Traffic infrastructure segmentation is widely used in for digitization of urban areas for smart city applications. In this paper, we use transfer learning for carriageway edge detection for Indian urban roads where lane edge markings are often invisible. Also, the edge of the pavement often overlaps with unpaved shoulders posing challenges for image-based edge detection. The images obtained from various routes in Chennai, India are annotated and their masks were trained using DeepLabV3with ResNet101 and MobileNetV3 as backbones to predict the classes for each pixel. Two performance metrics, AUROC and F1 score, were used to evaluate the methods. Results show that DeepLabV3 with ResNet101 outperformed DeepLabV3 with MobileNetV3.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Carriageway Edge Detection for Unmarked Urban Roads using Deep Learning Techniques


    Contributors:


    Publication date :

    2023-05-25


    Size :

    662449 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Non-junction accidents on urban single-carriageway roads

    Summersgill, I. / Layfield, R. E. | TIBKAT | 1996


    VISIO-SPATIAL ROAD BOUNDARY DETECTION FOR UNMARKED URBAN AND RURAL ROADS

    Kuhnl, T. / Fritzsche, J. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2014



    Accidents at three-arm priority junctions on urban single-carriageway roads

    Summersgill, I. / Kennedy, Janet V. / Baynes, D. | TIBKAT | 1996


    Accidents at 3-arm traffic signals on urban single-carriageway roads

    Taylor, Marie C. / Hall, R. D. / Chatterjee, K. | TIBKAT | 1996