Robust loop closures for scene reconstruction by combining odometry and visual correspondences

Zakaria Laskar, Sami Huttunen, Daniel Herrera C, Esa Rahtu, Juho Kannala

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

4 Citations (Scopus)

Abstract

Given an image sequence and odometry from a moving camera, we propose a batch-based approach for robust reconstruction of scene structure and camera motion. A key part of our method is robust loop closure disambiguation. First, a structure-from-motion pipeline is used to get a set of candidate feature correspondences and the respective triangulated 3D landmarks. Thereafter, the compatibility of each correspondence constraint and the odometry is evaluated in a bundle-adjustment optimization, where only compatible constraints affect. Our approach is evaluated using data from a Google Tango device. The results show that it produces better reconstructions than the device's built-in software or a state-of-the-art pose-graph formulation.
Original languageEnglish
Title of host publication2016 IEEE International Conference on Image Processing (ICIP)
PublisherIEEE
Pages2603-2607
Number of pages5
ISBN (Electronic)978-1-4673-9961-6
ISBN (Print)978-1-4673-9962-3
DOIs
Publication statusPublished - 19 Aug 2016
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Image Processing - Phoenix, United States
Duration: 25 Sep 201628 Sep 2016
Conference number: 23

Publication series

NameProceedings : International Conference on Image Processing
PublisherIEEE
ISSN (Print)1522-4880
ISSN (Electronic)2381-8549

Conference

ConferenceIEEE International Conference on Image Processing
Abbreviated titleICIP
CountryUnited States
CityPhoenix
Period25/09/201628/09/2016

Keywords

  • loop closures
  • SLAM
  • 3D reconstruction

Fingerprint Dive into the research topics of 'Robust loop closures for scene reconstruction by combining odometry and visual correspondences'. Together they form a unique fingerprint.

  • Cite this

    Laskar, Z., Huttunen, S., Herrera C, D., Rahtu, E., & Kannala, J. (2016). Robust loop closures for scene reconstruction by combining odometry and visual correspondences. In 2016 IEEE International Conference on Image Processing (ICIP) (pp. 2603-2607). (Proceedings : International Conference on Image Processing). IEEE. https://doi.org/10.1109/ICIP.2016.7532830