Bridge deflection measurement method based on machine vision technology

Xiao Wei Ye, Xiao Ming Zhang, Yiqing Ni, Kai Yuen Wong, Ke Qing Fan

Research output: Journal article publicationJournal articleAcademic researchpeer-review

8 Citations (Scopus)


In this paper, a structural displacement measurement method by use of the digital image processing technology is proposed for the purpose of structural displacement/deflection measurement of long-span bridges. The flowchart of structural displacement calculation based on the pattern matching algorithm is introduced. A machine vision-based displacement measurement system is developed, which integrates many advantages such as long-distance, non-contact, real-time, low-cost and convenient to implementation in realizing the structural displacement measurement with the accuracy level of millimetre. The laboratory and field calibration tests are carried out to validate its feasibility on the structural displacement measurement and the reliability on systematic measurement accuracy. The mid-span deflection of the Tsing Ma Bridge is simultaneously measured by the developed system with a working distance over one thousand meters and the GPS. The results show that the displacement measurement data from the developed system are in good agreement with those measured by the GPS in both the time and frequency domains. The developed machine vision-based displacement measurement system has wide application prospect in the displacement/deflection monitoring of civil engineering structures.
Original languageEnglish
Pages (from-to)813-819
Number of pages7
JournalZhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science)
Issue number5
Publication statusPublished - 1 Jan 2014


  • Deflection measurement
  • Digital image processing method
  • Long-span bridges
  • Machine vision technology
  • Pattern matching algorithm

ASJC Scopus subject areas

  • Engineering(all)


Dive into the research topics of 'Bridge deflection measurement method based on machine vision technology'. Together they form a unique fingerprint.

Cite this