This paper presents a novel approach for joint object detection and orientation estimation in a single deep convolutional neural network utilizing proposals calculated from 3D data. For orientation estimation, we extend a R-CNN like architecture by several carefully designed layers. Two new object proposal methods are introduced, to make use of stereo as well as lidar data. Our experiments on the KITTI dataset show that by combining proposals of both domains, high recall can be achieved while keeping the number of proposals low. Furthermore, our method for joint detection and orientation estimation outperforms state of the art approaches for cyclists on the easy test scenario of the KITTI test dataset.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pose-RCNN: Joint object detection and pose estimation using 3D object proposals


    Contributors:
    Braun, Markus (author) / Qing Rao, (author) / Wang, Yikang (author) / Flohr, Fabian (author)


    Publication date :

    2016-11-01


    Size :

    2716789 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    OBJECT POSE ESTIMATION

    SHRIVASTAVA SHUBHAM / PANDEY GAURAV / CHAKRAVARTY PUNARJAY | European Patent Office | 2023

    Free access

    OBJECT POSE ESTIMATION

    PAVONE MARCO / YANG HENG | European Patent Office | 2024

    Free access

    Object pose estimation

    SHRIVASTAVA SHUBHAM / PANDEY GAURAV / CHAKRAVARTY PUNARJAY | European Patent Office | 2024

    Free access

    Viewpoint-aware object detection and continuous pose estimation

    Glasner, D. / Galun, M. / Alpert, S. et al. | British Library Online Contents | 2012


    Factorization of view-object manifolds for joint object recognition and pose estimation

    Zhang, H. / El-Gaaly, T. / Elgammal, A. et al. | British Library Online Contents | 2015