This paper presents a method for detecting independently moving objects (IMOs) from a monocular camera mounted on a moving car. A CNN-based classifier is employed to generate IMO candidate patches; independent motion is detected by geometric criteria on keypoint trajectories in these patches. Instead of looking only at two consecutive frames, we analyze keypoints inside the IMO candidate patches through multi-frame epipolar consistency checks. The obtained motion labels (IMO/static) are then propagated over time using the combination of motion cues and appearance-based information of the IMO candidate patches. We evaluate the performance of our method on the KITTI dataset, focusing on sub-sequences containing IMOs.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    CNN-based multi-frame IMO detection from a monocular camera


    Beteiligte:
    Fanani, Nolang (Autor:in) / Ochs, Matthias (Autor:in) / Sturck, Alina (Autor:in) / Mester, Rudolf (Autor:in)


    Erscheinungsdatum :

    01.06.2018


    Format / Umfang :

    7718144 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    CNN-BASED MULTI-FRAME IMO DETECTION FROM A MONOCULAR CAMERA

    Fanani, Nolang / Ochs, Matthias / Sturck, Alina et al. | British Library Conference Proceedings | 2018


    Obstacle detection based on multiple cues fusion from monocular camera

    Liu, Wei / Zuo, Liyuan / Yu, Hongfei et al. | IEEE | 2013


    Geometry-based next frame prediction from monocular video

    Mahjourian, Reza / Wicke, Martin / Angelova, Anelia | IEEE | 2017


    MONOCULAR VISION RANGING METHOD, STORAGE MEDIUM, AND MONOCULAR CAMERA

    MIYAHARA SHUNJI | Europäisches Patentamt | 2022

    Freier Zugriff

    Person Detection for an Orthogonally Placed Monocular Camera

    Pavel Skrabanek / Petr Dolezel / Zdenek Nemec et al. | DOAJ | 2020

    Freier Zugriff