Road scene segmentation is of great significance in intelligent transportation system for different applications such as autonomous driving and semantic map building. Despite great progress in this field with the deep learning methods, there are still many difficulties such as robust segmentation of small objects and same type of objects with different sizes in different scenes. In this paper, we propose a new pyramid architecture for scene segmentation, which is a top-down architecture with lateral connections for multi-scale semantic feature maps building, and sufficiently incorporate the momentous global scenery prior. Besides, we also propose a novel training method, which combines the re-sampling, pixel-wise cost learning and transfer learning together, to deal with the imbalance problem. Experimental results on KITTI and Cityscapes dataset demonstrate effectiveness of the proposed method.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A New Feature Pyramid Network For Road Scene Segmentation


    Beteiligte:
    Zhan, Wujing (Autor:in) / Chen, Jiaxing (Autor:in) / Fan, Lei (Autor:in) / Ou, Xinqi (Autor:in) / Chen, Long (Autor:in)


    Erscheinungsdatum :

    2018-11-01


    Format / Umfang :

    1694681 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Road Network Pyramid Model

    Cai, Xian-Hua / Bai, Chun-Guang / Dou, Wen | Tema Archiv | 2012


    Road Network Pyramid Model

    Cai, X.H. / Bai, C.G. / Dou, W. | British Library Conference Proceedings | 2013


    RGB Road Scene Material Segmentation

    Cai, Sudong / Wakaki, Ryosuke / Nobuhara, Shohei et al. | British Library Conference Proceedings | 2023