Deep learning-based concrete crack detection using hybrid images

Yun Kyu An, Keunyoung Jang, Byunghyun Kim, Soojin Cho

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Scopus citations

Abstract

This paper presents a deep learning-based concrete crack detection technique using hybrid images. The hybrid images combining vision and infrared (IR) thermography images are able to improve crack detectability while minimizing false alarms. Large scale concrete-made infrastructures such as bridge, dam, and etc. can be effectively inspected by spatially scanning the hybrid imaging system including vision camera, IR camera and continuous-wave line laser. However, the decision-making for the crack identification often requires experts' intervention. As a target concrete structure gets larger, automated decision-making becomes more necessary in the practical point of view. The proposed technique is able to achieve automated crack identification by modifying a well-trained convolutional neural network using a set of crack images as a training image set, while retaining the advantages of hybrid images. The proposed technique is experimentally validated using a lab-scale concrete specimen developed with various-size cracks. The test results reveal that macro-and micro-cracks are automatically detected with minimizing false-alarms.

Original languageEnglish
Title of host publicationSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018
EditorsKon-Well Wang, Hoon Sohn, Jerome P. Lynch
PublisherSPIE
ISBN (Electronic)9781510616929
DOIs
StatePublished - 2018
EventSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018 - Denver, United States
Duration: 5 Mar 20188 Mar 2018

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10598
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018
Country/TerritoryUnited States
CityDenver
Period5/03/188/03/18

Keywords

  • Convolutional neural network
  • Deep learning
  • Hybrid image scanning
  • IR thermography
  • Nondestructive crack detection
  • Vision-based crack detection

Fingerprint

Dive into the research topics of 'Deep learning-based concrete crack detection using hybrid images'. Together they form a unique fingerprint.

Cite this