The dynamics of linear combinations: tracking 3D skeletons of human subjects
Image and Vision ComputingPublished 1 April 2002
Eng-Jon Ong, Shaogang Gong
Citations11
SJR quartileQ1
SJR score0.79
SNIP1.33
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 general framework for addressing three fundamental issues using linear combinations, the properties of the examples to linearly combine, the constraints, and the method for estimating the linear combinations coefficients for reconstructing an object based on noisy and incomplete visual observations is proposed.
Abstract
Abstract We propose a general framework for addressing three fundamental issues using linear combinations: (1) the properties of the examples to linearly combine, (2) the constraints, and (3) the method for estimating the linear combinations coefficients for reconstructing an object based on noisy and incomplete visual observations. To this end, we synthesise the necessary examples from known data using principal component analysis. Crucially, the dynamics of the object is dealt with by learning spatio-temporal constraints on the coefficients of the linear combinations. The CONDENSATION framework was adopted to estimate the coefficients for legitimate and plausible linear combinations. Finally, we apply the linear combinations framework to track 3D skeletons of human subjects using a hybrid representation.
Keywords
Computer Science
Choice Reviews OnlineNeural networks for pattern recognition
18,687 Citations1994
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Journal of Cognitive NeuroscienceEigenfaces for Recognition
13,775 Citations1991Matthew Turk, Alex Pentland
A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
Computer Vision and Image UnderstandingActive Shape Models-Their Training and Application
7,187 Citations1995T.F. Cootes, Chris Taylor +2 more
This work describes a method for building models by learning patterns of variability from a training set of correctly annotated images that can be used for image search in an iterative refinement algorithm analogous to that employed by Active Contour Models (Snakes).
International Journal of Computer VisionCONDENSATION—Conditional Density Propagation for Visual Tracking
4,885 Citations1998Michael Isard, Andrew Blake
The Condensation algorithm uses “factored sampling”, previously applied to the interpretation of static images, in which the probability distribution of possible interpretations is represented by a randomly generated set.
Image Processing, Analysis and Machine Vision
3,719 Citations1993Milan Sonka, Václav Hlaváč +1 more
The digitized image and its properties are studied, including shape representation and description, and linear discrete image transforms, and texture analysis.
IEEE Transactions on Pattern Analysis and Machine IntelligenceApplication of the Karhunen-Loeve procedure for the characterization of human faces
2,454 Citations1990Michael Kirby, L. Sirovich
The use of natural symmetries (mirror images) in a well-defined family of patterns (human faces) is discussed within the framework of the Karhunen-Loeve expansion, which results in an extension of the data and imposes even and odd symmetry on the eigenfunctions of the covariance matrix.
International Journal of Computer VisionEigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
1,032 Citations1998Michael J. Black, Allan D. Jepson
A “subspace constancy assumption” is defined that allows techniques for parameterized optical flow estimation to simultaneously solve for the view of an object and the affine transformation between the eigenspace and the image.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRecognition by linear combinations of models
817 Citations1991Shimon Ullman, Ronen Basri
An approach to visual object recognition in which a 3D object is represented by the linear combination of 2D images of the object is proposed and it is shown that for objects with sharp edges as well as with smooth bounding contours, the set of possible images of a given object is embedded in a linear space spanned by a small number of views.
Image and Vision ComputingModel-based vision: a program to see a walking person
458 Citations1983David Hogg
The computer program described here, the WALKER model, maps images into a description in which a person is represented by the series of hierarchical levels, i.e. a person has an arm which has a lower-armWhich has a hand.
IEEE Transactions on Pattern Analysis and Machine IntelligenceLinear object classes and image synthesis from a single example image
407 Citations1997Thomas Vetter, Tomaso Poggio
For linear object classes, it is shown that linear transformations can be learned exactly from a basis set of 2D prototypical views and preliminary evidence that the technique can effectively "rotate" high-resolution face images from a single 2D view is shown.
Image and Vision ComputingTracking colour objects using adaptive mixture models
313 Citations1999S.J. McKenna, Yogesh Raja +1 more
The use of adaptive Gaussian mixtures to model the colour distributions of objects is described to perform robust, real-time tracking under varying illumination, viewing geometry and camera parameters.
Lecture notes in computer scienceLearning flexible models from image sequences
255 Citations1994Adam Baumberg, David Hogg
An extended model is described which incorporates direction of motion, allowing the extrapolation of direction from shape, and a method is described for generating a similar flexible shape model automatically from real image data.
International Journal of Computer VisionAutomatic extraction of deformable part models
232 Citations1990Alex Pentland
A system that first segments an image into parts, and then fits deformable models to range data associated with the image, which significantly improves the computational complexity of both model recovery and subsequent processing.
Improving Specificity in PDMs using a Hierarchical Approach.
57 Citations1997T. Heap, David Hogg
A piecewise linear method for applying constraints within model shape space whereby principal component analysis is used on training data clusters in shape space to generate lower dimensional overlapping subspaces thus improving the speci city of the model.
An automatic system for model-based coding of faces
49 Citations2002B. Moghaddam, Alex Pentland
A fully automatic system for 2D model-based image coding of human faces for potential applications such as video telephony, database image compression, and face recognition that has been successfully tested on a database of nearly 2000 facial photographs.
Visual analysis of high DOF articulated objects with application to hand tracking
42 Citations1995James M. Rehg
This thesis addresses noninvasive real-time 3D tracking of human motion using sequences of ordinary video images and illustrates the effectiveness of explicit kinematic models in constraining the interpretation of hand intensity images and analyzing self-occluding motion.
Reconstructing 3D Pose and Motion from a Single Camera View
40 Citations1998Richard Bowden, T. A. Mitchell +1 more
A model based approach to human body tracking is presented in which the 2D silhouette of a moving human and the corresponding 3D skeletal structure are encapsulated within a non-linear Point Distribution Model.
Research Explorer (The University of Manchester)A mixture model for representing shape variation
32 Citations1997T.F. Cootes, Chris Taylor
Bayesian Modality Fusion for Tracking Multiple People with a Multi-Camera System
30 Citations2002Ting-Hsun Chang, Shaogang Gong
A multi-camera system based on Bayesian modality fusion to track multiple people in an indoor environment that can maintain people’s identities by using multiple cameras cooperatively is presented.
Image and Vision ComputingVery low bit rate face video compression using linear combination of 2D face views and principal components analysis
27 Citations1999Ioannis Koufakis, Bernard F. Buxton
An image synthesis technique for very low bit rate encoding of faces for videoconferencing applications over the Internet or mobile communication networks and results in a very compact representation of the face video data.
3D Deformable Hand Models
20 Citations1997T. Heap, David Hogg
This work presents a method for capturing landmark data which makes use of standard physically-based models, and demonstrates how the technique can be used to build a 3D Point Distribution Model from 3D MRI data, using a Simplex Mesh.
White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York)Learning deformable shape models for object tracking
5 Citations1997Anthony James Heap
Learning object shape dynamics are combined with stochastic tracking to produce a system which can track from automatically-generated models, as well as being able to handle discontinuous shape changes, in the domain of hand tracking.