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 conferencePaper

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 languageEnglish
Pages1269-1276
Number of pages8
Publication statusPublished - 2018 Jan 1
Event39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018 - Kuala Lumpur, Malaysia
Duration: 2018 Oct 152018 Oct 19

Conference

Conference39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018
CountryMalaysia
CityKuala Lumpur
Period18/10/1518/10/19

Fingerprint

Crack detection
crack
Antennas
Digital cameras
Tapes
Cracks
methodology
detection
high mountain
Processing
experiment
Experiments

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

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. 1269-1276. Paper presented at 39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018, Kuala Lumpur, Malaysia.

Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas. / Nakagawa, Masafumi; Igusa, Ryusei; Usuki, Nobuhiro; Takigawa, Masanori; Nishimura, Naoki; Katsumata, Yoshiaki; Eguchi, Tomoaki.

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 conferencePaper

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.
Nakagawa M, Igusa R, Usuki N, Takigawa M, Nishimura N, Katsumata Y et al. Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas. 2018. Paper presented at 39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018, Kuala Lumpur, Malaysia.
Nakagawa, Masafumi ; Igusa, Ryusei ; Usuki, Nobuhiro ; Takigawa, Masanori ; Nishimura, Naoki ; Katsumata, Yoshiaki ; Eguchi, Tomoaki. / 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.8 p.
@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 = "1",
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

SP - 1269

EP - 1276

ER -