Automated recognition of surface defects in subway systems

T. Dawood, Z. Zhu, Tarek Zayed

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

Subway networks monitoring and maintenance present substantial challenges for managers and engineers. Major subway authorities in the world have several tunnels running under rivers. Water leakage through soil has been considered as the main cause of concrete degradation in subway facilities. Other structural defects are derived from water intrusion, such as rebar corrosion, spalling, and delamination. Therefore, condition assessment of subway networks represents a challenging task in the sustainability of a sound concrete infrastructure. Visual inspection techniques are considered the principal methods used in the condition evaluation of civil infrastructure. These methods are time-consuming, expensive, and dependent inherently on subjective criteria. Automating the current practice is expected to provide more objective, accurate, and quantitative results. This paper presents a defect-based condition assessment model for subway networks based on image processing methods. The model performs damage identification and quantification of moisture marks on the external surface of concrete through different image enhancement algorithms such as histogram equalization, edge detection and mask processing. It provides guidelines to enhance the quality and consistency of a condition assessment approach, as well as, reducing the cost and time required to inspect subway networks. The proposed methodology has been tested on segments of the Montreal subway system.
Original languageEnglish
JournalCivil-Comp Proceedings
Volume109
Publication statusPublished - 1 Jan 2015
Externally publishedYes

Keywords

  • Concrete infrastructure
  • Condition assessment
  • Image processing
  • Subway networks
  • Visual inspection
  • Water leakage

ASJC Scopus subject areas

  • Environmental Engineering
  • Civil and Structural Engineering
  • Computational Theory and Mathematics
  • Artificial Intelligence

Cite this