skip to main content
10.1145/3663976.3663984acmotherconferencesArticle/Chapter ViewAbstractPublication PagescvipprConference Proceedingsconference-collections
research-article

Research on Model-Free 6D Object Pose Estimation Based on Vision 3D Matching

Published: 27 June 2024 Publication History

Abstract

6D object pose estimation is a crucial and fundamental task in the field of human-robot interaction. Existing visual target localization methods either need to rely on an additional depth camera to obtain spatial information of the target object or need to resort to a specific CAD model, which leads to high cost and poor adaptability of pose estimation. In this paper, we propose a 6D pose estimation method for objects based on RGB images and without CAD models, starting from the 3D reconstruction of objects. First, this paper constructs a sparse model of the target object by simple RGB scanning, then, 2D key points in the image are matched with 3D points in the object model using a feature-matching network, and finally, to alleviate the poor matching of such methods on low-resolution images, we introduce a 2D-3D-3D key points matching method, which achieves efficient and robust object 6D pose estimation results. Experimental results on the Onepose dataset demonstrate the accuracy and robustness of the method.

References

[1]
[1] Gattullo M, Scurati G W, Fiorentino M, et al. Towards augmented reality manuals for industry 4.0: A methodology[J]. robotics and computer-integrated manufacturing, 2019, 56: 276-286.
[2]
[2] Tang F, Wu Y, Hou X, et al. 3D mapping and 6D pose computation for real time augmented reality on cylindrical objects[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2019, 30(9): 2887-2899.
[3]
[3] Costanzo M, De Simone M, Federico S, et al. Enhanced 6d pose estimation for robotic fruit picking[C]//2023 9th International Conference on Control, Decision and Information Technologies (CoDIT). IEEE, 2023: 901-906.
[4]
[4] Wu D, Zhuang Z, Xiang C, et al. 6d-vnet: End-to-end 6-dof vehicle pose estimation from monocular rgb images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019.
[5]
[5] Grigorescu S, Trasnea B, Cocias T, et al. A survey of deep learning techniques for autonomous driving[J]. Journal of field robotics, 2020, 37(3): 362-386.
[6]
[6] Chowdhury A B, Li J, Cappelleri D J. Neural Network-Based Pose Estimation Approaches for Mobile Manipulation[J]. Journal of Mechanisms and Robotics, 2023, 15(1): 011009.
[7]
[7] Wang G, Manhardt F, Tombari F, et al. Gdr-net: Geometry-guided direct regression network for monocular 6d object pose estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 16611-16621.
[8]
[8] He Y, Sun W, Huang H, et al. Pvn3d: A deep point-wise 3d keypoints voting network for 6dof pose estimation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 11632-11641.
[9]
[9] Gonzalez M, Kacete A, Murienne A, et al. L6dnet: Light 6 DoF network for robust and precise object pose estimation with small datasets[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 2914-2921.
[10]
[10] Peng S, Liu Y, Huang Q, et al. Pvnet: Pixel-wise voting network for 6dof pose estimation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 4561-4570.
[11]
[11] Sun J, Wang Z, Zhang S, et al. Onepose: One-shot object pose estimation without cad models[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 6825-6834.
[12]
[12] Xiang Y, Schmidt T, Narayanan V, et al. Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes[J]. arXiv preprint arXiv:1711.00199, 2017.
[13]
[13] Trabelsi A, Chaabane M, Blanchard N, et al. A pose proposal and refinement network for better 6d object pose estimation[C]//Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2021: 2382-2391.
[14]
[14] Xu Y, Lin K Y, Zhang G, et al. Rnnpose: Recurrent 6-dof object pose refinement with robust correspondence field estimation and pose optimization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 14880-14890.
[15]
[15] Cao T, Luo F, Fu Y, et al. DGECN: A depth-guided edge convolutional network for end-to-end 6D pose estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 3783-3792.
[16]
[16] Jiang X, Li D, Chen H, et al. Uni6d: A unified cnn framework without projection breakdown for 6d pose estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 11174-11184.
[17]
[17] Wang H, Sridhar S, Huang J, et al. Normalized object coordinate space for category-level 6d object pose and size estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 2642-2651.
[18]
[18] Lin H, Liu Z, Cheang C, et al. Sar-net: Shape alignment and recovery network for category-level 6d object pose and size estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 6707-6717.
[19]
[19] Shi Y, Huang J, Xu X, et al. Stablepose: Learning 6d object poses from geometrically stable patches[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 15222-15231.
[20]
[20] Schonberger J L, Frahm J M. Structure-from-motion revisited[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 4104-4113.
[21]
[21] Jocher G, Stoken A, Borovec J, et al. ultralytics/yolov5: v5. 0-YOLOv5-P6 1280 models, AWS, Supervise. ly and YouTube integrations[J]. Zenodo, 2021.

Index Terms

  1. Research on Model-Free 6D Object Pose Estimation Based on Vision 3D Matching

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    CVIPPR '24: Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition
    April 2024
    373 pages
    ISBN:9798400716607
    DOI:10.1145/3663976
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 27 June 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. 6D Object Pose Estimation
    2. Key Points Matching
    3. Modeling
    4. RGB

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Funding Sources

    • the Support Plan for Leading Innovation Team of Dalian University
    • the Key Project of NSFC
    • 111 Project
    • the Science and Technology Innovation Fund of Dalian
    • the Scientifc Research Funds of Education Department of Liaoning Province
    • the Support Plan for Key Field Innovation Team of Dalian
    • the Program for Innovative Research Team in University of Liaoning Province

    Conference

    CVIPPR 2024

    Acceptance Rates

    Overall Acceptance Rate 14 of 38 submissions, 37%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 38
      Total Downloads
    • Downloads (Last 12 months)38
    • Downloads (Last 6 weeks)8
    Reflects downloads up to 20 Jan 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media