Human motion signatures: analysis, synthesis, recognition

Vasilescu, M. Alex O.

doi:10.1109/icpr.2002.1047975

Cited by 102 publications

(83 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Matrix unfolding operation: Given an r-order tensor A with dimensions N 1 ×N 2 ×· · ·× N r , the mode-n matrix unfolding, denoted by unf olding(A, n), is flattening A into a matrix whose column vectors are the mode-n vectors [14,27]. Therefore, the dimension of the unfolded matrix…”

Section: Appendixmentioning

confidence: 99%

“…Higher-order singular value decomposition (HOSVD) is a generalization of SVD for multilinear model analysis by [14,27,28]. Multilinear model is a generalization of linear model (one-factor models) and bilinear model (two-factor models) [25] into higher-order tensor decomposition (multi-factor models).…”

Section: Multilinear Model For Gait Analysismentioning

confidence: 99%

“…In the recognition phase, a new walking of unknown person in unknown view is aligned to the learned model and then iterative procedure is used to solve for both the gait-style and the view. Related work in using mulitlinear analysis for gait includes [27] One important feature of the proposed framework is it's scalability to include new people. Given a learned model we can add a new person to the model even if only single view is available for that person, i.e., one cycle gait sequence from one of the multiple possible views is need to include new people to the database.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards Scalable View-Invariant Gait Recognition: Multilinear Analysis for Gait

Lee

Elgammal

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper we introduce a novel approach for learning view-invariant gait representation that does not require synthesizing particular views or any camera calibration. Given walking sequences captured from multiple views for multiple people, we fit a multilinear generative model using higher-order singular value decomposition which decomposes view factors, body configuration factors, and gait-style factors. Gait-style is a view-invariant, time-invariant, and speedinvariant gait signature that can then be used in recognition. In the recognition phase, a new walking cycle of unknown person in unknown view is automatically aligned to the learned model and then iterative procedure is used to solve for both the gait-style parameter and the view. The proposed framework allows for scalability to add a new person to already learned model even if a single cycle of a single view is available.

show abstract

Section: Appendixmentioning

confidence: 99%

Section: Multilinear Model For Gait Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards Scalable View-Invariant Gait Recognition: Multilinear Analysis for Gait

Lee

Elgammal

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In [12], multilinear tensor analysis was used to decompose face images into orthogonal factors controlling the appearance of the face including geometry (people), expressions, head pose, and illumination using High Order Singular Value Decomposition (HOSVD) [15]. Tensor representation of image data was used in [16] for video compression, and in [17] for motion analysis and synthesis. N-mode analysis of higher-order tensors was originally proposed and developed in [13,18,19] and others.…”

Section: Factorized Models: Linear Bilinear and Multi-linear Modelsmentioning

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

“…Singular value decomposition (SVD) can be used for PCA analysis and iterative SVD with vector transpose for bilinear analysis. Higher-order tensor analysis can be achieved by higher-order sigular value decomposition (HOSVD) with unfolding, which is a generalization of SVD [22,23,27].…”

Section: Decompositionmentioning

confidence: 99%