Transactions of the Japanese Society for Artificial Intelligence
Online ISSN : 1346-8030
Print ISSN : 1346-0714
ISSN-L : 1346-0714
Technical Papers
Time-Series Human Motion Analysis with Kernels Derived from Learned Switching Linear Dynamics
Taketoshi MoriMasamichi ShimosakaTatsuya HaradaTomomasa Sato
Author information
JOURNAL FREE ACCESS

2005 Volume 20 Issue 3 Pages 197-208

Details
Abstract
In this paper, we propose a novel kernel computation algorithm between time-series human motion data for online action recognition. The proposed kernel is based on probabilistic models called switching linear dynamics (SLDs). SLD is one of the powerful tools for tracking, analyzing and classifying human complex time-series motion. The proposed kernel incorporates information about the latent variables in SLDs. The empirical evaluation using real motion data shows that a classifier using SVM with our proposed kernel has much better performance than the classifiers with some conventional kernel techniques. Another experimental result using kernel principal component analysis shows that the proposed kernel has excellent performance in extracting and separating different action categories, such as walking and running.
Content from these authors
© 2005 JSAI (The Japanese Society for Artificial Intelligence)
Previous article Next article
feedback
Top