Results 1  10
of
41
Icondensation: Unifying lowlevel and highlevel tracking in a stochastic framework
, 1998
"... . Tracking research has diverged into two camps; lowlevel approaches which are typically fast and robust but provide little finescale information, and highlevel approaches which track complex deformations in highdimensional spaces but must trade off speed against robustness. Realtime highlevel ..."
Abstract

Cited by 311 (13 self)
 Add to MetaCart
(Show Context)
. Tracking research has diverged into two camps; lowlevel approaches which are typically fast and robust but provide little finescale information, and highlevel approaches which track complex deformations in highdimensional spaces but must trade off speed against robustness. Realtime highlevel systems perform poorly in clutter and initialisation for most highlevel systems is either performed manually or by a separate module. This paper presents a new technique to combine low and highlevel information in a consistent probabilistic framework, using the statistical technique of importance sampling combined with the Condensation algorithm. The general framework, which we term Icondensation, is described, and a hand tracker is demonstrated which combines colour blobtracking with a contour model. The resulting tracker is robust to rapid motion, heavy clutter and handcoloured distractors, and reinitialises automatically. The system runs comfortably in real time on an...
Estimating Articulated Human Motion With Covariance Scaled Sampling
 International Journal of Robotics Research
, 2003
"... We present a method for recovering 3D human body motion from monocular video sequences based on a robust image matching metric, incorporation of joint limits and nonselfintersection constraints, and a new sampleandrefine search strategy guided by rescaled costfunction covariances. Monocular 3D ..."
Abstract

Cited by 125 (10 self)
 Add to MetaCart
We present a method for recovering 3D human body motion from monocular video sequences based on a robust image matching metric, incorporation of joint limits and nonselfintersection constraints, and a new sampleandrefine search strategy guided by rescaled costfunction covariances. Monocular 3D body tracking is challenging: besides the difficulty of matching an imperfect, highly flexible, selfoccluding model to cluttered image features, realistic body models have at least 30 joint parameters subject to highly nonlinear physical constraints, and at least a third of these degrees of freedom are nearly unobservable in any given monocular image. For image matching we use a carefully designed robust cost metric combining robust optical flow, edge energy, and motion boundaries. The nonlinearities and matching ambiguities make the parameterspace cost surface multimodal, illconditioned and highly nonlinear, so searching it is difficult. We discuss the limitations of CONDENSATIONlike samplers, and describe a novel hybrid search algorithm that combines inflatedcovariancescaled sampling and robust continuous optimization subject to physical constraints and model priors. Our experiments on challenging monocular sequences show that robust cost modeling, joint and selfintersection constraints, and informed sampling are all essential for reliable monocular 3D motion estimation.
Learning and classification of complex dynamics
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2000
"... AbstractÐStandard, exact techniques based on likelihood maximization are available for learning AutoRegressive Process models of dynamical processes. The uncertainty of observations obtained from real sensors means that dynamics can be observed only approximately. Learning can still be achieved via ..."
Abstract

Cited by 88 (2 self)
 Add to MetaCart
AbstractÐStandard, exact techniques based on likelihood maximization are available for learning AutoRegressive Process models of dynamical processes. The uncertainty of observations obtained from real sensors means that dynamics can be observed only approximately. Learning can still be achieved via ªEMKºÐExpectationMaximization (EM) based on Kalman Filtering. This cannot handle more complex dynamics, however, involving multiple classes of motion. A problem arises also in the case of dynamical processes observed visually: background clutter arising for example, in camouflage, produces nonGaussian observation noise. Even with a single dynamical class, nonGaussian observations put the learning problem beyond the scope of EMK. For those cases, we show here how ªEMCºÐbased on the CONDENSATION algorithm which propagates random ªparticlesets,º can solve the learning problem. Here, learning in clutter is studied experimentally using visual observations of a hand moving over a desktop. The resulting learned dynamical model is shown to have considerable predictive value: When used as a prior for estimation of motion, the burden of computation in visual observation is significantly reduced. Multiclass dynamics are studied via visually observed juggling; plausible dynamical models have been found to emerge from the learning process, and accurate classification of motion has resulted. In practice, EMC learning is computationally burdensome and the paper concludes with some discussion of computational complexity. Index TermsÐComputer vision, learning dynamics, AutoRegressive Process, Expectation Maximization. 1
Visual Motion Analysis by Probabilistic Propagation of Conditional Density
, 1998
"... This thesis establishes a stochastic framework for tracking curves in visual clutter, using a Bayesian randomsampling algorithm. The approach is rooted in ideas from statistics, control theory and computer vision. The problem is to track outlines and features of foreground objects, modelled as curv ..."
Abstract

Cited by 36 (0 self)
 Add to MetaCart
This thesis establishes a stochastic framework for tracking curves in visual clutter, using a Bayesian randomsampling algorithm. The approach is rooted in ideas from statistics, control theory and computer vision. The problem is to track outlines and features of foreground objects, modelled as curves, as they move in substantial clutter, and to do it at, or close to, video framerate. The algorithm, named Condensation, for Conditional density propagation, has recently been derived independently by several researchers, and is generating signi cant interest in the statistics and signal processing communities. This thesis contributes to the literature on Condensationlike lters by presenting some novel applications of and extensions to the basic algorithm, and contributes to the visual motion estimation literature by demonstrating high tracking performance in cluttered environments. Despite its power the Condensation algorithm has a remarkably simple form and this allows the use of nonlinear motion models which combine characteristics of discrete Hidden Markov Models with the continuous AutoRegressive Process motion models traditionally used in Kalman lters. These mixed discretecontinuous models have promising applications to the emerging eld of perception of action. This thesis also implements two algorithms to smooth the output of the Condensation lter which improves the accuracy of motion estimation in a batchmode procedure after tracking is complete.
Statistical Models of Visual Shape and Motion
 A
, 1998
"... This paper addresses some problems in the interpretation of visually observed shapes in motion, both planar and threedimensional shapes. Mumford (1996), interpreting the "Pattern Theory" developed over a number of years by Grenander (1976), views images as "pure" patterns that h ..."
Abstract

Cited by 27 (0 self)
 Add to MetaCart
(Show Context)
This paper addresses some problems in the interpretation of visually observed shapes in motion, both planar and threedimensional shapes. Mumford (1996), interpreting the "Pattern Theory" developed over a number of years by Grenander (1976), views images as "pure" patterns that have been distorted by a combination of four kinds of degradations. This view applies naturally to the analysis of static, twodimensional images. The four degradations are given here, together with comments on how they need to be extended to take account of threedimensional objects in motion.
"Shape Activity": A Continuous State HMM for Moving/Deforming Shapes with Application to Abnormal Activity Detection
"... The aim is to model "activity" performed by a group of moving and interacting objects (which can be people or cars or different rigid components of the human body) and use the models for abnormal activity detection. Previous approaches to modeling group activity include cooccurrence stati ..."
Abstract

Cited by 24 (11 self)
 Add to MetaCart
(Show Context)
The aim is to model "activity" performed by a group of moving and interacting objects (which can be people or cars or different rigid components of the human body) and use the models for abnormal activity detection. Previous approaches to modeling group activity include cooccurrence statistics (individual and joint histograms) and Dynamic Bayesian Networks, neither of which is applicable when the number of interacting objects is large. We treat the objects as point objects (referred to as "landmarks") and propose to model their changing configuration as a moving and deforming "shape" (using Kendall's shape theory for discrete landmarks). A continuous state Hidden Markov Model (HMM) is defined for landmark shape dynamics in an activity. The configuration of landmarks at a given time forms the observation vector and the corresponding shape and the scaled Euclidean motion parameters form the hidden state vector. An abnormal activity is then defined as a change in the shape activity model, which could be slow or drastic and whose parameters are unknown. Results are shown on a real abnormal activity detection problem involving multiple moving objects.
Shape Activity”: a continuousstate HMM for moving/deforming shapes with application to abnormal activity detection
 IEEE Transactions on Image Processing
, 2005
"... Abstract—The aim is to model “activity ” performed by a group of moving and interacting objects (which can be people, cars, or different rigid components of the human body) and use the models for abnormal activity detection. Previous approaches to modeling group activity include cooccurrence statis ..."
Abstract

Cited by 23 (2 self)
 Add to MetaCart
(Show Context)
Abstract—The aim is to model “activity ” performed by a group of moving and interacting objects (which can be people, cars, or different rigid components of the human body) and use the models for abnormal activity detection. Previous approaches to modeling group activity include cooccurrence statistics (individual and joint histograms) and dynamic Bayesian networks, neither of which is applicable when the number of interacting objects is large. We treat the objects as point objects (referred to as “landmarks”) and propose to model their changing configuration as a moving and deforming “shape ” (using Kendall’s shape theory for discrete landmarks). A continuousstate hidden Markov model is defined for landmark shape dynamics in an activity. The configuration of landmarks at a given time forms the observation vector, and the corresponding shape and the scaled Euclidean motion parameters form the hiddenstate vector. An abnormal activity is then defined as a change in the shape activity model, which could be slow or drastic and whose parameters are unknown. Results are shown on a real abnormal activitydetection problem involving multiple moving objects. Index Terms—Abnormal acitivity detection, activity recognition, hidden Markov model (HMM), landmark shape dynamics, particle filtering, shape activity. I.
A Brief Overview of Hand Gestures Used in Wearable Human Computer Interfaces
, 2003
"... This technical report provides a brief overview of how human hand gestures can be used in wearable Human Computer Interfaces (HCI). ..."
Abstract

Cited by 14 (4 self)
 Add to MetaCart
(Show Context)
This technical report provides a brief overview of how human hand gestures can be used in wearable Human Computer Interfaces (HCI).
Recognition of dynamic hand gestures
, 2003
"... This paper is concerned with the problem ofrecogTy;Ik of dynamic handgndyIW#I We have consideredgonside which are sequences of distinct hand poses. In thesegeseyWM hand poses canunderg motion and discrete changte However, continuous deformations of the hand shapes are not permitted. We have deve ..."
Abstract

Cited by 8 (0 self)
 Add to MetaCart
This paper is concerned with the problem ofrecogTy;Ik of dynamic handgndyIW#I We have consideredgonside which are sequences of distinct hand poses. In thesegeseyWM hand poses canunderg motion and discrete changte However, continuous deformations of the hand shapes are not permitted. We have developed arecogy;IKH engog which canreliablyrecogqyg these geseyKT despite individual variations. TheengqW also has the abilityto detect start and end ofgyHW#I sequences in an automated fashion. The recogMzy;I strategy;IH a combination of static shaperecogzq##y (performedusing contour discriminant analysis), Kalman #lter based handtracking and a HMM based temporal characterization scheme. The system is fairlyrobust tobackgy;Iq clutter and uses skin color for static shaperecogMkMKy andtracking A real time implementation on standard hardware is developed. Experimental results establish the e#ectiveness of the approach.