We investigate a new strategy for improving localization accuracy of detected vehicles using a deep convolutional neural network. Specifically, we implement an iterative bounding box refinement on top of a state-of-the-art object detector. The bounding box refinement is achieved by iteratively pooling features from previous object location predictions. On KITTI vehicle detection benchmark, we achieve up to 6% improvement in average precision over the baseline results. Furthermore, the proposed refinement framework is computationally light, allowing for object detection at high run-time speeds. Our method runs at ∼0.22 seconds per image on images of size 1242 × 375, making it one of the fastest detectors reported on the KITTI object detection benchmark.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    RefineNet: Iterative refinement for accurate object localization


    Beteiligte:


    Erscheinungsdatum :

    2016-11-01


    Format / Umfang :

    2245795 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    RefineNet: Refining Object Detectors for Autonomous Driving

    Rajaram, Rakesh Nattoji / Ohn-Bar, Eshed / Trivedi, Mohan Manubhai | IEEE | 2016


    Iterative Model Refinement for Orbital Trajectory Optimization (AAS 12-231)

    Hudson, J. / Kolmanovsky, I. / American Astronautical Society et al. | British Library Conference Proceedings | 2012


    Estimating urban traffic states using iterative refinement and Wardrop equilibria

    Li, Weizi / Jiang, Meilei / Chen, Yaoyu et al. | IET | 2018

    Freier Zugriff

    Estimating urban traffic states using iterative refinement and Wardrop equilibria

    Li, Weizi / Jiang, Meilei / Chen, Yaoyu et al. | Wiley | 2018

    Freier Zugriff

    CONTEXTUALIZATION AND REFINEMENT OF SIMULTANEOUS LOCALIZATION AND MAPPING

    YANG MENGDA / JIANG WEIXIN / YAN ZHENG | Europäisches Patentamt | 2022

    Freier Zugriff