Keyframe and inlier selection for visual SLAM

John Stalbaum; Jae Bok Song

doi:10.1109/URAI.2013.6677295

Keyframe and inlier selection for visual SLAM

John Stalbaum, Jae Bok Song

School of Mechanical Engineering

Research output: Contribution to conference › Paper › peer-review

9 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 language	English
Pages	391-396
Number of pages	6
DOIs	https://doi.org/10.1109/URAI.2013.6677295
Publication status	Published - 2013
Event	2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013 - Jeju, Korea, Republic of Duration: 2013 Oct 30 → 2013 Nov 2

Other

Other	2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013
Country/Territory	Korea, Republic of
City	Jeju
Period	13/10/30 → 13/11/2

Keywords

SLAM
bundle adjustment
inlier selection
keyframe selection
visual feature extaction

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction

Access to Document

10.1109/URAI.2013.6677295

Cite this

@conference{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 = "SLAM, bundle adjustment, inlier selection, keyframe selection, visual feature extaction",

author = "John Stalbaum and Song, {Jae Bok}",

year = "2013",

doi = "10.1109/URAI.2013.6677295",

language = "English",

pages = "391--396",

note = "2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013 ; Conference date: 30-10-2013 Through 02-11-2013",

}

TY - CONF

T1 - Keyframe and inlier selection for visual SLAM

AU - Stalbaum, John

AU - Song, Jae Bok

PY - 2013

Y1 - 2013

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 - SLAM

KW - bundle adjustment

KW - inlier selection

KW - keyframe selection

KW - visual feature extaction

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

U2 - 10.1109/URAI.2013.6677295

DO - 10.1109/URAI.2013.6677295

M3 - Paper

AN - SCOPUS:84899102011

SP - 391

EP - 396

T2 - 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2013

Y2 - 30 October 2013 through 2 November 2013

ER -

Keyframe and inlier selection for visual SLAM

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this