Monocular visual odometry is a fundamental problem in computer vision and it was extensively studied in literature. The vast majority of visual odometry algorithms are based on a standard pipeline consisting in feature detection, feature matching, motion estimation and local optimization. Only recently, deep learning approaches have shown cutting-edge performance, replacing the standard pipeline with an end-to-end solution. One of the main advantages of deep learning approaches over the standard methods is the reduced inference time, that is an important requirement for the application of visual odometry in real-time. Less emphasis, however, has been placed on memory requirements and training efficiency. The memory footprint, in particular, is important for real world applications such as robot navigation or autonomous driving, where the devices have limited memory resources. In this paper we tackle both aspects introducing novel architectures based on Depth-Wise Separable Convolutional Neural Network and deep Quaternion Recurrent Convolutional Neural Network. In particular, we obtain equal or better accuracy with respect to the other state-of-the-art methods on the KITTI VO dataset with a reduction of the number of parameters and a speed-up in the inference time.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Visual odometry with depth-wise separable convolution and quaternion neural networks



    Erscheinungsdatum :

    01.01.2023


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    A Dual Quaternion Based Visual Odometry Method for a Lunar Lander

    Uzun, Semra Sultan / Soken, Halil Ersin | IEEE | 2024


    Visual odometry

    Nister, D. / Naroditsky, O. / Bergen, J. | IEEE | 2004


    Visual Odometry

    Nister, D. / Naroditsky, O. / Bergen, J. et al. | British Library Conference Proceedings | 2004


    Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry

    Shinde, Kashmira / Lee, Jongseok / Humt, Matthias et al. | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2020

    Freier Zugriff

    A real-time method for depth enhanced visual odometry

    Zhang, J. | British Library Online Contents | 2017