Feature-based quality evaluation of 3D heterogeneous data registration

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

Abstract

The production of 3D realistic map databases is a matter of increasing interest. An approach based on the fusion of heterogeneous 3D representations was studied in previous works. Three methods of rigid registration were tested as well as the behaviors of those algorithms. One of the most difficult problems is the quantitative evaluation of 3D registration. In this term we propose a new quantitative evaluation method based on reference features comparison to improve and compare the accuracy of the registration methods.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Three-Dimensional Image Processing (3DIP) and Applications
DOIs
Publication statusPublished - 22 Mar 2010
Externally publishedYes
EventThree-Dimensional Image Processing (3DIP) and Applications - San Jose, CA, United States
Duration: 18 Jan 201019 Jan 2010

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7526
ISSN (Print)0277-786X

Conference

ConferenceThree-Dimensional Image Processing (3DIP) and Applications
Country/TerritoryUnited States
CitySan Jose, CA
Period18/01/1019/01/10

Keywords

  • 3D registration
  • DSM
  • FB-evaluation
  • ICP
  • Mobile mapping systems
  • Point clouds
  • RANSAC

Fingerprint

Dive into the research topics of 'Feature-based quality evaluation of 3D heterogeneous data registration'. Together they form a unique fingerprint.

Cite this