TY - JOUR

T1 - Optimization and filtering for human motion capture

T2 - AAA multi-layer framework

AU - Gall, Juergen

AU - Rosenhahn, Bodo

AU - Brox, Thomas

AU - Seidel, Hans Peter

PY - 2008/11/15

Y1 - 2008/11/15

N2 - Local optimization and filtering have been widely applied to model-based 3D human motion capture. Global stochastic optimization has recently been proposed as promising alternative solution for tracking and initialization. In order to benefit from optimization and filtering, we introduce a multi-layer framework that combines stochastic optimization, filtering, and local optimization. While the first layer relies on interacting simulated annealing and some weak prior information on physical constraints, the second layer refines the estimates by filtering and local optimization such that the accuracy is increased and ambiguities are resolved over time without imposing restrictions on the dynamics. In our experimental evaluation, we demonstrate the significant improvements of the multi-layer framework and provide quantitative 3D pose tracking results for the complete HumanEva-II dataset. The paper further comprises a comparison of global stochastic optimization with particle filtering, annealed particle filtering, and local optimization.

AB - Local optimization and filtering have been widely applied to model-based 3D human motion capture. Global stochastic optimization has recently been proposed as promising alternative solution for tracking and initialization. In order to benefit from optimization and filtering, we introduce a multi-layer framework that combines stochastic optimization, filtering, and local optimization. While the first layer relies on interacting simulated annealing and some weak prior information on physical constraints, the second layer refines the estimates by filtering and local optimization such that the accuracy is increased and ambiguities are resolved over time without imposing restrictions on the dynamics. In our experimental evaluation, we demonstrate the significant improvements of the multi-layer framework and provide quantitative 3D pose tracking results for the complete HumanEva-II dataset. The paper further comprises a comparison of global stochastic optimization with particle filtering, annealed particle filtering, and local optimization.

KW - Filtering

KW - Human motion capture

KW - Stochastic optimization

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=75149167102&partnerID=8YFLogxK

U2 - 10.1007/s11263-008-0173-1

DO - 10.1007/s11263-008-0173-1

M3 - Article

AN - SCOPUS:75149167102

VL - 87

SP - 75

EP - 92

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1-2

ER -