Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas

Masafumi Nakagawa; Ryusei Igusa; Nobuhiro Usuki; Masanori Takigawa; Naoki Nishimura; Yoshiaki Katsumata; Tomoaki Eguchi

Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas

Masafumi Nakagawa, Ryusei Igusa, Nobuhiro Usuki, Masanori Takigawa, Naoki Nishimura, Yoshiaki Katsumata, Tomoaki Eguchi

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

Abstract

Collapse investigations in high mountain areas are generally conducted byfield surveys using handheld digital cameras and tape measures. A presurvey is alsoconducted using processing of aerial images for more efficient surveys. However, identifyingcracks from various edges in aerial images is usually a manual operation. We have proposed amethodology to automate crack detection using multiple aerial images and our knowledge ofcracks. Moreover, we evaluated our methodology through an experiment on crack detectionand classification using multiple aerial images.

Original language	English
Pages	1269-1276
Number of pages	8
Publication status	Published - 2018 Jan 1
Event	39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018 - Kuala Lumpur, Malaysia Duration: 2018 Oct 15 → 2018 Oct 19

Conference

Conference	39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018
Country/Territory	Malaysia
City	Kuala Lumpur
Period	18/10/15 → 18/10/19

Keywords

Crack classification
Edge detection
Point cloud
Triplet image matching

ASJC Scopus subject areas

Computer Science Applications
Information Systems
Earth and Planetary Sciences(all)
Computer Networks and Communications

Cite this

Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas. / Nakagawa, Masafumi; Igusa, Ryusei; Usuki, Nobuhiro et al.
2018. 1269-1276 Paper presented at 39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018, Kuala Lumpur, Malaysia.

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

Nakagawa, M, Igusa, R, Usuki, N, Takigawa, M, Nishimura, N, Katsumata, Y & Eguchi, T 2018, 'Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas', Paper presented at 39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018, Kuala Lumpur, Malaysia, 18/10/15 - 18/10/19 pp. 1269-1276.

@conference{68567c1d82314449990dc6fab3f9c882,

title = "Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas",

abstract = "Collapse investigations in high mountain areas are generally conducted byfield surveys using handheld digital cameras and tape measures. A presurvey is alsoconducted using processing of aerial images for more efficient surveys. However, identifyingcracks from various edges in aerial images is usually a manual operation. We have proposed amethodology to automate crack detection using multiple aerial images and our knowledge ofcracks. Moreover, we evaluated our methodology through an experiment on crack detectionand classification using multiple aerial images.",

keywords = "Crack classification, Edge detection, Point cloud, Triplet image matching",

author = "Masafumi Nakagawa and Ryusei Igusa and Nobuhiro Usuki and Masanori Takigawa and Naoki Nishimura and Yoshiaki Katsumata and Tomoaki Eguchi",

year = "2018",

month = jan,

day = "1",

language = "English",

pages = "1269--1276",

note = "39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018 ; Conference date: 15-10-2018 Through 19-10-2018",

}

TY - CONF

T1 - Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas

AU - Nakagawa, Masafumi

AU - Igusa, Ryusei

AU - Usuki, Nobuhiro

AU - Takigawa, Masanori

AU - Nishimura, Naoki

AU - Katsumata, Yoshiaki

AU - Eguchi, Tomoaki

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Collapse investigations in high mountain areas are generally conducted byfield surveys using handheld digital cameras and tape measures. A presurvey is alsoconducted using processing of aerial images for more efficient surveys. However, identifyingcracks from various edges in aerial images is usually a manual operation. We have proposed amethodology to automate crack detection using multiple aerial images and our knowledge ofcracks. Moreover, we evaluated our methodology through an experiment on crack detectionand classification using multiple aerial images.

AB - Collapse investigations in high mountain areas are generally conducted byfield surveys using handheld digital cameras and tape measures. A presurvey is alsoconducted using processing of aerial images for more efficient surveys. However, identifyingcracks from various edges in aerial images is usually a manual operation. We have proposed amethodology to automate crack detection using multiple aerial images and our knowledge ofcracks. Moreover, we evaluated our methodology through an experiment on crack detectionand classification using multiple aerial images.

KW - Crack classification

KW - Edge detection

KW - Point cloud

KW - Triplet image matching

UR - http://www.scopus.com/inward/record.url?scp=85071934118&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071934118&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85071934118

SP - 1269

EP - 1276

T2 - 39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018

Y2 - 15 October 2018 through 19 October 2018

ER -

Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this