Bridge Deterioration Quantification Protocol Using UAV

Luis Duque, Junwon Seo, James Wacker

Research output: Contribution to journalArticlepeer-review

57 Scopus citations


This paper focuses on evaluating the effectiveness of an unmanned aerial vehicle (UAV) as a supplementary bridge damage quantification tool. For this study, a glued-laminated timber arch bridge in South Dakota was selected, and an UAV was utilized for the bridge damage quantification. A recommended four-stage UAV-enabled bridge damage quantification protocol involving image quality assessment and image-based damage quantification was developed. A field application using the UAV to measure crack lengths, thicknesses, and rust stain areas of the selected bridge was conducted following the recommended protocol. The image quality parameters, including sharpness and entropy, were used to determine the quality of the UAV-captured images. Pixel- and photogrammetry-based measurements using the high-quality images were obtained to quantify the bridge damage, and the damage was compared to that from actual field measurements. Once the damage information was gathered, the UAV image-based damage level classification was established based on the damage levels defined by current standards. The findings confirmed the accuracy of the recommended protocol, with results within 3.5, 7.9, and 14.9% difference for crack length, thickness, and rust stain area, respectively, when compared with the field measurements.

Original languageEnglish
Article number0001289
JournalJournal of Bridge Engineering
Issue number10
StatePublished - Oct 1 2018

Bibliographical note

Publisher Copyright:
© 2018 American Society of Civil Engineers.


  • Bridge
  • Damage
  • Image
  • Measurements
  • Photogrammetry
  • Pixel
  • Quantification
  • Unmanned aerial vehicle (UAV)

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction


Dive into the research topics of 'Bridge Deterioration Quantification Protocol Using UAV'. Together they form a unique fingerprint.

Cite this