3D object detection has become a hot topic in intelligent vehicle applications in recent years. Generally, deep learning has been the primary framework used in 3D object detection, and regression of the object location and classification of the objectness are the two indispensable components. In the process of training, the $\ell_{n}\ (n=1,2)$ and the focal loss are considered as the frequent solutions to minimize the regression and classification loss, respectively. However, there are two problems to be solved in the existing methods. For regression component, there is a gap between evaluation metrics, e.g., 3D Intersection over Union (IoU), and the traditional regression loss. As for the classification component, confidence score exists ambiguous due to the binary label assignment of target. To solve these problems, we propose a loss by jointing 3D IoU and other geometric attributes (named as jointed attribute-oriented 3D loss), which can be directly used in optimizing the regression component. In addition, the jointed attribute-oriented 3D loss can assign a soft label for supervising the training of the classification. By incorporating the proposed loss function into several state-of-the-art 3D object detection methods, the significant performance improvement has been achieved on the KITTI benchmark.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Improving 3D Object Detection via Joint Attribute-oriented 3D Loss


    Contributors:
    Ye, Zhen (author) / Xue, Jianru (author) / Dou, Jian (author) / Pan, Yuxin (author) / Fang, Jianwu (author) / Wang, Di (author) / Zheng, Nanning (author)


    Publication date :

    2020-10-19


    Size :

    3571102 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Improving scene attribute recognition using web-scale object detectors

    Tung, F. / Little, J.J. | British Library Online Contents | 2015


    Improving object detection with boosted histograms

    Laptev, I. | British Library Online Contents | 2009


    Object oriented technology

    British Library Online Contents | 1998


    Method and system for improving object detection and object classification

    SAMII SOHEIL / DUTTA BORDOLOI UNMESH / BAI FAN et al. | European Patent Office | 2020

    Free access

    The Object Of Object-Oriented Authoring

    Kozel, K. | British Library Online Contents | 1996