We present a method for recovering 3D human body motion from monocular video sequences using robust image matching, joint limits and non-self-intersection constraints, and a new sample-and-refine search strategy guided by rescaled cost-function covariances. Monocular 3D body tracking is challenging: for reliable tracking at least 30 joint parameters need to be estimated, subject to highly nonlinear physical constraints; the problem is chronically ill conditioned as about 1/3 of the d.o.f. (the depth-related ones) are almost unobservable in any given monocular image; and matching an imperfect, highly flexible self-occluding model to cluttered image features is intrinsically hard. To reduce correspondence ambiguities we use a carefully designed robust matching-cost metric that combines robust optical flow, edge energy, and motion boundaries. Even so, the ambiguity, nonlinearity and non-observability make the parameter-space cost surface multi-modal, unpredictable and ill conditioned, so minimizing it is difficult. We discuss the limitations of CONDENSATION-like samplers, and introduce a novel hybrid search algorithm that combines inflated-covariance-scaled sampling and continuous optimization subject to physical constraints. Experiments on some challenging monocular sequences show that robust cost modelling, joint and self-intersection constraints, and informed sampling are all essential for reliable monocular 3D body tracking.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Covariance scaled sampling for monocular 3D body tracking


    Contributors:


    Publication date :

    2001-01-01


    Size :

    1156615 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Covariance Scaled Sampling for Monocular 3D Body Tracking

    Sminchisescu, C. / Triggs, B. / IEEE | British Library Conference Proceedings | 2001


    Monocular based lane-change on scaled-down autonomous vehicles

    Wen He, / Xiaodong Wang, / Guisheng Chen, et al. | IEEE | 2011


    Monocular Based Lane Change on Scaled-Down Autonomous Vehicles

    He, W. / Wang, X. / Chen, G. et al. | British Library Conference Proceedings | 2011


    True scaled 6 DoF egocentric localisation with monocular wearable systems

    Gutierrez-Gomez, D. / Guerrero, J. J. | British Library Online Contents | 2016


    Temporal motion models for monocular and multiview 3D human body tracking

    Urtasun, R. / Fleet, D. J. / Fua, P. | British Library Online Contents | 2006