Kinematic jump processes for monocular 3D human tracking
Published 21 November 2003Open access
Cristian Sminchisescu, Bill Triggs
Citations270
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
This work uses simple kinematic reasoning to enumerate the tree of possible forwards/backwards flips, thus greatly speeding the search within each linked group of minima in the model-image matching cost function.
Abstract
International audience
Keywords
Computer Science
Practical Methods of Optimization
6,403 Citations2000R. Ian Fletcher
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.
Articulated body motion capture by annealed particle filtering
860 Citations2002J. Deutscher, A. Blake +1 more
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.
Global and local deformations of solid primitives
728 Citations1984Alan H. Barr
3-D model-based tracking of humans in action: a multi-view approach
702 Citations1996Dariu M. Gavrila, L.S. Davis
A vision system for the 3-D model-based tracking of unconstrained human movement and initial tracking results from a large new Humans-in-Action database containing more than 2500 frames in each of four orthogonal views are presented.
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.
Graphical ModelsReal-Time Inverse Kinematics Techniques for Anthropomorphic Limbs
581 Citations2000Deepak Tolani, Ambarish Goswami +1 more
A combination of analytical and numerical methods to solve generalized inverse kinematics problems including position, orientation, and aiming constraints suitable for an anthropomorphic arm or leg.
ACM SIGGRAPH Computer GraphicsGlobal and local deformations of solid primitives
473 Citations1984Alan H. Barr
Lecture notes in computer sciencePartitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking
463 Citations2000John MacCormick, Michael Isard
This paper describes how to use partitioned sampling on articulated objects, obtaining results that would be impossible with standard sampling methods.
Medical Entomology and ZoologyRobot Control: The Task Function Approach
441 Citations1991Claude Samson, Bernard Espiau +1 more
Lecture notes in computer scienceImplicit Probabilistic Models of Human Motion for Synthesis and Tracking
316 Citations2002Hedvig Sidenbladh, Michael J. Black +1 more
A low dimensional linear model of human motion is learned that is used to structure the example motion database into a binary tree and an approximate probabilistic tree search method exploits the coefficients of this low-dimensional representation and runs in sub-linear time.
Covariance scaled sampling for monocular 3D body tracking
293 Citations2005Cristian Sminchisescu, Bill Triggs
Experiments on some challenging monocular sequences show that robust cost modelling, joint and self-intersection constraints, and informed sampling are all essential for reliable monocular 3D body tracking.
Computer Vision and Image UnderstandingReconstruction of Articulated Objects from Point Correspondences in a Single Uncalibrated Image
240 Citations2000Camillo J. Taylor
Computer Vision Graphics and Image ProcessingDetermination of 3D human body postures from a single view
202 Citations1985Hsi-Jian Lee, Zen Chen
A method is proposed to recover and interpret the 3D body structures of a person from a single view, provided that at least six feature points on the head and a set of body joints are available on the image plane, and the geometry of head and lengths of body segments formed by joints are known.
People tracking using hybrid Monte Carlo filtering
177 Citations2002Kiam Choo, David J. Fleet
This work describes a filter that uses hybrid Monte Carlo (HMC) to obtain samples in high dimensional spaces and finds that the HMC filter is several thousand times faster than a conventional particle filter on a 28 D people tracking problem.
Reconstruction of articulated objects from point correspondences in a single uncalibrated image
156 Citations2002Catherine Taylor
This paper investigates the problem of recovering information about the configuration of an articulated object, such as a human figure, from point correspondences in a single-image by considering the foreshortening of the segments of the model in the image.
Lecture notes in computer scienceHyperdynamics Importance Sampling
48 Citations2002Cristian Sminchisescu, Bill Triggs
This work presents a general strategy for reducing MCMC trapping that generalizes Voter's 'hyperdynamic sampling' from computational chemistry, and constructs an adaptive importance sampler that focuses samples on low cost negative curvature regions likely to contain 'transition states'.
Lecture notes in computer scienceBuilding Roadmaps of Local Minima of Visual Models
32 Citations2002Cristian Sminchisescu, Bill Triggs
Two families of methods for locating transition states and minima are presented, originally derived in chemistry but here generalized, clarified and adapted to the needs of model based vision: eigenvector tracking is a modified form of damped Newton minimization, while hypersurface sweeping sweeps a moving hypersurfaces through the space, tracking minima within it.
Consistency and coupling in human model likelihoods
27 Citations2003Cristian Sminchisescu
This paper introduces an entirely continuous formulation which enforces consistency by means of an attraction/explanation pair for silhouettes and contours in model-based contexts and addresses the search window vs. noise level dilemma.