Tracking types and extent of pavement deterioration is critical for maintaining road networks in a serviceable condition. The prevailing methods for obtaining pavement condition data include manual and semiautomated surveys, which are time-consuming and involve significant human intervention. Extensive research has been performed in automating the process for more efficient, objective, and repeatable distress evaluations. This paper highlights the preliminary results from an effort sponsored by the Florida Department of Transportation to develop and implement automated software for identification and quantification of pavement surface cracking distresses. A technical framework was developed for systematic evaluation of available automated technologies in contrast to manual methods. Pertinent performance measures were identified to evaluate the accuracy, precision, repeatability, reproducibility, and efficiency of various methods. This framework was implemented to determine the gaps in effectiveness of automated applications, to design corresponding solutions, and to gauge reliability expectations accordingly. The evaluation follows two main steps: ( a) comparison of the cumulative quantities of various distress types found in manual surveys versus automated surveys and ( b) verification of the automatically detected distresses against reference crack maps generated through a semiautomated process of manually rating the collected images. Although the overall comparison of distress quantities indicates strengths and weaknesses of the evaluated algorithm, the distress by distress verification of software performance is used to identify design solutions for addressing the indicated weaknesses. The guidelines in this systematic framework can be modified with context-sensitive considerations to be applicable to other highway agencies transitioning to automated applications.


    Access

    Download

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Evaluation Framework for Automated Pavement Distress Identification and Quantification Applications


    Additional title:

    Transportation Research Record


    Contributors:


    Publication date :

    2017-01-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Automated Pavement Evaluation System for Pavement Distress Assessment

    H. Oh / N. W. Garrick / L. E. K. Achenie | NTIS | 1997


    Automated Pavement Distress Analyzer

    Burke, M. W. / Transportation Association of Canada / International Road Federation | British Library Conference Proceedings | 1994


    Automated Real-Time Pavement Distress Analysis

    Cheng, H. D. / Jiang, X. / Li, J. et al. | Transportation Research Record | 1999


    Automated Real-Time Pavement Distress Analysis

    Cheng, H.D. | Online Contents | 1999


    Evaluation of Semiautomated and Automated Pavement Distress Collection for Network-Level Pavement Management

    Tighe, Susan L. / Ningyuan, Li / Kazmierowski, Tom | Transportation Research Record | 2008