Road maintenance is one of the most critical issues confronting agricultural based countries. Road foundations are vital to society since most traffic accidents are caused by poor road conditions such as potholes. Potholes are caused by poor quality and a failure to keep up with the roadways. Furthermore, the continuous rise of overweight vehicles, such as trucks, are responsible for the potholed roads. These poor quality roads will extremely damage the automobiles in terms of underinflated tires and accidents. Hence, a A suitable structure for monitoring road conditions and planning future works should be developed. Pits are generally formed by mature roadways and poor road support structures, and their number grows with time. Potholes compromise road safety and reduce transportation efficiency. This research study proposes a portable framework called PotholeEye + to consequently observe the outer layer of a road and progressively distinguish asphalt problems through video investigation. As you drive the road director, PotholeEye+ pre-processes the images, removes the inclusion and sort out the misery. This research work is testing PotholeEye+ on a real road constantly for a year by using original settings, a camera, a small-scale PC, a beneficiary GPS, etc. Subsequently, PotholeEye + has recognized asphalt problems with 92% typical accuracy, 87% accuracy and 74% review when driving at a typical speed of 110 km/h on an actual highway.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Deep-Learning-Based Intelligent PotholeEye+ Detection Pavement Distress Detection System




    Publication date :

    2022-05-09


    Size :

    1646078 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Pavement Distress Detection Based on the Staged Deep Learning Classifier Approach

    Dipankar, Amit / Suman, Sanjeev Kumar | Transportation Research Record | 2024


    Pavement distress detection and avoidance for intelligent vehicles

    Bellone,M. / Reina,G. / Chalmers Univ.of Technology,SE et al. | Automotive engineering | 2016



    Evaluation of Safety State of Freeway Pavement Based on Pavement Distress Detection

    Leng, Haiyang / Xiang, Qiaojun / Ning, Jing et al. | ASCE | 2011


    A weakly-supervised deep learning model for end-to-end detection of airfield pavement distress

    Zefeng Tao / Hongren Gong / Liming Liu et al. | DOAJ | 2025

    Free access