Covariance Scaled Sampling for Monocular 3D Body Tracking

Cristian Sminchisescu 1 Bill Triggs 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/inria-00548273
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 8:42:38 AM
Last modification on : Wednesday, April 11, 2018 - 1:54:30 AM
Long-term archiving on: Thursday, June 30, 2011 - 1:44:52 PM

File

Sminchisescu-cvpr01.pdf
Files produced by the author(s)

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Cristian Sminchisescu, Bill Triggs. Covariance Scaled Sampling for Monocular 3D Body Tracking. International Conference on Computer Vision & Pattern Recognition (CVPR '01), Dec 2001, Kauai, United States. pp.447--454, ⟨10.1109/CVPR.2001.990509⟩. ⟨inria-00548273⟩

Share

Metrics

Record views

333

Files downloads

437