Keyframe and inlier selection for visual SLAM

John Stalbaum, Jae-Bok Song

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

4 Citations (Scopus)

Abstract

Using stereo cameras to perform Simultaneous Localization and Mapping (SLAM) is an active area of mobile robotics research with many applications. Regardless of which SLAM algorithm is used for an application, the quality of the results depends heavily on the quality and consistency of the data going into the algorithm. In this study, a novel algorithm for inlier and keyframe selection is used to produce sets of observations that can be used to perform SLAM. Several simulations are performed using data sets captured in large outdoor environments, and the results are evaluated in terms of physical consistency, covisibility between frames, and SLAM results. The results obtained from these simulations suggest that the algorithm can be useful in the implementation of SLAM.

Original languageEnglish
Title of host publication2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013
PublisherIEEE Computer Society
Pages391-396
Number of pages6
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013 - Jeju, Korea, Republic of
Duration: 2013 Oct 302013 Nov 2

Other

Other2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013
CountryKorea, Republic of
CityJeju
Period13/10/3013/11/2

Fingerprint

Robotics
Cameras

Keywords

  • bundle adjustment
  • inlier selection
  • keyframe selection
  • SLAM
  • visual feature extaction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Stalbaum, J., & Song, J-B. (2013). Keyframe and inlier selection for visual SLAM. In 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013 (pp. 391-396). [6677295] IEEE Computer Society. https://doi.org/10.1109/URAI.2013.6677295

Keyframe and inlier selection for visual SLAM. / Stalbaum, John; Song, Jae-Bok.

2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013. IEEE Computer Society, 2013. p. 391-396 6677295.

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

Stalbaum, J & Song, J-B 2013, Keyframe and inlier selection for visual SLAM. in 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013., 6677295, IEEE Computer Society, pp. 391-396, 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013, Jeju, Korea, Republic of, 13/10/30. https://doi.org/10.1109/URAI.2013.6677295
Stalbaum J, Song J-B. Keyframe and inlier selection for visual SLAM. In 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013. IEEE Computer Society. 2013. p. 391-396. 6677295 https://doi.org/10.1109/URAI.2013.6677295
Stalbaum, John ; Song, Jae-Bok. / Keyframe and inlier selection for visual SLAM. 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013. IEEE Computer Society, 2013. pp. 391-396
@inproceedings{2c6835d6922f4f33895eb8fb775d9aab,
title = "Keyframe and inlier selection for visual SLAM",
abstract = "Using stereo cameras to perform Simultaneous Localization and Mapping (SLAM) is an active area of mobile robotics research with many applications. Regardless of which SLAM algorithm is used for an application, the quality of the results depends heavily on the quality and consistency of the data going into the algorithm. In this study, a novel algorithm for inlier and keyframe selection is used to produce sets of observations that can be used to perform SLAM. Several simulations are performed using data sets captured in large outdoor environments, and the results are evaluated in terms of physical consistency, covisibility between frames, and SLAM results. The results obtained from these simulations suggest that the algorithm can be useful in the implementation of SLAM.",
keywords = "bundle adjustment, inlier selection, keyframe selection, SLAM, visual feature extaction",
author = "John Stalbaum and Jae-Bok Song",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/URAI.2013.6677295",
language = "English",
pages = "391--396",
booktitle = "2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Keyframe and inlier selection for visual SLAM

AU - Stalbaum, John

AU - Song, Jae-Bok

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Using stereo cameras to perform Simultaneous Localization and Mapping (SLAM) is an active area of mobile robotics research with many applications. Regardless of which SLAM algorithm is used for an application, the quality of the results depends heavily on the quality and consistency of the data going into the algorithm. In this study, a novel algorithm for inlier and keyframe selection is used to produce sets of observations that can be used to perform SLAM. Several simulations are performed using data sets captured in large outdoor environments, and the results are evaluated in terms of physical consistency, covisibility between frames, and SLAM results. The results obtained from these simulations suggest that the algorithm can be useful in the implementation of SLAM.

AB - Using stereo cameras to perform Simultaneous Localization and Mapping (SLAM) is an active area of mobile robotics research with many applications. Regardless of which SLAM algorithm is used for an application, the quality of the results depends heavily on the quality and consistency of the data going into the algorithm. In this study, a novel algorithm for inlier and keyframe selection is used to produce sets of observations that can be used to perform SLAM. Several simulations are performed using data sets captured in large outdoor environments, and the results are evaluated in terms of physical consistency, covisibility between frames, and SLAM results. The results obtained from these simulations suggest that the algorithm can be useful in the implementation of SLAM.

KW - bundle adjustment

KW - inlier selection

KW - keyframe selection

KW - SLAM

KW - visual feature extaction

UR - http://www.scopus.com/inward/record.url?scp=84899102011&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899102011&partnerID=8YFLogxK

U2 - 10.1109/URAI.2013.6677295

DO - 10.1109/URAI.2013.6677295

M3 - Conference contribution

SP - 391

EP - 396

BT - 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013

PB - IEEE Computer Society

ER -