The scale of public roads, particularly highways, has rapidly increased in many nations over the last few decades. To increase the road’s usability and thus its social and economic benefits, road maintenance has received more attention lately. Road inspections were done manually, the old-fashioned way takes a lot of time, and work, and is subjective. For proper road maintenance, deteriorated roads must be repaired as quickly as possible. Therefore, there is an urgent need for high-performance, low-cost technology to identify road surface distress. Unmanned aerial vehicles (UAVs), on the other hand, are an exciting option for monitoring the status of roads. They have the benefits of great flexibility, cheap cost, and simple agility. The data was collected in a 5 km road stretch of NH-336, Tamil Nadu. In this study, some of the computer vision tools including OpenCV, CUDA, etc. are tried to detect and localize the distress. It includes the detection and classification of pavement distress by using Object detection algorithms like Faster RCNN, Yolov3, and Yolov4 were used for detection and classification of road distresses. The main focus is on the detection and classification of potholes and cracks. Local road authorities and communities can benefit from this system to evaluate the state of their road network pavement in real-time. The application of deep learning techniques in transportation engineering problems is very rare. This study makes an effort to use deep learning techniques in the classification of the distresses and localizing them.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pavement Distress Detection Using Image Processing from Unmanned Aerial Vehicle Data


    Additional title:

    Lecture Notes in Civil Engineering


    Contributors:

    Conference:

    International Conference on Innovative Methods and Practical Applications for Cognizant Transportation Systems ; 2023 ; Thiruvananthapuram, India March 20, 2023 - March 22, 2023



    Publication date :

    2024-11-30


    Size :

    15 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Automatic Road Pavement Distress Recognition Using Deep Learning Networks from Unmanned Aerial Imagery

    Farhad Samadzadegan / Farzaneh Dadrass Javan / Farnaz Ashtari Mahini et al. | DOAJ | 2024

    Free access

    Unmanned aerial vehicle pavement marking machine

    PAN YUE / LAN CHENGYAN | European Patent Office | 2024

    Free access



    Unmanned aerial vehicle implementation for pavement condition survey

    Yackob Astor / Yasuyuki Nabesima / Retno Utami et al. | DOAJ | 2023

    Free access