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 conferencePaperpeer-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 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

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

Fingerprint Dive into the research topics of 'Crack detection from high-resolution aerial triplet images for safer collapse investigations in high mountain areas'. Together they form a unique fingerprint.

Cite this