Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. To achieve the real-time execution of the proposed method, we apply semantic segmentation only to downsampled keyframes in parallel with mapping processes. In addition, the proposed method corrects scales of camera poses and three-dimensional (3D) points, using estimated ground plane from road-labeled 3D points and the real camera height. The proposed method also removes inappropriate corner features labeled as moving objects and low parallax areas. Experiments with eight video sequences demonstrate that the proposed monocular SLAM system achieves significantly improved and comparable trajectory tracking accuracy, compared to existing state-of-the-art monocular and stereo SLAM systems, respectively. The proposed system can achieve real-time tracking on a standard CPU potentially with a standard GPU support, whereas existing segmentation-aided monocular SLAM does not.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames


    Beteiligte:
    Lee, Jinkyu (Autor:in) / Back, Muhyun (Autor:in) / Hwang, Sung Soo (Autor:in) / Chun, Il Yong (Autor:in)


    Erscheinungsdatum :

    2023-03-01


    Format / Umfang :

    3541323 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Parsimonious real time monocular SLAM

    Bresson, Guillaume / Feraud, Thomas / Aufrere, Romuald et al. | IEEE | 2012


    Parsimonious Real Time Monocular SLAM

    Bresson, G. / Feraud, T. / Aufrere, R. et al. | British Library Conference Proceedings | 2012


    GenPa-SLAM: Using a General Panoptic Segmentation for a Real-Time Semantic Landmark SLAM

    Beer, Lukas / Luettel, Thorsten / Wuensche, Hans-Joachim | IEEE | 2022


    Real-Time Monocular SLAM With Low Memory Requirements

    Bresson, Guillaume / Feraud, Thomas / Aufrere, Romuald et al. | IEEE | 2015


    Real-Time Monocular SLAM With Low Memory Requirements

    Bresson, Guillaume | Online Contents | 2015