In complex traffic scenarios, there are many problems such as inaccurate vehicle positioning, low recognition rate, and missed detection of vehicles for instability of the traffic environment. This paper proposes an improved Faster R-CNN algorithm for accurate vehicle detection. We use feature maps of depth images to supplement vehicle details by adding a depth channel into the detection model. When training the model, we add a hard sample mining strategy. We evaluate our newly proposed approach using KITTI dataset. The experimental results show that our proposed approach has a significant improvement in recognition accuracy by 5%.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A vehicle detection algorithm in complex traffic scenes


    Beteiligte:
    Jin, Tianyu (Autor:in) / Zhang, Dengyin (Autor:in) / Ding, Fei (Autor:in) / Zhang, Zhen (Autor:in) / Zhang, Min (Autor:in)

    Kongress:

    Twelfth International Conference on Digital Image Processing (ICDIP 2020) ; 2020 ; Osaka,Japan


    Erschienen in:

    Proc. SPIE ; 11519


    Erscheinungsdatum :

    2020-06-12





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Vision-Based Lane Detection Algorithm in Urban Traffic Scenes

    Ran, Feng / Jiang, Zhoulong / Xu, Meihua | Tema Archiv | 2014


    Vision-Based Lane Detection Algorithm in Urban Traffic Scenes

    Ran, F. / Jiang, Z. / Xu, M. | British Library Conference Proceedings | 2014


    Vision-Based Lane Detection Algorithm in Urban Traffic Scenes

    Ran, Feng / Jiang, Zhoulong / Xu, Meihua | Springer Verlag | 2014


    Mono-Vision Based Moving Object Detection in Complex Traffic Scenes

    Fremont, Vincent / Rodriguez, Sergio / Wang, Bihao | British Library Conference Proceedings | 2017


    Mono-vision based moving object detection in complex traffic scenes

    Fremont, Vincent / Florez, Sergio Alberto Rodriguez / Wang, Bihao | IEEE | 2017