Research for Recognizing Individual Parts of Bridge Using Point Cloud Data with Deep Learning

• TSUKADA Yoshinori

  Faculty of Business Administration, Setsunan University

• KUBOTA Satoshi

  Faculty of Environmental and Urban Engineering, Kansai University

• TANAKA Shigenori

  Faculty of Informatics, Kansai University

• UMEHARA Yoshimasa

  Organization for Research and Development of Innovative Science and Technology, Kansai University

• NAKAHARA Masaya

  Graduate School of Informatics, Kansai University

• NAKAHATA Koki

  Graduate School of Informatics, Kansai University

Bibliographic Information

Other Title

• 橋梁の点群データを用いた深層学習による部位識別に関する研究
• キョウリョウ ノ テングン データ オ モチイタ シンソウ ガクシュウ ニ ヨル ブイ シキベツ ニ カンスル ケンキュウ

Abstract

In Japan, a large number of bridges constructed during the period of high economic growth are aging. The Ministry of Land, Infrastructure, Transport and Tourism has formulated a specification for creating a three-dimensional model and a definition of notation for the purpose of improving efficiency and upgrading of maintenance management of these bridges. In this background, a method was proposed for generating a three-dimensional model of a bridge using the point cloud data obtained from the laser scanner on the ground or UAV. However, in existing research, it is impossible to generate models for each individual part specified by the current specification. In this study, we propose a method for automatically recognizing individual parts of the main girder, the road surface, the handrail, and the abutment from the point cloud data of a bridge using deep learning.

Journal

• Journal of Japan Society for Fuzzy Theory and Intelligent Informatics

  Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 32 (1), 627-631, 2020-02-15

  Japan Society for Fuzzy Theory and Intelligent Informatics

Keywords

• bridge
• laser scanner
• point cloud data
• deep learning
• object segmentation

Details

• CRID: 1390565134829038592
• NII Article ID: 130007798539
• NII Book ID: AA1181479X
• DOI: 10.3156/jsoft.32.1_627
• ISSN: 18817203
• ISSN: 13477986
• NDL BIB ID: 030267128
• Web Site: http://id.ndl.go.jp/bib/030267128
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I030267128
• Web Site: https://www.jstage.jst.go.jp/article/jsoft/32/1/32_627/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed