In this paper, an algorithm for automatic extraction of expressways from high resolution satellite images is proposed. Some characteristic geometrical properties of expressways are assumed and an algorithm of road extraction is constructed based on the assumptions. Two of the assumptions are: Expressways can be approximately linear within each small region of images and they are continuous; and Zero-crossings of the image intensity are used for edge detection. The possibility that a pixel on an edge exists on a road is estimated. A road is extracted as a continuous line using those values of the possibility and the continuity of road. The proposed algorithm can be applied to extract railways and main rivers by changing the algorithm according to the properties of the objects.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Automatic Road Extraction from Satellite Images Using Zero-Crossings


    Contributors:
    Y. Rianto (author) / T. Kim (author) / S. Kondo (author)

    Publication date :

    1993


    Size :

    8 pages


    Type of media :

    Report


    Type of material :

    No indication


    Language :

    English





    Study of road accidents at automatic road/rail crossings

    Forestier,M. / INRETS,FR | Automotive engineering | 1988



    Improved road crossings

    Engineering Index Backfile | 1943


    Automatic Extraction of Road Network from Satellite Images of Urban Areas Using Convolution Neural Network

    Nohwal, Aman / Jangid, Tushar / Panigrahi, Narayan | Springer Verlag | 2021