Jin, Y., Rossiter, J.A. orcid.org/0000-0002-1336-0633 and Veres, S.M. (2021) Accurate 6D object pose estimation and refinement in cluttered scenes. In: Galambos, P. and Kayacan, E., (eds.) Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems. 2nd International Conference on Robotics, Computer Vision and Intelligent Systems (ROBOVIS 2021), 27-28 Oct 2021, Virtual conference. SCITEPRESS Digital Library , pp. 31-39. ISBN 9789897585371
Abstract
Estimating the 6D pose of objects is an essential part of a robot’s ability to perceive their environment. This paper proposes a method for detecting a known object and estimating its 6D pose from a single RGB image. Unlike most of the state-of-the-art methods that deploy PnP algorithms for estimating 6D pose, the method here can output the 6D pose in one step. In order to obtain estimation accuracy that is comparable to RGB-D based methods, an efficient refinement algorithm, called contour alignment (CA), is presented; this can increase the predicted 6D pose accuracy significantly. We evaluate the new method in two widely used benchmarks, LINEMOD for single object pose estimation and Occlusion-LINEMOD for multiple objects pose estimation. The experiments show that the proposed method surpasses other state-of-the-art prediction approaches.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2021 by SCITEPRESS – Science and Technology Publications, Lda. This is an author-produced version of a paper subsequently published in Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | 6D Pose Estimation; 3D Robotic Vision; 3D Object detection |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) |
Funding Information: | Funder Grant number Engineering and Physical Sciences Research Council EP/R026084/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 20 Aug 2021 12:41 |
Last Modified: | 29 Apr 2022 06:55 |
Status: | Published |
Publisher: | SCITEPRESS Digital Library |
Refereed: | Yes |
Identification Number: | 10.5220/0010654500003061 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:177010 |