We introduce an approach to image-based road detection that exploits the availability of unannotated training images to learn an appearance model. Our approach allows us to remove the standard assumption that the lower part of the input image belongs to the road surface, which does not always hold and often yields strongly biased appearance models. Instead, we exploit this assumption in the training images, which yields a much more general appearance model. We then use the learned model to classify the pixels of an input image as road or background without requiring any assumptions about this image. Our experimental evaluation shows the benefits of our approach over existing methods in challenging real-world driving scenarios.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning appearance models for road detection


    Beteiligte:
    Alvarez, Jose M. (Autor:in) / Salzmann, Mathieu (Autor:in) / Barnes, Nick (Autor:in)


    Erscheinungsdatum :

    2013-06-01


    Format / Umfang :

    2556679 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LEARNING APPEARANCE MODELS FOR ROAD DETECTION

    Alvarez, J. / Salzmann, M. / Barnes, N. et al. | British Library Conference Proceedings | 2013


    Combining Priors, Appearance, and Context for Road Detection

    Alvarez, Jose M. / Lopez, Antonio M. / Gevers, Theo et al. | IEEE | 2014




    Automatic Learning of Appearance Face Models

    De la Torre, F. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2001