Representing cyclic human motion using functional analysis

Ormoneit, Dirk; Black, Michael J.; Hastie, Trevor; Kjellström, Hedvig

doi:10.1016/j.imavis.2005.09.004

Cited by 63 publications

(42 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last few years, there has been increasing interest in exploiting this fact through using intermediate activity-based manifold representations [4,[31][32][33][34][35][36][37][38]. For example in [4], the visual manifold of human silhouette deformations, due to motion, has been learned explicitly and used for recovering the 3D body configuration from silhouettes in a closed-form.…”

Section: Manifold-based Models Of Human Motionmentioning

confidence: 99%

Homeomorphic Manifold Analysis (HMA): Generalized separation of style and content on manifolds

Elgammal

Lee

2013

Image and Vision Computing

View full text Add to dashboard Cite

The problem of separation of style and content is an essential element of visual perception, and is a fundamental mystery of perception. This problem appears extensively in different computer vision applications. The problem we address in this paper is the separation of style and content when the content lies on a low dimensional nonlinear manifold representing a dynamic object. We show that such a setting appears in many human motion analysis problems. We introduce a framework for learning parameterization of style and content in such settings. Given a set of topologically equivalent manifolds, the Homeomorphic Manifold Analysis (HMA) framework models the variation in their geometries in the space of functions that maps between a topologically-equivalent common representation and each of them. The framework is based on decomposing the style parameters in the space of nonlinear functions that map between a unified embedded representation of the content manifold and style-dependent visual observations. We show the application of the framework in synthesis, recognition, and tracking of certain human motions that follow this setting, such as gait and facial expressions.

show abstract

Section: Manifold-based Models Of Human Motionmentioning

confidence: 99%

Homeomorphic Manifold Analysis (HMA): Generalized separation of style and content on manifolds

Elgammal

Lee

2013

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…-An automated method for modelling cyclic 3D motion [19]. This work developed an algorithm enforcing smooth transitions between cycles by operating in the Fourier domain.…”

Section: Human Animationmentioning

confidence: 99%

Cyclic animation using partial differential equations

2010

View full text Add to dashboard Cite

This work presents an efficient and fast method for achieving cyclic animation using Partial Differential Equations (PDEs). The boundary-value nature associated with elliptic PDEs offers a fast analytic solution technique for setting up a framework for this type of animation. The surface of a given character is thus created from a set of pre-determined curves, which are used as boundary conditions so that a number of PDEs can be solved. Two different approaches to cyclic animation are presented here. The first consists of using attaching the set of curves to a skeletal system holding the animation for cyclic motions linked to a set mathematical expressions, the second one exploits the spine associated with the analytic solution of the PDE as a driving mechanism to achieve cyclic animation, which is also manipulated mathematically. The first of these approaches is implemented within a framework related to cyclic motions inherent to human-like characters, whereas the spine-based approach is focused on modelling the undulatory movement observed in fish when swimming. The proposed method is fast and accurate. Additionally, the animation can be either used in the PDE-based surface representation of the model or transferred to the original mesh model by means of a point to point map. Thus, the user is offered with the choice of using either of these two animation representations of the same object, the selection depends on the computing resources such as storage and memory capacity associated with each particular application.

show abstract

“…We avoid the use of sophisticated activity-specific prior models (e.g., [18,30]) that are prone to over-fitting, thereby biasing pose estimates and masking useful information. Following [23,28,31,33] our motion features are derived from a low-dimensional representation of joint trajectories in a body-centric coordinate frame. We then use a regularized form of logistic regression for classification.…”

Section: Introductionmentioning

confidence: 99%