Book ChapterDOI
Monocular tracking with a mixture of view-dependent learned models
Tobias Jaeggli,Esther Koller-Meier,Luc Van Gool +2 more
- pp 494-503
Reads0
Chats0
TLDR
In this article, the joint probability distribution of appearance and body pose using a mixture of view-dependent models is learned for monocular human body tracking using learned models, which can capture multimodal and nonlinear relationships reliably.Abstract:
This paper considers the problem of monocular human body tracking using learned models. We propose to learn the joint probability distribution of appearance and body pose using a mixture of view-dependent models. In such a way the multimodal and nonlinear relationships can be captured reliably. We formulate inference algorithms that are based on generative models while exploiting the advantages of a learned model when compared to the traditionally used geometric body models. Given static images or sequences, body poses and bounding box locations are inferred using silhouette based image descriptors. Prior information about likely body poses and a motion model are taken into account. We consider analytical computations and Monte-Carlo techniques, as well as a combination of both. In a Rao-Blackwellised particle filter, the tracking problem is partitioned into a part that is solved analytically, and a part that is solved with particle filtering. Tracking results are reported for human locomotionread more
Citations
More filters
Journal ArticleDOI
A survey of advances in vision-based human motion capture and analysis
TL;DR: This survey reviews recent trends in video-based human capture and analysis, as well as discussing open problems for future research to achieve automatic visual analysis of human movement.
Proceedings ArticleDOI
Semi-supervised Hierarchical Models for 3D Human Pose Reconstruction
TL;DR: This paper combines multilevel encodings with improved stability to geometric transformations, with metric learning and semi-supervised manifold regularization methods in order to further profile them for task-invariance -resistance to background clutter and within the same human pose class differences.
Journal ArticleDOI
BM³E : Discriminative Density Propagation for Visual Tracking
TL;DR: The research establishes the density propagation rules for discriminative inference in continuous, temporal chain models and proposes flexible supervised and unsupervised algorithms to learn feed-forward, multivalued contextual mappings based on compact, conditional Bayesian mixture of experts models.
Journal ArticleDOI
Shared Kernel Information Embedding for Discriminative Inference
TL;DR: An LVM called the Kernel Information Embedding (KIE) is proposed that defines a coherent joint density over the input and a learned latent space and a generalization, the shared KIE (sKIE), that allows us to model multiple input spaces using a single, shared latent representation.
Journal ArticleDOI
Learning Generative Models for Multi-Activity Body Pose Estimation
TL;DR: In this paper, a generative model of the relationship of body pose and image appearance using a sparse kernel regressor is proposed to track through poorly segmented low-resolution image sequences where tracking otherwise fails.
References
More filters
Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks.
Kevin Murphy,Stuart Russell +1 more
TL;DR: In this article, Rao-Blackwellised particle filters (RBPFs) were proposed to increase the efficiency of particle filtering, using a technique known as Rao-blackwellisation.
Book ChapterDOI
Rao-blackwellised particle filtering for dynamic Bayesian networks
TL;DR: In this paper, Rao-Blackwellised particle filters (RBPFs) were proposed to increase the efficiency of particle filtering, using a technique known as Rao-blackwellisation.
Proceedings ArticleDOI
Articulated body motion capture by annealed particle filtering
TL;DR: The principal contribution of the paper is the development of a modified particle filter for search in high dimensional configuration spaces that uses a continuation principle based on annealing to introduce the influence of narrow peaks in the fitness function, gradually.
Proceedings ArticleDOI
Fast pose estimation with parameter-sensitive hashing
Shakhnarovich,Viola,Darrell +2 more
TL;DR: A new algorithm is introduced that learns a set of hashing functions that efficiently index examples relevant to a particular estimation task, and can rapidly and accurately estimate the articulated pose of human figures from a large database of example images.
Book ChapterDOI
Stochastic Tracking of 3D Human Figures Using 2D Image Motion
TL;DR: A probabilistic method for tracking 3D articulated human figures in monocular image sequences that relies only on a frame-to-frame assumption of brightness constancy and hence is able to track people under changing viewpoints, in grayscale image sequences, and with complex unknown backgrounds.