In order to improve the accuracy of ORB-SLAM2 poses estimation in dynamic environment, an Instance Segmentation method is proposed to remove the moving feature points distributed on the human body and improve the pose accuracy in view of the deception of motion. In this method, ORB feature points are extracted from the input image, and the image is segmented to obtain the position of the pixels in the image. Then the feature points distributed above the human are removed, and the position and attitude are estimated by using the feature points which are relatively stable after the removal. The improved method is used to test on TUM data set. The results show that the improved system can significantly reduce the absolute error and relative drift of pose estimation in dynamic environment, which proves that this method can significantly improve the accuracy of pose estimation in dynamic environment compared with the traditional ORB-SLAM2 system.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    An Improved ORB-SLAM2 in Dynamic Scene with Instance Segmentation


    Beteiligte:
    Qian, Huaming (Autor:in) / Ding, Peng (Autor:in)


    Erscheinungsdatum :

    2019-11-01


    Format / Umfang :

    827673 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Autonomous Navigation Using Monocular ORB SLAM2

    Vithalani, Shubham / Soni, Sneh / Rajpura, Param | Springer Verlag | 2019


    Research on omnidirectional ORB-SLAM2 for mobile robots

    Wang, Yule / Yang, Xubo | IEEE | 2018


    Instance Segmentation as Image Segmentation Annotation

    Watanabe, Thomio / Wolf, Denis F. | IEEE | 2019


    Instance segmentation imaging system

    PHILION JONAH / ZHAO YIBIAO | Europäisches Patentamt | 2023

    Freier Zugriff

    Instance segmentation imaging system

    PHILION JONAH / ZHAO YIBIAO | Europäisches Patentamt | 2020

    Freier Zugriff