CRACK DETECTION SYSTEM FOR CONCRETE SURFACE BASED ON DEEP CONVOLUTION NEURAL NETWORK

• NOMURA Yasutoshi

  立命館大学 理工学部都市システム工学科

• MURAO Saki

  関西大学 総合情報学部総合情報学科

• SAKAGUCHI Yukihiro

  立命館大学 理工学部都市システム工学科

• FURUTA Hitoshi

  関西大学 総合情報学部総合情報学科

Bibliographic Information

Other Title

• 深層畳み込みニューラルネットワークに基づくコンクリート表面のひび割れ検出システム

Abstract

 Recently, assessing the integrity of the structures accurately and reliably has become extremely important in various fields in order to increase operational lifetime and improve safety. Detecting cracks in evaluating the soundness of the structure is particularly important as it is one of the major factors causing deterioration and destruction of the structure.<br> For the purpose of constructing an inspection system against spaces where an inspector is difficult to enter, we attempt in this study to develop a system that can detect crack in real time from the images of the whole structure photographed by UAV or web camera, by deep convolution neural network.

Journal

• Journal of Japan Society of Civil Engineers, Ser. F6 (Safety Problem)

  Journal of Japan Society of Civil Engineers, Ser. F6 (Safety Problem) 73 (2), I_189-I_198, 2017

  Japan Society of Civil Engineers

Keywords

• Deep convolution neural network
• real-time object detection
• concrete crack detection

Details

• CRID: 1390001205356172160
• NII Article ID: 130006338454
• DOI: 10.2208/jscejsp.73.i_189
• ISSN: 21856621
• Web Site: https://www.jstage.jst.go.jp/article/jscejsp/73/2/73_I_189/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed