Multi-view gait recognition using a doubly-kernel approach on the Grassmann manifold

Tee Connie, Kah Ong Michael Goh, Beng Jin Teoh

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

View variation is one of the greatest challenges faced by the gait recognition research community. Recently, there are studies that model sets of gait features from multiple views as linear subspaces, which are known to form a special manifold called the Grassmann manifold. Conjecturing that modeling via linear subspace representation is not completely sufficient for gait recognition across view change, we take a step forward to consider non-linear subspace representation. A collection of multi-view gait features encapsulated in the form of a linear subspace is projected to the non-linear subspace through the expansion coefficients induced by kernel principal component analysis. Since subspace representation is inherently non-Euclidean, naïve vectorization as input to the vector-based pattern analysis machines is expected to yield suboptimal accuracy performance. We deal with this difficulty by embedding the manifold in a Reproducing Kernel Hilbert Space (RKHS) through a positive definite kernel function defined on the Grassmann manifold. A closer examination reveals that the proposed approach can actually be interpreted as a doubly-kernel method. To be specific, the first kernel maps the linear subspace representation non-linearly to a feature space; while the second kernel permits the application of kernelization-enabled machines established for vector-based data on the manifold-valued multi-view gait features. Experiments on the CASIA gait database shows that the proposed doubly-kernel method is effective against view change in gait recognition.

Original languageEnglish
Pages (from-to)534-542
Number of pages9
JournalNeurocomputing
Volume216
DOIs
Publication statusPublished - 2016 Dec 5

Fingerprint

Gait
Hilbert spaces
Principal component analysis
Experiments
Principal Component Analysis
Databases
Research

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this

@article{d341f034e2d94c01b65fa09734c22267,
title = "Multi-view gait recognition using a doubly-kernel approach on the Grassmann manifold",
abstract = "View variation is one of the greatest challenges faced by the gait recognition research community. Recently, there are studies that model sets of gait features from multiple views as linear subspaces, which are known to form a special manifold called the Grassmann manifold. Conjecturing that modeling via linear subspace representation is not completely sufficient for gait recognition across view change, we take a step forward to consider non-linear subspace representation. A collection of multi-view gait features encapsulated in the form of a linear subspace is projected to the non-linear subspace through the expansion coefficients induced by kernel principal component analysis. Since subspace representation is inherently non-Euclidean, na{\"i}ve vectorization as input to the vector-based pattern analysis machines is expected to yield suboptimal accuracy performance. We deal with this difficulty by embedding the manifold in a Reproducing Kernel Hilbert Space (RKHS) through a positive definite kernel function defined on the Grassmann manifold. A closer examination reveals that the proposed approach can actually be interpreted as a doubly-kernel method. To be specific, the first kernel maps the linear subspace representation non-linearly to a feature space; while the second kernel permits the application of kernelization-enabled machines established for vector-based data on the manifold-valued multi-view gait features. Experiments on the CASIA gait database shows that the proposed doubly-kernel method is effective against view change in gait recognition.",
author = "Tee Connie and Goh, {Kah Ong Michael} and Teoh, {Beng Jin}",
year = "2016",
month = "12",
day = "5",
doi = "10.1016/j.neucom.2016.08.002",
language = "English",
volume = "216",
pages = "534--542",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

Multi-view gait recognition using a doubly-kernel approach on the Grassmann manifold. / Connie, Tee; Goh, Kah Ong Michael; Teoh, Beng Jin.

In: Neurocomputing, Vol. 216, 05.12.2016, p. 534-542.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multi-view gait recognition using a doubly-kernel approach on the Grassmann manifold

AU - Connie, Tee

AU - Goh, Kah Ong Michael

AU - Teoh, Beng Jin

PY - 2016/12/5

Y1 - 2016/12/5

N2 - View variation is one of the greatest challenges faced by the gait recognition research community. Recently, there are studies that model sets of gait features from multiple views as linear subspaces, which are known to form a special manifold called the Grassmann manifold. Conjecturing that modeling via linear subspace representation is not completely sufficient for gait recognition across view change, we take a step forward to consider non-linear subspace representation. A collection of multi-view gait features encapsulated in the form of a linear subspace is projected to the non-linear subspace through the expansion coefficients induced by kernel principal component analysis. Since subspace representation is inherently non-Euclidean, naïve vectorization as input to the vector-based pattern analysis machines is expected to yield suboptimal accuracy performance. We deal with this difficulty by embedding the manifold in a Reproducing Kernel Hilbert Space (RKHS) through a positive definite kernel function defined on the Grassmann manifold. A closer examination reveals that the proposed approach can actually be interpreted as a doubly-kernel method. To be specific, the first kernel maps the linear subspace representation non-linearly to a feature space; while the second kernel permits the application of kernelization-enabled machines established for vector-based data on the manifold-valued multi-view gait features. Experiments on the CASIA gait database shows that the proposed doubly-kernel method is effective against view change in gait recognition.

AB - View variation is one of the greatest challenges faced by the gait recognition research community. Recently, there are studies that model sets of gait features from multiple views as linear subspaces, which are known to form a special manifold called the Grassmann manifold. Conjecturing that modeling via linear subspace representation is not completely sufficient for gait recognition across view change, we take a step forward to consider non-linear subspace representation. A collection of multi-view gait features encapsulated in the form of a linear subspace is projected to the non-linear subspace through the expansion coefficients induced by kernel principal component analysis. Since subspace representation is inherently non-Euclidean, naïve vectorization as input to the vector-based pattern analysis machines is expected to yield suboptimal accuracy performance. We deal with this difficulty by embedding the manifold in a Reproducing Kernel Hilbert Space (RKHS) through a positive definite kernel function defined on the Grassmann manifold. A closer examination reveals that the proposed approach can actually be interpreted as a doubly-kernel method. To be specific, the first kernel maps the linear subspace representation non-linearly to a feature space; while the second kernel permits the application of kernelization-enabled machines established for vector-based data on the manifold-valued multi-view gait features. Experiments on the CASIA gait database shows that the proposed doubly-kernel method is effective against view change in gait recognition.

UR - http://www.scopus.com/inward/record.url?scp=84994157799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994157799&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2016.08.002

DO - 10.1016/j.neucom.2016.08.002

M3 - Article

AN - SCOPUS:84994157799

VL - 216

SP - 534

EP - 542

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -