Depth estimation from monocular image plays an essential role in artificial intelligence, which is one of the important ways for sensing the operating environment in automatic-driving system or advanced driving assistant system. The most recent approaches have gained significant improvement for depth prediction based on convolutional neural networks (CNNs). In this paper, a novel framework of CNNs is proposed for monocular depth estimation based on deep ordinal regression network (DORN) and a U-net structure. The new model is trained, verified in process and tested on 5000 images from a simulation experiment platform provide by “Grand Theft Auto”. To eliminate or at least largely reduce the impact from ground truth with no depth values, three different training strategies were employed for network optimization. We developed an effective weighted training strategy for depth prediction to improve the estimation accuracy. The comparison of evaluations over our results and DORN demonstrated the effectiveness of our method. The results showed that the proposed method achieved state-of-the-art performances.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An Improved Convolutional Neural Network for Monocular Depth Estimation


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Wang, Wuhong (editor) / Baumann, Martin (editor) / Jiang, Xiaobei (editor) / Kang, Jing (author) / Dang, Anrong (author) / Zhang, Bailing (author) / Wang, Yongming (author) / Su, Hang (author) / Su, Fei (author) / Ci, Tianyu (author)


    Publication date :

    2020-03-24


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation

    Dong, Xingshuai / Garratt, Matthew A. / Anavatti, Sreenatha G. et al. | IEEE | 2022


    Monocular depth estimation

    European Patent Office | 2021

    Free access

    Visual Depth Mapping from Monocular Images using Recurrent Convolutional Neural Networks

    Mern, John M. / Julian, Kyle D. / Tompa, Rachael E. et al. | TIBKAT | 2019


    Visual Depth Mapping from Monocular Images using Recurrent Convolutional Neural Networks

    Mern, John M. / Julian, Kyle D. / Tompa, Rachael E. et al. | AIAA | 2019


    Monocular Depth Estimation Using Information Exchange Network

    Su, Wen / Zhang, Haifeng / Zhou, Quan et al. | IEEE | 2021