In this work, we solve the task of automotive traffic scene classification using a deep learning approach on low-level radar data. In contrast to existing approaches using 2D camera images, the input are complex-valued 3D range-beam-doppler tensors outputted by an automotive radar. We design, train and evaluate three different networks and analyze the effects of different nuances in processing this type of data in deep neural networks. Particular attention is paid to complex-valued convolutions and their usage on complex-valued 3D tensors. The resulting networks achieve a classification accuracy above 95% on split test datasets and show the usability of automotive radar data for traffic scene classification, which can be integrated into weather robust multi-sensor systems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Complex-Valued Convolutional Neural Networks for Automotive Scene Classification Based on Range-Beam-Doppler Tensors


    Beteiligte:
    Meyer, Michael (Autor:in) / Kuschk, Georg (Autor:in) / Tomforde, Sven (Autor:in)


    Erscheinungsdatum :

    2020-09-20


    Format / Umfang :

    1436722 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Ship classification based on convolutional neural networks

    Yang, Yang / Ding, Kaifa / Chen, Zhuang | Taylor & Francis Verlag | 2022



    Fully Convolutional Neural Networks for Automotive Radar Interference Mitigation

    Ristea, Nicolae-Catalin / Anghel, Andrei / Ionescu, Radu Tudor | IEEE | 2020


    Deep Complex-Valued Convolutional Neural Network for Drone Recognition Based on RF Fingerprinting

    Jie Yang / Hao Gu / Chenhan Hu et al. | DOAJ | 2022

    Freier Zugriff