Monocular 3D object detection has attracted great attention due to simplicity and low cost. However, object location recovery in the 3D space from a monocular image is challenging since the depth information is lost. How to estimate the instance depth is the core problem to be solved. Intuitively, the ground depth is continuous and global in essence, independent of the objects in the scene. Therefore the ground depth estimation can be more accurate and easier than the object depth estimation. Inspired by this, we propose to map a set of surface points of an object onto the ground plane and decompose the object depth solving problem into the ground depth estimation and surface point heights estimation. During the training stage, dense ground depth labels are provided by the ground truth (GT) surface depths of objects from LiDAR data. In the inference stage, surface depths are recovered through querying the ground depth map. As a result, a set of instance depth candidates are obtained and the final instance depth can be assembled according to their uncertainties. In addition, since most of the mapped ground points are occluded by the object which may mislead the network learning, we devise a depth expansion strategy to extend the ground depth labels. The proposed method MonoSGC achieves state-of-the-art (SOTA) performance on the KITTI and Waymo datasets. Ablation studies demonstrate the effectiveness of the proposed components. The code and model are released at https://github.com/JiYinshuai/MonoSGC.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Depth Estimation From Surface-Ground Correspondence for Monocular 3D Object Detection


    Beteiligte:
    Ji, Yinshuai (Autor:in) / Xu, Jinhua (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.11.2024


    Format / Umfang :

    2516567 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Realtime depth estimation and obstacle detection from monocular video

    Wedel, Andreas / Franke, Uwe / Klappstein, Jens et al. | Tema Archiv | 2006


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

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


    Mono-DCNet: Monocular 3D Object Detection via Depth-based Centroid Refinement and Pose Estimation

    Astudillo, Armando / Al-Kaff, Abdulla / Garcia, Fernando | IEEE | 2022


    Joint vehicle detection and distance prediction via monocular depth estimation

    Shen, Chao / Zhao, Xiangmo / Liu, Zhanwen et al. | Wiley | 2020

    Freier Zugriff

    Sparse Pseudo-LiDAR Depth Assisted Monocular Depth Estimation

    Shao, Shuwei / Pei, Zhongcai / Chen, Weihai et al. | IEEE | 2024