Making Convolutional Neural Networks (CNNs) successful in learning problems like image based ego motion estimation, highly depends on the ability of the network to extract the temporal information from videos. Therefore, the architecture of a network needs the capability to learn temporal features. We propose two CNN architectures which are able to learn features for the extraction of this temporal information and are able to solve problems like ego motion estimation. Our architectures achieve first promising results in ego motion estimation and might be a good foundation for systems dealing with temporal information. As the architectures reach real time inference time, they can be applied in domains like autonomous driving.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning temporal features with CNNs for monocular visual ego motion estimation


    Contributors:


    Publication date :

    2017-10-01


    Size :

    954653 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    MONOCULAR VISUAL LOCALIZATION USING ROAD STRUCTURAL FEATURES

    Yu, Y. / Zhao, H. / Davoine, F. et al. | British Library Conference Proceedings | 2014


    Momo: Monocular motion estimation on manifolds

    Graeter, Johannes / Strauss, Tobias / Lauer, Martin | IEEE | 2017


    Retrospective head motion estimation in structural brain MRI with 3D CNNs

    Iglesias, JE / Lerma-Usabiaga, G / Garcia-Peraza-Herrera, LC et al. | BASE | 2017

    Free access

    Multimodal scale estimation for monocular visual odometry

    Fanani, Nolang / Sturck, Alina / Barnada, Marc et al. | IEEE | 2017