Gaussian Process Latent Variable Models for Human Pose Estimation
Lecture notes in computer sciencePublished 21 February 2008
Carl Henrik Ek, Philip H. S. Torr, Neil D. Lawrence
Citations141
SJR quartileQ2
SJR score0.35
SNIP0.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A dynamical model over the latent space is learned which allows us to disambiguate between ambiguous silhouettes by temporal consistency and is easily extended to multiple observation spaces without constraints on type.
Abstract
We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a silhouette representation in a principled way. We learn a dynamical model over the latent space which allows us to disambiguate between ambiguous silhouettes by temporal consistency. The model has only two free parameters and has several advantages over both regression approaches and other generative methods. In addition to the application shown in this paper the suggested model is easily extended to multiple observation spaces without constraints on type.
Keywords
Computer ScienceDecision Sciences
The MIT Press eBooksGaussian Processes for Machine Learning
10,409 Citations2005Carl Edward Rasmussen, Christopher K. I. Williams
The book provides a long-needed, systematic and unified treatment of theoretical and practical aspects of GPs in machine learning, targeted at researchers and students in machine learning and applied statistics.
IEEE Transactions on Information TheoryError bounds for convolutional codes and an asymptotically optimum decoding algorithm
6,705 Citations1967Andrew J. Viterbi
The upper bound is obtained for a specific probabilistic nonsequential decoding algorithm which is shown to be asymptotically optimum for rates above R_{0} and whose performance bears certain similarities to that of sequential decoding algorithms.
Probabilistic Non-linear Principal Component Analysis with Gaussian Process Latent Variable Models
948 Citations2005Neil D. Lawrence
Fast pose estimation with parameter-sensitive hashing
764 Citations2003Shakhnarovich, Viola +1 more
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.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRecovering 3D human pose from monocular images
729 Citations2006Ankur Agarwal, Bill Triggs
A learning-based method for recovering 3D human body pose from single images and monocular image sequences, embedded in a novel regressive tracking framework, using dynamics from the previous state estimate together with a learned regression value to disambiguate the pose.
Lecture notes in computer scienceStochastic Tracking of 3D Human Figures Using 2D Image Motion
694 Citations2000Hedvig Sidenbladh, Michael J. Black +1 more
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.
Gaussian Process Latent Variable Models for Visualisation of High Dimensional Data
684 Citations2003Neil D. Lawrence
A new underlying probabilistic model for principal component analysis (PCA) is introduced that shows that if the prior's covariance function constrains the mappings to be linear the model is equivalent to PCA, and is extended by considering less restrictive covariance functions which allow non-linear mappings.
Shape Context: A New Descriptor for Shape Matching and Object Recognition
512 Citations2000Serge Belongie, Jitendra Malik +1 more
It is demonstrated that shape contexts greatly simplify recovery of correspondences between points of two given shapes, and is used in a nearest-neighbor classifier for recognition of hand written digits as well as 3D objects, using exactly the same distance function.
IEEE Transactions on Pattern Analysis and Machine IntelligenceEfficient shape matching using shape contexts
455 Citations2005Giulio Mori, Serge Belongie +1 more
It is demonstrated that shape contexts can be used to quickly prune a search for similar shapes, and shapemes are used, using vector quantization in the space of shape contexts to obtain prototypical shape pieces.
Gaussian Process Dynamical Models
432 Citations2005Jianguo Wang, Aaron Hertzmann +1 more
This paper marginalize out the model parameters in closed-form, using Gaussian Process (GP) priors for both the dynamics and the observation mappings, resulting in a nonparametric model for dynamical systems that accounts for uncertainty in the model.
Lecture notes in computer scienceNon-linear Bayesian Image Modelling
409 Citations2000Chris Bishop, John Winn
A novel and tractable probabilistic approach to modelling manifolds which can handle complex non-linearities and is illustrated using two classical problems: modelling the manifold of face images and modelling the manifolds of hand-written digits.
Local distance preservation in the GP-LVM through back constraints
221 Citations2006Neil D. Lawrence, Joaquin Quiñonero-Candela
This paper provides an overview of dimensionality reduction techniques, placing the emphasis on the kind of distance relation preserved, and shows how the GP-LVM can be generalized, through back constraints, to additionally preserve local distances.
Discriminative Density Propagation for 3D Human Motion Estimation
217 Citations2005Cristian Sminchisescu, Atul Kanaujia +2 more
The density propagation rules for discriminative inference in continuous, temporal chain models are established and flexible algorithms for learning multimodal state distributions based on compact, conditional Bayesian mixture of experts models are proposed.
Inferring 3D structure with a statistical image-based shape model
195 Citations2003Grauman, Shakhnarovich +1 more
The shape model enables accurate estimation of structure despite segmentation errors or missing views in the input silhouettes, and it works even with only a single input view, using a training set of thousands of pedestrian images generated from a synthetic model.
Learning Shared Latent Structure for Image Synthesis and Robotic Imitation
181 Citations2005Aaron P. Shon, Keith Grochow +2 more
An algorithm that uses Gaussian process regression to learn common hidden structure shared between corresponding sets of heterogenous observations can learn the nonlinear mapping between corresponding views of objects, filling in missing data as needed to synthesize novel views.
Full Body Tracking from Multiple Views Using Stochastic Sampling
108 Citations2005Roland Kehl, M. Bray +1 more
By comparing even a simplified version of SMD to the commonly used Levenberg-Marquardt method, the power of stochastic compared to deterministic sampling is demonstrated, especially in cases of noisy and incomplete data.
Regression-based Hand Pose Estimation from Multiple Cameras
74 Citations2006Teófilo de Campos, David W. Murray
The RVM-based learning method for whole body pose estimation proposed by Agarwal and Triggs is adapted to hand pose recovery and a method for combining multiple views is proposed to help overcome the difficulties presented by the greater degree of self-occlusion.
TU/e Research PortalHuman pose estimation from silhouettes: a consistent approach using distance level sets
74 Citations2002Cristian Sminchisescu, Alexandru Telea
This work introduces an entirely continuous formulation which enforces model estimation consistency by means of an attraction/explanation silhouette-based term pair and presents a novel similarity measure (likelihood) for estimating three-dimensional human pose from image silhouettes in model-based vision applications.
Inferring 3D Structure with a Statistical Image-Based Shape Model
53 Citations2003Kristen Grauman, Gregory Shakhnarovich +1 more
Regression-Based Human Motion Capture From Voxel Data
27 Citations2006Yuning Sun, M. Bray +3 more
A regression based method is proposed to recover human body pose from 3D voxel data using a Bayesian approach based on Mixture of Probabilistic PCA that transforms a collection of 3D shape context descriptors, extracted from the voxels, to a compact feature vector.