DEEP LEARNING AND RANDOM FOREST BASED CRACK DETECTION FROM AN IMAGE OF CONCRETE SURFACE

• CHUN Pang-jo

  愛媛大学 工学部環境建設工学科

• SHIMAMOTO Yuri

  愛媛大学大学院理工学研究科

• OKUBO Kazuaki

  愛媛大学 防災情報研究センター

• MIWA Chihiro

  滋賀県庁

• OHGA Mitao

  愛媛大学

Bibliographic Information

Other Title

• ディープラーニングおよびRandom Forestによるコンクリートのひび割れ自動検出手法

Abstract

 In the past years there has been an extensive effort to develop an automated crack detection method by image processing to improve inspection and evaluation process of concrete structures. However, these methods are not yet accurate enough due to the difficulty and complexity of the problem. Especially, the mold mark is misjudged as the crack because image characteristics are quite similar to each other. To solve this problem, this paper proposes the method which distinguishes cracks and mold marks properly by convolutional neural network which is a type of deep learning. Then, accurate classification is archieved by the random forest method with considering image characteristic related to pixel value and geometric shape. The accuracy of developed method is investigated by the photos of concrete structures with lots of adverse conditions including not only the mold mark but also shadow and dirt, and it is found that the method can extract the crack region with high accuracy.

Journal

• Journal of Japan Society of Civil Engineers, Ser. F3 (Civil Engineering Informatics)

  Journal of Japan Society of Civil Engineers, Ser. F3 (Civil Engineering Informatics) 73 (2), I_297-I_307, 2017

  Japan Society of Civil Engineers

Keywords

• deep learning
• convolutional neural network
• Random Forest
• image analysis
• crack detection
• concrete

Details

• CRID: 1390282680331966848
• NII Article ID: 130006555727
• DOI: 10.2208/jscejcei.73.i_297
• ISSN: 21856591
• Web Site: https://www.jstage.jst.go.jp/article/jscejcei/73/2/73_I_297/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed