Results 1  10
of
77
Stochastic Tracking of 3D Human Figures Using 2D Image Motion
 In European Conference on Computer Vision
, 2000
"... . A probabilistic method for tracking 3D articulated human gures in monocular image sequences is presented. Within a Bayesian framework, we de ne a generative model of image appearance, a robust likelihood function based on image graylevel dierences, and a prior probability distribution over pose an ..."
Abstract

Cited by 320 (33 self)
 Add to MetaCart
. A probabilistic method for tracking 3D articulated human gures in monocular image sequences is presented. Within a Bayesian framework, we de ne a generative model of image appearance, a robust likelihood function based on image graylevel dierences, and a prior probability distribution over pose and joint angles that models how humans move. The posterior probability distribution over model parameters is represented using a discrete set of samples and is propagated over time using particle ltering. The approach extends previous work on parameterized optical ow estimation to exploit a complex 3D articulated motion model. It also extends previous work on human motion tracking by including a perspective camera model, by modeling limb self occlusion, and by recovering 3D motion from a monocular sequence. The explicit posterior probability distribution represents ambiguities due to image matching, model singularities, and perspective projection. The method relies only on a...
Robust Online Appearance Models for Visual Tracking
, 2001
"... We propose a framework for learning robust, adaptive, appearance models to be used for motionbased tracking of natural objects. The approach involves a mixture of stable image structure, learned over long time courses, along with 2frame motion information and an outlier process. An online EMalgor ..."
Abstract

Cited by 242 (3 self)
 Add to MetaCart
We propose a framework for learning robust, adaptive, appearance models to be used for motionbased tracking of natural objects. The approach involves a mixture of stable image structure, learned over long time courses, along with 2frame motion information and an outlier process. An online EMalgorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motionbased tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions. It is also provides the ability to adapt to natural changes in appearance, such as those due to facial expressions or variations in 3D pose. We show experimental results on a variety of natural image sequences of people moving within cluttered environments.
A Multiple Hypothesis Approach to Figure Tracking
, 1999
"... This paper describes a probabilistic multiplehypothesis framework for tracking highly articulated objects. In this framework, the probability density of the tracker state is represented as a set of modes with piecewise Gaussians characterizing the neighborhood around these modes. The temporal evolu ..."
Abstract

Cited by 188 (9 self)
 Add to MetaCart
This paper describes a probabilistic multiplehypothesis framework for tracking highly articulated objects. In this framework, the probability density of the tracker state is represented as a set of modes with piecewise Gaussians characterizing the neighborhood around these modes. The temporal evolution of the probability density is achieved through sampling from the prior distribution, followed by local optimization of the sample positions to obtain updated modes. This method of generating hypotheses from statespace search does not require the use of discrete features unlike classical multiplehypothesis tracking. The parametric form of the model is suited for highdimensional statespaces which cannot be efficiently modeled using nonparametric approaches. Results are shown for tracking Fred Astaire in a movie dance sequence.
3D Articulated Models and MultiView Tracking with Physical Forces
"... this article we focus on the study of the gestures of a person, but the same methodology could be applied to the study of robots motions or of other kinds of articulated objects. Some examples of applications are listed in the table 1. ..."
Abstract

Cited by 157 (0 self)
 Add to MetaCart
this article we focus on the study of the gestures of a person, but the same methodology could be applied to the study of robots motions or of other kinds of articulated objects. Some examples of applications are listed in the table 1.
Estimating Human Body Configurations using Shape Context Matching
, 2002
"... The problem we consider in this paper is to take a single twodimensional image containing a human body, locate the joint positions, and use these to estimate the body configuration and pose in threedimensional space. The basic approach is to store a number of exemplar 2D views of the human body in ..."
Abstract

Cited by 146 (11 self)
 Add to MetaCart
The problem we consider in this paper is to take a single twodimensional image containing a human body, locate the joint positions, and use these to estimate the body configuration and pose in threedimensional space. The basic approach is to store a number of exemplar 2D views of the human body in a variety of different configurations and viewpoints with respect to the camera. On each of these stored views, the locations of the body joints (left elbow, right knee, etc.) are manually marked and labelled for future use. The test shape is then matched to each stored view, using the technique of shape context matching in conjunction with a kinematic chainbased deformation model. Assuming that there is a stored view sufficiently similar in configuration and pose, the correspondence process will succeed. The locations of the body joints are then transferred from the exemplar view to the test shape. Given the joint locations, the 3D body configuration and pose are then estimated.
Covariance scaled sampling for monocular 3D body tracking
 CVPR
, 2001
"... We present a method for recovering 3D human body motion from monocular video sequences using robust image matching, joint limits and nonselfintersection constraints, and a new sampleandrefine search strategy guided by rescaled costfunction covariances. Monocular 3D body tracking is challenging: ..."
Abstract

Cited by 132 (3 self)
 Add to MetaCart
We present a method for recovering 3D human body motion from monocular video sequences using robust image matching, joint limits and nonselfintersection constraints, and a new sampleandrefine search strategy guided by rescaled costfunction 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 illconditioned as about 1/3 of the d.o.f. (the depthrelated ones) are almost unobservable in any given monocular image; and matching an imperfect, highly flexible, selfoccluding model to cluttered image features is intrinsically hard. To reduce correspondence ambiguities we use a carefully designed robust matchingcost metric that combines robust optical flow, edge energy, and motion boundaries. Even so, the ambiguity, nonlinearity and nonobservability make the parameterspace cost surface multimodal, unpredictable and illconditioned, so minimizing it is difficult. We discuss the limitations of CONDENSATIONlike samplers, and introduce a novel hybrid search algorithm that combines inflatedcovariancescaled sampling and continuous optimization subject to physical constraints. Experiments on some challenging monocular sequences show that robust cost modelling, joint and selfintersection constraints, and informed sampling are all essential for reliable monocular 3D body tracking.
Probabilistic Data Association Methods for Tracking Multiple and Compound Visual Objects
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2000
"... We describe a framework that explicitly reasons about data association to improve tracking performance in many difficult visual environments. A hierarchy of tracking strategies results from ascribing ambiguous or missing data to: (1) noiselike visual occurrences; (2) persistent, known scene element ..."
Abstract

Cited by 113 (2 self)
 Add to MetaCart
We describe a framework that explicitly reasons about data association to improve tracking performance in many difficult visual environments. A hierarchy of tracking strategies results from ascribing ambiguous or missing data to: (1) noiselike visual occurrences; (2) persistent, known scene elements (i.e. other tracked objects); or (3) persistent, unknown scene elements. First, we introduce a randomized tracking algorithm adapted from an existing probabilistic data association filter (PDAF) that is resistant to clutter and follows agile motion. The algorithm is applied to three different tracking modalities  homogeneous regions, textured regions, and snakes  and extensibly defined for straightforward inclusion of other methods. Second, we add the capacity to track multiple objects by adapting to vision a joint PDAF which oversees correspondence choices between samemodality trackers and image features. We then derive a related technique that allows mixed tracker modalities and handles object...
Learning Switching Linear Models of Human Motion
, 2000
"... The human figure exhibits complex and rich dynamic behavior that is both nonlinear and timevarying. Effective models of human dynamics can be learned from motion capture data using switching linear dynamic system (SLDS) models. We present results for human motion synthesis, classification, and v ..."
Abstract

Cited by 111 (1 self)
 Add to MetaCart
The human figure exhibits complex and rich dynamic behavior that is both nonlinear and timevarying. Effective models of human dynamics can be learned from motion capture data using switching linear dynamic system (SLDS) models. We present results for human motion synthesis, classification, and visual tracking using learned SLDS models. Since exact inference in SLDS is intractable, we present three approximate inference algorithms and compare their performance. In particular, a new variational inference algorithm is obtained by casting the SLDS model as a Dynamic Bayesian Network. Classification experiments show the superiority of SLDS over conventional HMM's for our problem domain. 1 Introduction The human figure exhibits complex and rich dynamic behavior. Dynamics are essential to the classification of human motion (e.g. gesture recognition) as well as to the synthesis of realistic figure motion for computer graphics. In visual tracking applications, dynamics can provide a p...
Guiding Model Search Using Segmentation
, 2005
"... ... paradigm can be used to improve the efficiency and accuracy of model search in an image. We operationalize this idea using an oversegmentation of an image into superpixels. The problem domain we explore is human body pose estimation from still images. The superpixels prove useful in two ways. F ..."
Abstract

Cited by 57 (0 self)
 Add to MetaCart
... paradigm can be used to improve the efficiency and accuracy of model search in an image. We operationalize this idea using an oversegmentation of an image into superpixels. The problem domain we explore is human body pose estimation from still images. The superpixels prove useful in two ways. First, we restrict the joint positions in our human body model to lie at centers of superpixels, which reduces the size of the model search space. In addition, accurate support masks for computing features on halflimbs of the body model are obtained by using agglomerations of superpixels as halflimb segments. We present results on a challenging dataset of people in sports news images.
Recovering 3D Human Body Configurations Using Shape Contexts
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2006
"... The problem we consider in this paper is to take a single twodimensional image containing a human figure, locate the joint positions, and use these to estimate the body configuration and pose in threedimensional space. The basic approach is to store a number of exemplar 2D views of the human body ..."
Abstract

Cited by 46 (2 self)
 Add to MetaCart
The problem we consider in this paper is to take a single twodimensional image containing a human figure, locate the joint positions, and use these to estimate the body configuration and pose in threedimensional space. The basic approach is to store a number of exemplar 2D views of the human body in a variety of different configurations and viewpoints with respect to the camera. On each of these stored views, the locations of the body joints (left elbow, right knee, etc.) are manually marked and labeled for future use. The input image is then matched to each stored view, using the technique of shape context matching in conjunction with a kinematic chainbased deformation model. Assuming that there is a stored view sufficiently similar in configuration and pose, the correspondence process will succeed. The locations of the body joints are then transferred from the exemplar view to the test shape. Given the 2D joint locations, the 3D body configuration and pose are then estimated using an existing algorithm. We can apply this technique to video by treating each frame independentlyâ€”tracking just becomes repeated recognition. We present results on a variety of data sets.