Environment perception is the task for intelligent vehicles on which all subsequent steps rely. A key part of perception is to safely detect other road users such as vehicles, pedestrians, and cyclists. With modern deep learning techniques huge progress was made over the last years in this field. However such deep learning based object detection models cannot predict how certain they are in their predictions, potentially hampering the performance of later steps such as tracking or sensor fusion. We present a viable approaches to estimate uncertainty in an one-stage object detector, while improving the detection performance of the baseline approach. The proposed model is evaluated on a large scale automotive pedestrian dataset. Experimental results show that the uncertainty outputted by our system is coupled with detection accuracy and the occlusion level of pedestrians.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Uncertainty Estimation in One-Stage Object Detection


    Beteiligte:
    Kraus, Florian (Autor:in) / Dietmayer, Klaus (Autor:in)


    Erscheinungsdatum :

    2019-10-01


    Format / Umfang :

    3024291 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Object uncertainty detection

    VAN HEUKELOM MATTHEW / LEE TENCIA / WANG KAI ZHENYU | Europäisches Patentamt | 2022

    Freier Zugriff

    Laplace Approximation for Real-Time Uncertainty Estimation in Object Detection

    Gui, Ming / Qiu, Tianming / Bauer, Fridolin et al. | IEEE | 2022


    Multi-stage object heading estimation

    LEE DAVID / JIN XIAOHAN / LI CONGCONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    MULTI-STAGE OBJECT HEADING ESTIMATION

    LEE DAVID / JIN XIAOHAN / LI CONGCONG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    MULTI-STAGE OBJECT HEADING ESTIMATION

    LEE DAVID / JIN XIAOHAN / LI CONGCONG et al. | Europäisches Patentamt | 2020

    Freier Zugriff