This paper presents a real-time and dense structure from motion approach, based on an efficient planar parallax motion decomposition, and also proposes several optimizations to improve the optical flow firstly computed. Later, it is estimated using our own GPU implementation of the well-known pyramidal algorithm of Lucas and Kanade. Then, each pair of points previously matched is evaluated according to the spatial continuity constraint provided by the Tensor Voting framework applied in the 4-D joint space of image coordinates and motions. Thus, assuming the ground locally planar, the homography corresponding to its image motion is robustly and quickly estimated using RANSAC on designated well-matched pairwise by the prior Tensor Voting process. Depth map is finally computed from the parallax motion decomposition. The initialization of successive runs is also addressed, providing noticeable enhancement, as well as the hardware integration using the CUDA technology.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Real-time quasi dense two-frames depth map for Autonomous Guided Vehicles


    Beteiligte:
    Ducrot, A. (Autor:in) / Dumortier, Y. (Autor:in) / Herlin, I. (Autor:in) / Ducrot, V. (Autor:in)


    Erscheinungsdatum :

    01.06.2011


    Format / Umfang :

    1441405 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Real-Time Quasi Dense Two-Frames Depth Map for Autonomous Guided Vehicles

    Ducrot, A. / Dumortier, Y. / Herlin, I. et al. | British Library Conference Proceedings | 2011



    Real-Time Dense Stereo for Intelligent Vehicles

    Mark, W.van der | Online Contents | 2006


    Real-time dense stereo for intelligent vehicles

    van der Mark, W. / Gavrila, D.M. | IEEE | 2006