0
  • DE
  • EN
  • FR
  • Base de données et galerie internationale d'ouvrages d'art et du génie civil

Publicité

Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique

Auteur(s):

Médium: article de revue
Langue(s): anglais
Publié dans: Advances in Civil Engineering, , v. 2019
Page(s): 1-12
DOI: 10.1155/2019/6520620
Abstrait:

Crack detection is important for the inspection and evaluation during the maintenance of concrete structures. However, conventional image-based methods need extract crack features using complex image preprocessing techniques, so it can lead to challenges when concrete surface contains various types of noise due to extensively varying real-world situations such as thin cracks, rough surface, shadows, etc. To overcome these challenges, this paper proposes an image-based crack detection method using a deep convolutional neural network (CNN). A CNN is designed through modifying AlexNet and then trained and validated using a built database with 60000 images. Through comparing validation accuracy under different base learning rates, 0.01 was chosen as the best base learning rate with the highest validation accuracy of 99.06%, and its training result is used in the following testing process. The robustness and adaptability of the trained CNN are tested on 205 images with 3120 × 4160 pixel resolutions which were not used for training and validation. The trained CNN is integrated into a smartphone application to mobile more public to detect cracks in practice. The results confirm that the proposed method can indeed detect cracks in images from real concrete surfaces.

Copyright: © 2019 Shengyuan Li et al.
License:

Cette oeuvre a été publiée sous la license Creative Commons Attribution 4.0 (CC-BY 4.0). Il est autorisé de partager et adapter l'oeuvre tant que l'auteur est crédité et la license est indiquée (avec le lien ci-dessus). Vous devez aussi indiquer si des changements on été fait vis-à-vis de l'original.

  • Informations
    sur cette fiche
  • Reference-ID
    10312890
  • Publié(e) le:
    09.05.2019
  • Modifié(e) le:
    02.06.2021