Monocular 3D object detection, with the aim of predicting the geometric properties of on-road objects, is a promising research topic for the intelligent perception systems of autonomous driving. Most state-of-the-art methods follow a keypoint-based paradigm, where the keypoints of objects are predicted and employed as the basis for regressing the other geometric properties. In this work, a unified network named as FADNet is presented to address the task of monocular 3D object detection. In contrast to previous keypoint-based methods, we propose to divide the output modalities into different groups according to the estimation difficulty of object properties. Different groups are treated differently and sequentially associated by a convolutional Gated Recurrent Unit. Another contribution of this work is the strategy of depth hint augmentation. To provide characterized depth patterns as hints for depth estimation, a dedicated depth hint module is designed to generate row-wise features named as depth hints, which are explicitly supervised in a bin-wise manner. The contributions of this work are validated by conducting experiments and ablation study on the KITTI benchmark. Without utilizing depth priors, post optimization, or other refinement modules, our network performs competitively against state-of-the-art methods while maintaining a decent running speed.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Monocular 3D Object Detection With Sequential Feature Association and Depth Hint Augmentation


    Beteiligte:
    Gao, Tianze (Autor:in) / Pan, Huihui (Autor:in) / Gao, Huijun (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.06.2022


    Format / Umfang :

    4363979 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Boosting Monocular 3D Object Detection With Object-Centric Auxiliary Depth Supervision

    Kim, Youngseok / Kim, Sanmin / Sim, Sangmin et al. | IEEE | 2023



    Hint generation and completion for feature recognition

    Han,J.H. / Reguicha,A.A. / Univ.of Southern California,US | Kraftfahrwesen | 1996


    Monocular Fisheye Depth Estimation for UAV Applications with Segmentation Feature Integration

    Jaisawal, Pravin Kumar / Papakonstantinou, Stephanos / Gollnick, Volker | IEEE | 2024


    Hint Generation and Completion for Feature Recognition

    Han, J.-H. / Requicha, A. A. G. | British Library Conference Proceedings | 1996