In this paper, we present an Adaptive Feature Optimization Strategy as a novel frontend feature selection strategy which can be applied in the most direct method-based Simultaneous Localization And Mapping (SLAM) system for high accuracy, efficiency and robustness compared to the original SLAM system. It chooses adaptively the ORB points or Direct Sparse Odometry (DSO)-based points for tracking depending on in which scenario the cameras situate. Our evaluation on public datasets presents that the SLAM system integrated with our strategy outperforms the state-of-the-art which significantly reduces the processing time for each frame while retains the tracking accuracy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An Adaptive Feature Optimization Strategy for Direct Visual Odometry


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Wu, Meiping (editor) / Niu, Yifeng (editor) / Gu, Mancang (editor) / Cheng, Jin (editor) / Deng, Junyuan (author) / Pei, Ling (author) / Wu, Qi (author) / Li, Tao (author) / Chen, Xin (author) / Yu, Wenxian (author)

    Conference:

    International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021



    Publication date :

    2022-03-18


    Size :

    12 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    An Adaptive Feature Optimization Strategy for Direct Visual Odometry

    Deng, Junyuan / Pei, Ling / Wu, Qi et al. | British Library Conference Proceedings | 2022


    Deep Direct Visual Odometry

    Zhao, Chaoqiang / Tang, Yang / Sun, Qiyu et al. | IEEE | 2022


    Feature Tracking For Visual Odometry

    HUNT SHAWN | European Patent Office | 2019

    Free access

    Feature tracking for visual odometry

    HUNT SHAWN | European Patent Office | 2020

    Free access

    Visual Odometry

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