This paper proposes PredictiveSLAM, a novel extension to ORB-SLAM2, which extracts features from specific regions of interest (ROI). The proposed method was designed with the risk posed both to humans and robotic systems in large-scale industrial sites in mind. The ROI are determined through an object detection network trained to detect moving human beings. The method detects and removes humans from feature extraction, predicting their potential future trajectory. This is done by omitting a specific ROI from extraction, deemed to be occluded in consecutive time steps. Two masking methods -static object and moving object trajectories - are proposed. This approach improves tracking accuracy and the performance of SLAM by removing the dynamic features from the reference for tracking and loop closures. The method is tested on data collected in a laboratory environment and compared against a state-of-the-art ground truth system. The validation data was collected from real-time experiments which aimed at simulating the typical human worker behaviours in industrial environments using an unmanned aerial vehicle (UAV). This study illustrates the advantages of the proposed method over earlier approaches, even with a highly dynamic camera setup on a UAV working in challenging environments.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    PredictiveSLAM - Robust Visual SLAM Through Trajectory-Aware Object Masking


    Beteiligte:
    Heis, Micha (Autor:in) / Hansen, Jakob Grimm (Autor:in) / Li, Dengyun (Autor:in) / Kozlowski, Michal (Autor:in) / Kayacan, Erdal (Autor:in)


    Erscheinungsdatum :

    2023-06-06


    Format / Umfang :

    5719535 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Fast, Robust, Accurate, Multi-Body Motion Aware SLAM

    Yang, Linghao / Zhang, Yunzhou / Tian, Rui et al. | IEEE | 2024


    UVS: Underwater Visual SLAM - A Robust Monocular Visual SLAM System for Lifelong Underwater Operations

    Leonardi, Marco / Ludvigsen, Martin / Stahl, Annette et al. | BASE | 2023

    Freier Zugriff

    DOT: Dynamic Object Tracking for Visual SLAM

    Ballester, Campos | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2020

    Freier Zugriff

    InertialNet: Toward Robust SLAM via Visual Inertial Measurement

    Liu, Tse-An Jacky / Lin, Huei-Yung / Lin, Wei-Yang | IEEE | 2019


    A Novel Texture-Less Object Oriented Visual SLAM System

    Dong, Yanchao / Wang, Senbo / Yue, Jiguang et al. | IEEE | 2021