With the development of computer technology and the increasing data processing capability and speed, the robot vision-based SLAM problem is gradually emerging. In this paper, based on the traditional vision odometry implementation scheme, the ORB feature extraction algorithm is used to extract the feature points of the image and calculate the BRIEF descriptors, and then a combination of PnP and improved ICP is used to solve the bit pose of the camera. In order to improve the accuracy and stability of the algorithm, the PROSAC algorithm is used to reject the mis-match in this paper. Finally, the algorithm is tested using the public dataset of TUM, which proves that the algorithm has faster computational speed and stability.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Study on visual odometry and optimization of SLAM system


    Beteiligte:
    Chengxu, Yao (Autor:in)


    Erscheinungsdatum :

    12.10.2022


    Format / Umfang :

    1965616 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    CoVOR-SLAM: Cooperative SLAM Using Visual Odometry and Ranges for Multi-Robot Systems

    Lee, Young-Hee / Zhu, Chen / Wiedemann, Thomas et al. | IEEE | 2025

    Freier Zugriff

    Visual Odometry

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


    Visual odometry

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



    Automotive visual odometry

    Buczko, Martin / Shaker Verlag | TIBKAT | 2018