Joint pose and principal curvature refinement using quadrics

Andrew Spek, Tom Drummond

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

Abstract

In this paper we present a novel joint approach for optimising surface curvature and pose alignment. We present two implementations of this joint optimisation strategy, including a fast implementation that uses two frames and an offline multi-frame approach. We demonstrate an order of magnitude improvement in simulation over state of the art dense relative point-to-plane Iterative Closest Point (ICP) pose alignment using our dense joint frame-to-frame approach and show comparable pose drift to dense point-to-plane ICP bundle adjustment using low-cost depth sensors. Additionally our improved joint quadric based approach can be used to more accurately estimate surface curvature on noisy point clouds than previous approaches.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Robotics and Automation (ICRA 2017)
EditorsHaoyong Yu, Zhidong Wang
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages3968-3975
Number of pages8
ISBN (Electronic)9781509046331
ISBN (Print)9781509046338
DOIs
Publication statusPublished - 21 Jul 2017
EventIEEE International Conference on Robotics and Automation 2017 - Sands Expo and Convention Centre, Singapore, Singapore
Duration: 29 May 20173 Jun 2017
http://www.icra2017.org/

Conference

ConferenceIEEE International Conference on Robotics and Automation 2017
Abbreviated titleICRA 2017
CountrySingapore
CitySingapore
Period29/05/173/06/17
Internet address

Cite this

Spek, A., & Drummond, T. (2017). Joint pose and principal curvature refinement using quadrics. In H. Yu, & Z. Wang (Eds.), 2017 IEEE International Conference on Robotics and Automation (ICRA 2017) (pp. 3968-3975). [7989456] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICRA.2017.7989456
Spek, Andrew ; Drummond, Tom. / Joint pose and principal curvature refinement using quadrics. 2017 IEEE International Conference on Robotics and Automation (ICRA 2017). editor / Haoyong Yu ; Zhidong Wang. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 3968-3975
@inproceedings{8adee5b9b3984d88986e848dd05ad1f6,
title = "Joint pose and principal curvature refinement using quadrics",
abstract = "In this paper we present a novel joint approach for optimising surface curvature and pose alignment. We present two implementations of this joint optimisation strategy, including a fast implementation that uses two frames and an offline multi-frame approach. We demonstrate an order of magnitude improvement in simulation over state of the art dense relative point-to-plane Iterative Closest Point (ICP) pose alignment using our dense joint frame-to-frame approach and show comparable pose drift to dense point-to-plane ICP bundle adjustment using low-cost depth sensors. Additionally our improved joint quadric based approach can be used to more accurately estimate surface curvature on noisy point clouds than previous approaches.",
author = "Andrew Spek and Tom Drummond",
year = "2017",
month = "7",
day = "21",
doi = "10.1109/ICRA.2017.7989456",
language = "English",
isbn = "9781509046338",
pages = "3968--3975",
editor = "Haoyong Yu and Zhidong Wang",
booktitle = "2017 IEEE International Conference on Robotics and Automation (ICRA 2017)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Spek, A & Drummond, T 2017, Joint pose and principal curvature refinement using quadrics. in H Yu & Z Wang (eds), 2017 IEEE International Conference on Robotics and Automation (ICRA 2017)., 7989456, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 3968-3975, IEEE International Conference on Robotics and Automation 2017, Singapore, Singapore, 29/05/17. https://doi.org/10.1109/ICRA.2017.7989456

Joint pose and principal curvature refinement using quadrics. / Spek, Andrew; Drummond, Tom.

2017 IEEE International Conference on Robotics and Automation (ICRA 2017). ed. / Haoyong Yu; Zhidong Wang. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 3968-3975 7989456.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Joint pose and principal curvature refinement using quadrics

AU - Spek, Andrew

AU - Drummond, Tom

PY - 2017/7/21

Y1 - 2017/7/21

N2 - In this paper we present a novel joint approach for optimising surface curvature and pose alignment. We present two implementations of this joint optimisation strategy, including a fast implementation that uses two frames and an offline multi-frame approach. We demonstrate an order of magnitude improvement in simulation over state of the art dense relative point-to-plane Iterative Closest Point (ICP) pose alignment using our dense joint frame-to-frame approach and show comparable pose drift to dense point-to-plane ICP bundle adjustment using low-cost depth sensors. Additionally our improved joint quadric based approach can be used to more accurately estimate surface curvature on noisy point clouds than previous approaches.

AB - In this paper we present a novel joint approach for optimising surface curvature and pose alignment. We present two implementations of this joint optimisation strategy, including a fast implementation that uses two frames and an offline multi-frame approach. We demonstrate an order of magnitude improvement in simulation over state of the art dense relative point-to-plane Iterative Closest Point (ICP) pose alignment using our dense joint frame-to-frame approach and show comparable pose drift to dense point-to-plane ICP bundle adjustment using low-cost depth sensors. Additionally our improved joint quadric based approach can be used to more accurately estimate surface curvature on noisy point clouds than previous approaches.

UR - http://www.scopus.com/inward/record.url?scp=85028024654&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2017.7989456

DO - 10.1109/ICRA.2017.7989456

M3 - Conference Paper

AN - SCOPUS:85028024654

SN - 9781509046338

SP - 3968

EP - 3975

BT - 2017 IEEE International Conference on Robotics and Automation (ICRA 2017)

A2 - Yu, Haoyong

A2 - Wang, Zhidong

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Spek A, Drummond T. Joint pose and principal curvature refinement using quadrics. In Yu H, Wang Z, editors, 2017 IEEE International Conference on Robotics and Automation (ICRA 2017). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 3968-3975. 7989456 https://doi.org/10.1109/ICRA.2017.7989456