>This work is licensed under a Creative Commons Attribution 4.0 License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2020-10-20T15:30:21.1922684 v2 54162 2020-05-07 Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking 42ff9eed09bcd109fbbe484a0f99a8a8 0000-0001-8316-5289 Shuai Li Shuai Li true false 2020-05-07 ACEM Robotic bin-picking is a common process in modern manufacturing, logistics, and warehousing that aims to pick-up known or unknown objects with random poses out of a bin by using a robot-camera system. Rapid and accurate object pose estimation pipelines have become an escalating issue for robot picking in recent years. In this paper, a fast 6-DoF (degrees of freedom) pose estimation pipeline for random bin-picking is proposed in which the pipeline is capable of recognizing different types of objects in various cluttered scenarios and uses an adaptive threshold segment strategy to accelerate estimation and matching for the robot picking task. Particularly, our proposed method can be effectively trained with fewer samples by introducing the geometric properties of objects such as contour, normal distribution, and curvature. An experimental setup is designed with a Kinova 6-Dof robot and an Ensenso industrial 3D camera for evaluating our proposed methods with respect to four different objects. The results indicate that our proposed method achieves a 91.25% average success rate and a 0.265s average estimation time, which sufficiently demonstrates that our approach provides competitive results for fast objects pose estimation and can be applied to robotic random bin-picking tasks. Journal Article IEEE Access 8 63055 63064 Institute of Electrical and Electronics Engineers (IEEE) 2169-3536 15 4 2020 2020-04-15 10.1109/access.2020.2983173 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University 2020-10-20T15:30:21.1922684 2020-05-07T10:34:24.6420531 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Wu Yan 1 Zhihao Xu 2 Xuefeng Zhou 3 Qianxing Su 4 Shuai Li 0000-0001-8316-5289 5 Hongmin Wu 6 54162__17201__56cac41413d447ca840944c074439be2.pdf 54162.pdf 2020-05-07T10:38:41.7227470 Output 1876472 application/pdf Version of Record true This work is licensed under a Creative Commons Attribution 4.0 License. true eng https://creativecommons.org/licenses/by/4.0/
title Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking
spellingShingle Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking
Shuai Li
title_short Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking
title_full Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking
title_fullStr Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking
title_full_unstemmed Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking
title_sort Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking
author_id_str_mv 42ff9eed09bcd109fbbe484a0f99a8a8
author_id_fullname_str_mv 42ff9eed09bcd109fbbe484a0f99a8a8_***_Shuai Li
author Shuai Li
author2 Wu Yan
Zhihao Xu
Xuefeng Zhou
Qianxing Su
Shuai Li
Hongmin Wu
format Journal article
container_title IEEE Access
container_volume 8
container_start_page 63055
publishDate 2020
institution Swansea University
issn 2169-3536
doi_str_mv 10.1109/access.2020.2983173
publisher Institute of Electrical and Electronics Engineers (IEEE)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str 1
active_str 0
description Robotic bin-picking is a common process in modern manufacturing, logistics, and warehousing that aims to pick-up known or unknown objects with random poses out of a bin by using a robot-camera system. Rapid and accurate object pose estimation pipelines have become an escalating issue for robot picking in recent years. In this paper, a fast 6-DoF (degrees of freedom) pose estimation pipeline for random bin-picking is proposed in which the pipeline is capable of recognizing different types of objects in various cluttered scenarios and uses an adaptive threshold segment strategy to accelerate estimation and matching for the robot picking task. Particularly, our proposed method can be effectively trained with fewer samples by introducing the geometric properties of objects such as contour, normal distribution, and curvature. An experimental setup is designed with a Kinova 6-Dof robot and an Ensenso industrial 3D camera for evaluating our proposed methods with respect to four different objects. The results indicate that our proposed method achieves a 91.25% average success rate and a 0.265s average estimation time, which sufficiently demonstrates that our approach provides competitive results for fast objects pose estimation and can be applied to robotic random bin-picking tasks.
published_date 2020-04-15T02:08:44Z
_version_ 1822366079128698880
score 11.048453

Similar Items