Video object segmentation (VOS) is an essential part of intelligent transportation systems (ITS). In the real traffic scenes, not only stable accuracy but also real-time speed are important metrics. In this paper, we propose a semi-supervised real-time video object segmentation method based on a Siamese network with a novel polar representation method. This polar representation method could reduce the parameters for encoding masks, so that the inference speed is enhanced significantly. Besides, an asymmetric Siamese network is designed to extract the features from different spatial scales. To reduce the antagonism among the branches of the head part, we propose the idea of peeling convolution. Based on this idea, repeated cross-correlation and semi-FPN are designed as the neck part of the neural network. The experiments on the DAVIS-2016 dataset demonstrate that SiamPolar achieves 71.4% J-mean and 59.2fps. In the real traffic scene dataset, TSD-max dataset, SiamPolar performs the 80.5% J-mean.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    SiamPolar: Realtime Video Object Segmentation with Polar Representation in Traffic Scenes


    Beteiligte:
    Hong, Yuhui (Autor:in) / Li, Yaochen (Autor:in) / Zhu, Chao (Autor:in) / Zhang, Ying (Autor:in) / Liu, Yuehu (Autor:in)


    Erscheinungsdatum :

    19.09.2021


    Format / Umfang :

    2374644 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Towards Realtime Visual Based Tracking in Cluttered Traffic Scenes

    Koller, D. / Weber, J. / Malik, J. et al. | British Library Conference Proceedings | 1994


    Towards realtime visual based tracking in cluttered traffic scenes

    Koller, D. / Weber, J. / Malik, J. | IEEE | 1994


    Dynamic segmentation of traffic scenes

    Giachetti, A. / Cappello, M. / Torre, V. | IEEE | 1995


    Dynamic Segmentation of Traffic Scenes

    Giachetti, A. / Torre, V. / Cappello, M. et al. | British Library Conference Proceedings | 1995


    Reserch on Traffic Congestion Detection Using Realtime Video

    Xu, Ling ;Ba, Qun ;Hu, Shan | Trans Tech Publications | 2012