The recent advancements in deep convolutional neural networks have shown significant promise in the domain of road scene parsing. Nevertheless, the existing works focus primarily on freespace detection, with little attention given to hazardous road defects that could compromise both driving safety and comfort. In this article, we introduce RoadFormer, a novel Transformer-based data-fusion network developed for road scene parsing. RoadFormer utilizes a duplex encoder architecture to extract heterogeneous features from both RGB images and surface normal information. The encoded features are subsequently fed into a novel heterogeneous feature synergy block for effective feature fusion and recalibration. The pixel decoder then learns multi-scale long-range dependencies from the fused and recalibrated heterogeneous features, which are subsequently processed by a Transformer decoder to produce the final semantic prediction. Additionally, we release SYN-UDTIRI, the first large-scale road scene parsing dataset that contains over 10,407 RGB images, dense depth images, and the corresponding pixel-level annotations for both freespace and road defects of different shapes and sizes. Extensive experimental evaluations conducted on our SYN-UDTIRI dataset, as well as on three public datasets, including KITTI road, CityScapes, and ORFD, demonstrate that RoadFormer outperforms all other state-of-the-art networks for road scene parsing. Specifically, RoadFormer ranks first on the KITTI road benchmark.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing


    Beteiligte:
    Li, Jiahang (Autor:in) / Zhang, Yikang (Autor:in) / Yun, Peng (Autor:in) / Zhou, Guangliang (Autor:in) / Chen, Qijun (Autor:in) / Fan, Rui (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.07.2024


    Format / Umfang :

    9375401 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Spatial Prior for Nonparametric Road Scene Parsing

    Di, Shuai / Zhang, Honggang / Mei, Xue et al. | IEEE | 2015



    Exploiting Large Image Sets for Road Scene Parsing

    Alvarez, Jose M | Online Contents | 2016


    Exploiting Large Image Sets for Road Scene Parsing

    Alvarez, Jose M. / Salzmann, Mathieu / Barnes, Nick | IEEE | 2016


    Nighttime Road Scene Parsing by Unsupervised Domain Adaptation

    Song, Can / Wu, Jin / Zhu, Lei et al. | IEEE | 2022