Recovering deformable 3D motion from temporal 2D point tracks in a monocular video is an open problem with many everyday applications throughout science and industry, or the new augmented reality. Recently, several techniques have been proposed to deal the problem called Non-Rigid Structure from Motion (NRSfM), however, they can exhibit poor reconstruction performance on complex motion. In this project, we will analyze these situations for primitive human actions such as walk, run, sit, jump, etc. on different scenarios, reviewing first the current techniques to finally present our novel method. This approach is able to model complex motion into a union of subspaces, rather than the summation occurring in standard low-rank shape methods, allowing better reconstruction accuracy. Experiments in a wide range of sequences and types of motion illustrate the benefits of this new approach


    Access

    Download


    Export, share and cite



    Title :

    Non-Rigid Structure from Motion for Complex Motion



    Publication date :

    2016-09-05


    Type of media :

    Theses


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629




    Non-rigid Motion Analysis: Isometric Motion

    Penna, M. A. | British Library Online Contents | 1992


    Implicit Non-Rigid Structure-from-Motion with Priors

    Olsen, S. I. | British Library Online Contents | 2008


    Rigid Structure from Motion from a Blind Source Separation Perspective

    Fortuna, J. / Martinez, A. M. | British Library Online Contents | 2010


    Dynamic rigid motion estimation from weak perspective

    Soatto, S. / Perona, P. | IEEE | 1995


    Multilinear Factorizations for Multi-Camera Rigid Structure from Motion Problems

    Angst, R. / Pollefeys, M. | British Library Online Contents | 2013