In this paper, we propose a novel method to establish temporal correspondence between the frames of two videos. 3D epipolar geometry is used to eliminate the distortion generated by the projection from 3D to 2D. Although the fundamental matrix contains the extrinsic property of the projective geometry between views, it is sensitive to noise. Therefore, we propose the use of a rank constraint of corresponding points in two views to measure the similarity between trajectories. This rank constraint shows more robustness and avoids computation of the fundamental matrix. A dynamic programming approach using the similarity measurement is proposed to find the nonlinear time-warping function for videos containing human activities. In this way, videos of different individuals taken at different times and from distinct viewpoints can be synchronized. A temporal pyramid of trajectories is applied to improve the accuracy of the view-invariant dynamic time-warping approach. We show various applications of this approach such as video synthesis, human action recognition, and computer aider training. Compared to state-of-the-art techniques, our method shows a great improvement.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    View-invariant alignment and matching of video sequences


    Contributors:
    Rao, (author) / Gritai, (author) / Shah, (author) / Syeda-Mahmood, (author)


    Publication date :

    2003-01-01


    Size :

    686091 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    View-invariant Alignment and Matching of Video Sequences

    Rao, C. / Gritai, A. / Shah, M. et al. | British Library Conference Proceedings | 2003


    Unsupervised view and rate invariant clustering of video sequences

    Turaga, P. / Veeraraghavan, A. / Chellappa, R. | British Library Online Contents | 2009


    Translational photometric alignment of single-view image sequences

    Harrison, A. P. / Joseph, D. | British Library Online Contents | 2012


    Wide Baseline Matching between Unsynchronized Video Sequences

    Wolf, L. / Zomet, A. | British Library Online Contents | 2006


    Human appearance modeling for matching across video sequences

    Yu, Y. / Harwood, D. / Yoon, K. et al. | British Library Online Contents | 2007