Recent road marking recognition has achieved great success in the past few years along with the rapid development of deep learning. Although considerable advances have been made, they are often over-dependent on unrepresentative datasets and constrained conditions. In this paper, to overcome these drawbacks, we propose an alternative method that achieves higher accuracy and generates high-quality samples as data augmentation. With the following two major contributions: 1) The proposed deblurring network can successfully recover a clean road marking from a blurred one by adopting generative adversarial networks (GAN). 2) The proposed data augmentation method, based on mutual information, can preserve and learn semantic context from the given dataset. We construct and train a class-conditional GAN to increase the size of training set, which makes it suitable to recognize target. The experimental results have shown that our proposed framework generates deblurred clean samples from blurry ones, and outperforms other methods even with unconstrained road marking datasets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Unconstrained Road Marking Recognition with Generative Adversarial Networks


    Beteiligte:
    Lee, Younkwan (Autor:in) / Lee, Juhyun (Autor:in) / Hong, Yoojin (Autor:in) / Ko, YeongMin (Autor:in) / Jeon, Moongu (Autor:in)


    Erscheinungsdatum :

    2019-06-01


    Format / Umfang :

    404641 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    ROAD MARKING RECOGNITION DEVICE AND ROAD MARKING RECOGNITION PROGRAM

    UEDA YUSUKE / KAWASAKI NAOTERU / KUMANO TOSHIYA et al. | Europäisches Patentamt | 2015

    Freier Zugriff


    A Gated Generative Adversarial Imputation Approach for Signalized Road Networks

    Zhang, Tong / Wang, Jianlong / Liu, Jie | IEEE | 2022


    EvolGAN: Evolutionary Generative Adversarial Networks

    Roziere, Baptiste / Teytaud, Fabien / Hosu, Vlad et al. | British Library Conference Proceedings | 2021