Efficiency improvement of sfm using image blocks for infrastructure inspection

Masafumi Nakagawa; Keiichi Miwa; Shoya Nozue; Yasushi Sekiguchi; Katsuharu Hirate; Yasuaki Noda; Masahiro Miyo

Efficiency improvement of sfm using image blocks for infrastructure inspection

Masafumi Nakagawa, Keiichi Miwa, Shoya Nozue, Yasushi Sekiguchi, Katsuharu Hirate, Yasuaki Noda, Masahiro Miyo

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

Abstract

We focused on the efficiency improvement of Structure from Motion (SfM) for infrastructure inspection using close- and long-range images taken from various viewpoints. We also focused on the camera network optimization using a matching matrix with ordered image blocks. Our methodology consists of three steps: image block preparation, key image-pair estimation using a matching matrix, and point-cloud reconstruction. We have confirmed that our proposed methodology can improve the efficiency of SfM through three preliminary experiments and four experiments in outdoor environments.

Original language	English
Publication status	Published - 2017
Event	38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017 - New Delhi, India Duration: 2017 Oct 23 → 2017 Oct 27

Other

Other	38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017
Country/Territory	India
City	New Delhi
Period	17/10/23 → 17/10/27

Keywords

Image matching
Infrastructure inspection
Multiview stereo
Point cloud
Structure from Motion

ASJC Scopus subject areas

Computer Networks and Communications

Cite this

@conference{9bb8afcaf7024639a8c18aecc27b5e84,

title = "Efficiency improvement of sfm using image blocks for infrastructure inspection",

abstract = "We focused on the efficiency improvement of Structure from Motion (SfM) for infrastructure inspection using close- and long-range images taken from various viewpoints. We also focused on the camera network optimization using a matching matrix with ordered image blocks. Our methodology consists of three steps: image block preparation, key image-pair estimation using a matching matrix, and point-cloud reconstruction. We have confirmed that our proposed methodology can improve the efficiency of SfM through three preliminary experiments and four experiments in outdoor environments.",

keywords = "Image matching, Infrastructure inspection, Multiview stereo, Point cloud, Structure from Motion",

author = "Masafumi Nakagawa and Keiichi Miwa and Shoya Nozue and Yasushi Sekiguchi and Katsuharu Hirate and Yasuaki Noda and Masahiro Miyo",

note = "Funding Information: This work was supported by Japan Construction Information Center (JACIC). Publisher Copyright: {\textcopyright} 2017 ACRS. All rights reserved. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.; 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017 ; Conference date: 23-10-2017 Through 27-10-2017",

year = "2017",

language = "English",

}

TY - CONF

T1 - Efficiency improvement of sfm using image blocks for infrastructure inspection

AU - Nakagawa, Masafumi

AU - Miwa, Keiichi

AU - Nozue, Shoya

AU - Sekiguchi, Yasushi

AU - Hirate, Katsuharu

AU - Noda, Yasuaki

AU - Miyo, Masahiro

N1 - Funding Information: This work was supported by Japan Construction Information Center (JACIC). Publisher Copyright: © 2017 ACRS. All rights reserved. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2017

Y1 - 2017

N2 - We focused on the efficiency improvement of Structure from Motion (SfM) for infrastructure inspection using close- and long-range images taken from various viewpoints. We also focused on the camera network optimization using a matching matrix with ordered image blocks. Our methodology consists of three steps: image block preparation, key image-pair estimation using a matching matrix, and point-cloud reconstruction. We have confirmed that our proposed methodology can improve the efficiency of SfM through three preliminary experiments and four experiments in outdoor environments.

AB - We focused on the efficiency improvement of Structure from Motion (SfM) for infrastructure inspection using close- and long-range images taken from various viewpoints. We also focused on the camera network optimization using a matching matrix with ordered image blocks. Our methodology consists of three steps: image block preparation, key image-pair estimation using a matching matrix, and point-cloud reconstruction. We have confirmed that our proposed methodology can improve the efficiency of SfM through three preliminary experiments and four experiments in outdoor environments.

KW - Image matching

KW - Infrastructure inspection

KW - Multiview stereo

KW - Point cloud

KW - Structure from Motion

UR - http://www.scopus.com/inward/record.url?scp=85047405622&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047405622&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85047405622

T2 - 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017

Y2 - 23 October 2017 through 27 October 2017

ER -

Efficiency improvement of sfm using image blocks for infrastructure inspection

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this