Sliding window based landmark extraction for indoor 2D SLAM using forward-looking monocular camera

Heewon Chae, Chansoo Park, Jae Bok Song

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

2 Citations (Scopus)

Abstract

In this study, we propose a method to extract landmarks for pose-graph SLAM using only the forward-looking monocular camera mounted in a small mobile robot. By using the sliding window approach, the region of interest is determined to triangulate the landmarks. The landmark extraction process uses multiple sets of bearing information for triangulation. As the landmark is extracted, choose the landmark which is near the navigation plane to project into the 2D landmark node. To test its accuracy, the laser rangefinder is used as a ground truth. Also the various sliding window sizes are tried for a landmark to investigate the effect of the window size on the accuracy. Using this approach as landmark extraction for the SLAM algorithm, we expect to implement monocular based metric SLAM with the graph based back-end optimization.

Original languageEnglish
Title of host publicationICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages336-341
Number of pages6
ISBN (Electronic)9788993215090
DOIs
Publication statusPublished - 2015 Dec 23
Event15th International Conference on Control, Automation and Systems, ICCAS 2015 - Busan, Korea, Republic of
Duration: 2015 Oct 132015 Oct 16

Publication series

NameICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings

Other

Other15th International Conference on Control, Automation and Systems, ICCAS 2015
Country/TerritoryKorea, Republic of
CityBusan
Period15/10/1315/10/16

Keywords

  • Epipolar geometry
  • forward camera
  • monocular SLAM
  • sliding window

ASJC Scopus subject areas

  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Sliding window based landmark extraction for indoor 2D SLAM using forward-looking monocular camera'. Together they form a unique fingerprint.

Cite this