@inproceedings{ac0242fb3b1e44fc92495619ca66c4f1,
title = "Discriminative density propagation for 3D human motion estimation",
abstract = "We describe a mixture density propagation algorithm to estimate 3D human motion in monocular video sequences based on observations encoding the appearance of image silhouettes. Our approach is discriminative rather than generative, therefore it does not require the probabilistic inversion of a predictive observation model. Instead, it uses a large human motion capture data-base and a 3D computer graphics human model in order to synthesize training pairs of typical human configurations together with their realistically rendered 2D silhouettes. These are used to directly learn to predict the conditional state distributions required for 3D body pose tracking and thus avoid using the generative 3D model for inference (the learned discriminative predictors can also be used, complementary, as importance samplers in order to improve mixing or initialize generative inference algorithms). We aim for probabilistically motivated tracking algorithms and for models that can represent complex multivalued mappings common in inverse, uncertain perception inferences. Our paper has three contributions: (1) we establish the density propagation rules for discriminative inference in continuous, temporal chain models; (2) we propose flexible algorithms for learning multimodal state distributions based on compact, conditional Bayesian mixture of experts models; and (3) we demonstrate the algorithms empirically on real and motion capture-based test sequences and compare against nearest-neighbor and regression methods.",
keywords = "3D human tracking, Bayesian methods, Density propagation, Hierarchical mixture of experts, Mixture modeling, Sparse regression",
author = "Cristian Sminchisescu and Atul Kanaujia and Zhiguo Li and Dimitris Metaxas",
year = "2005",
doi = "10.1109/CVPR.2005.132",
language = "English (US)",
isbn = "0769523722",
series = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",
publisher = "IEEE Computer Society",
pages = "390--397",
booktitle = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",
address = "United States",
note = "2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 ; Conference date: 20-06-2005 Through 25-06-2005",
}