Human motion signatures: analysis, synthesis, recognition

25 June 2003

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

Vol. 3 (10514651) , 456-460
https://doi.org/10.1109/icpr.2002.1047975

Abstract

Human motion is the composite consequence of multiple elements, including the action performed and a motion signature that captures the distinctive pattern of movement of a particular individual. We develop an algorithm that is capable of extracting these motion elements and recombining them in novel ways. The algorithm analyzes motion data spanning multiple subjects performing different actions. The analysis yields a generative motion model that can synthesize new motions in the distinctive styles of these individuals. Our algorithms can also recognize people and actions from new motions by comparing motion signatures and action parameters.

Keywords

This publication has 10 references indexed in Scilit:

Multilinear image analysis for facial recognition
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
Multilinear Analysis of Image Ensembles: TensorFaces
Published by Springer Nature ,2002
Orthogonal Tensor Decompositions
SIAM Journal on Matrix Analysis and Applications, 2001
Separating Style and Content with Bilinear Models
Neural Computation, 2000
Style machines
Published by Association for Computing Machinery (ACM) ,2000
A Multilinear Singular Value Decomposition
SIAM Journal on Matrix Analysis and Applications, 2000
On the Best Rank-1 and Rank-(R₁ ,R₂ ,. . .,R_N) Approximation of Higher-Order Tensors
SIAM Journal on Matrix Analysis and Applications, 2000
NeuroAnimator
Published by Association for Computing Machinery (ACM) ,1998
An Approach to n-Mode Components Analysis
Psychometrika, 1986
Some mathematical notes on three-mode factor analysis
Psychometrika, 1966