Automatic symmetry plane estimation of bilateral objects in point clouds

Benoit Combes*, Robin Hennessy, John Waddington, Neil Roberts, Sylvain Prima

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, the problem of estimating automatically the symmetry plane of bilateral objects (having perfect or imperfect mirror symmetry) in point clouds is reexamined. Classical methods, mostly based on the ICP algorithm, are shown to be limited and complicated by an inappropriate parameterization of the problem. First, we show how an adequate parameterization, used in an ICP-like scheme, can lead to a simpler, more accurate and faster algorithm. Then, using this parameterization, we reinterpret the problem in a probabilistic framework, and use the maximum likelihood principle to define the optimal symmetry plane. This problem can be solved efficiently using an EM algorithm. The resulting iterative scheme can be seen as an ICP-like algorithm with multiple matches between the two sides of the object. This new algorithm, implemented using a multiscale, multiresolution approach, is evaluated in terms of accuracy, robustness and speed on ground truth data, and some results on real data are presented.

Original languageEnglish
Title of host publication2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12
Place of PublicationNEW YORK
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages2046-2053
Number of pages8
ISBN (Print)978-1-4244-2242-5
Publication statusPublished - 2008
EventIEEE Conference on Computer Vision and Pattern Recognition - Anchorage, United Kingdom
Duration: 23 Jun 200828 Jun 2008

Publication series

NamePROCEEDINGS - IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
PublisherIEEE
ISSN (Print)1063-6919

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition
Country/TerritoryUnited Kingdom
Period23/06/0828/06/08

Keywords

  • CLOSED-FORM SOLUTION
  • FACE AUTHENTICATION
  • ALGORITHM
  • REGISTRATION
  • RECOGNITION
  • IMAGES

Fingerprint

Dive into the research topics of 'Automatic symmetry plane estimation of bilateral objects in point clouds'. Together they form a unique fingerprint.

Cite this