DMCA
Canonical Time Warping for Alignment of Human Behavior
Cached
Download Links
| Citations: | 15 - 0 self |
BibTeX
@MISC{Zhou_canonicaltime,
author = {Feng Zhou and Fernando De La Torre},
title = {Canonical Time Warping for Alignment of Human Behavior},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Alignment of time series is an important problem to solve in many scientific disciplines. In particular, temporal alignment of two or more subjects performing similar activities is a challenging problem due to the large temporal scale difference between human actions as well as the inter/intra subject variability. In this paper we present canonical time warping (CTW), an extension of canonical correlation analysis (CCA) for spatio-temporal alignment of human motion between two subjects. CTW extends previous work on CCA in two ways: (i) it combines CCA with dynamic time warping (DTW), and (ii) it extends CCA by allowing local spatial deformations. We show CTW’s effectiveness in three experiments: alignment of synthetic data, alignment of motion capture data of two subjects performing similar actions, and alignment of similar facial expressions made by two people. Our results demonstrate that CTW provides both visually and qualitatively better alignment than state-of-the-art techniques based on DTW. 1
Keyphrases
human behavior canonical time warping present canonical time challenging problem similar action human motion large temporal scale difference state-of-the-art technique canonical correlation analysis temporal alignment similar facial expression ctw effectiveness important problem dynamic time previous work synthetic data motion capture data time series human action local spatial deformation inter intra subject variability many scientific discipline spatio-temporal alignment similar activity
