• DocumentCode
    272846
  • Title

    Enhanced automatic detection of road surface cracks by combining 2D/3D image processing techniques

  • Author

    Medina, Roberto ; Llamas, José ; Zalama, Eduardo ; Gomez-Garcia-Bermejo, Jaime

  • Author_Institution
    CARTIF Found., Valladolid, Spain
  • fYear
    2014
  • fDate
    27-30 Oct. 2014
  • Firstpage
    778
  • Lastpage
    782
  • Abstract
    In this paper, a comprehensive automatic visual inspection system for detecting pavement cracks, built around a Laser Road Inspection System (LRIS) onboard an instrumented vehicle, is presented. Two inertial profilers, a Differential Global Position System (DGPS), a high-definition camera and a high-speed area scan camera are the additional acquisition equipment. Visual appearance and geometrical information are obtained simultaneously since 3D profiles are obtained by capturing the laser line projected by the LRIS with the external area scan camera. Using AdaBoost algorithm for the combination of the processing results of these two types of data allows us to improve surface crack detection rates.
  • Keywords
    Global Positioning System; automatic optical inspection; cameras; crack detection; image processing; learning (artificial intelligence); measurement by laser beam; roads; structural engineering computing; surface cracks; 2D-3D image processing techniques; 3D profiles; AdaBoost algorithm; DGPS; LRIS onboard; acquisition equipment; comprehensive automatic visual inspection system; differential Global Position System; enhanced automatic detection; geometrical information; high-definition camera; high-speed area scan camera; inertial profilers; instrumented vehicle; laser line; laser road inspection system; pavement crack detection; road surface cracks; surface crack detection rates; visual appearance; Cameras; Gabor filters; Inspection; Lasers; Roads; Three-dimensional displays; Visualization; AdaBoost classification; Gabor filters; Machine vision; feature extraction; road inspection;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing (ICIP), 2014 IEEE International Conference on
  • Conference_Location
    Paris
  • Type

    conf

  • DOI
    10.1109/ICIP.2014.7025156
  • Filename
    7025156
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=272846