STUDY ON AUTOMATIC CLASSIFICATION OF GRAVEL BEACH SEDIMENTS USING MACHINE LEARNING

• INOUE Yuta

  岐阜工業高等専門学校 専攻科先端融合開発専攻

• KIKU Masami

  岐阜工業高等専門学校 環境都市工学科

• NAKAMURA Tomoaki

  名古屋大学 大学院工学研究科土木工学専攻

• MIZUTANI Norimi

  名古屋大学 大学院工学研究科土木工学専攻

Bibliographic Information

Other Title

• 機械学習による礫浜の構成物の自動分類に関する研究
• 深層学習による水際線変動と波浪条件の関連性の検討
• シンソウ ガクシュウ ニ ヨル ミズギワセン ヘンドウ ト ハロウ ジョウケン ノ カンレンセイ ノ ケントウ
• キカイ ガクシュウ ニ ヨル レキハマ ノ コウセイブツ ノ ジドウ ブンルイ ニ カンスル ケンキュウ

Abstract

 A machine learning model classifying orth-mosaic images of a gravel beach created from UAV-SfM/MVS survey into "gravel", "drifting", "vegetation", and "block" was constructed and examined in terms of the characteristics and usefulness. From investigation, it was found that the discrimination accuracy can be improved by reducing the size of the filter layer and increasing the number of filter layers. The visualization using Grad-CAM showed that the indiscrimination of “gravel” and “drifting” was caused by a few points of interest. Additionally, the machine with the trained model can work well even for images that are not used for training.

Journal

• Journal of Japan Society of Civil Engineers, Ser. B2 (Coastal Engineering)

  Journal of Japan Society of Civil Engineers, Ser. B2 (Coastal Engineering) 77 (2), I_673-I_678, 2021

  Japan Society of Civil Engineers

Keywords

• gravel beach
• sediments
• machine learning
• automatic classification

Details

• CRID: 1390571415708335104
• NII Article ID: 40022783290
• NII Article ID: 40022783281
• NII Article ID: 130008113462
• DOI: 10.2208/kaigan.77.2_i_673
• ISSN: 18838944
• ISSN: 18842399
• NDL BIB ID: 031893243
• NDL BIB ID: 031893256
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I031893243
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I031893256
• Web Site: https://www.jstage.jst.go.jp/article/kaigan/77/2/77_I_673/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed