We present a procedure for egomotion estimation from visual input of a stereo pair of video cameras. The 3D egomotion problem, which has six degrees of freedom in general, is simplified to four dimensions and further decomposed to two two-dimensional subproblems. The decomposition allows us to use a voting strategy to identify the most probable solution, avoiding the random sampling (RANSAC) or other approximation techniques. The input constitutes of image correspondences between consecutive stereo pairs, i.e. feature points do not need to be tracked over time. The experiments show that even if a trajectory is put together as a simple concatenation of frame-to-frame increments, it comes out reliable and precise.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A voting strategy for visual ego-motion from stereo


    Contributors:


    Publication date :

    2010-06-01


    Size :

    1593394 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Voting Strategy for Visual Ego-Motion from Stereo, pp. 382-387

    Obdrzalek, S. / Matas, G. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2010


    Voting-based grouping and interpretation of visual motion

    Nicolescu, M. / Medioni, G. | IEEE | 2004


    Visual surface segmentation from stereo

    Chen, L.-H. / Lin, W.-C. | British Library Online Contents | 1997


    Passive photometric stereo from motion

    Jongwoo Lim, / Ho, J. / Ming-Hsuan Yang, et al. | IEEE | 2005


    A voting stereo matching method for real-time obstacle detection

    Hariti, M. / Ruichek, Y. / Koukam, A. | Tema Archive | 2003