| Volume 27 Issue 7 - Publication Date: 1 July 2008 |
| |
| Incremental Learning, Clustering and Hierarchy Formation of Whole Body
Motion Patterns using Adaptive Hidden Markov Chains |
| |
| D. Kulic, W. Takano, and Y. Nakamura
Department of Mechano-Informatics, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan |
| |
| This paper describes a novel approach for autonomous and incremental
learning of motion pattern primitives by observation of human
motion. Human motion patterns are abstracted into a dynamic stochastic
model, which can be used for both subsequent motion recognition
and generation, analogous to the mirror neuron hypothesis in
primates. The model size is adaptable based on the discrimination
requirements in the associated region of the current knowledge base.
A new algorithm for sequentially training the Markov chains is developed,
to reduce the computation cost during model adaptation. As
new motion patterns are observed, they are incrementally grouped
together using hierarchical agglomerative clustering based on their
relative distance in the model space. The clustering algorithm forms
a tree structure, with specialized motions at the tree leaves, and generalized
motions closer to the root. The generated tree structure will
depend on the type of training data provided, so that the most specialized
motions will be those for which the most training has been
received. Tests with motion capture data for a variety of motion primitives
demonstrate the efficacy of the algorithm. |
| |
| Multimedia Key |
= Video |
 = Data |
= Code |
= Image |
|
| |
|
Extension |
Type |
Description |
|
1 |
|
Example
1: Video of animations of sample motions
from the database and motions generated
by the sequentially trained FHMM models. 21.8MB (wmv) |
|
2 |
|
Example
2: Zip file containing the test data used in the
experiments. Authors: Hiroaki Tanie, Koji
Tatani and Yoshihiko Nakaniura. Please
see the file readme.txt in the zip file for a
description of the file contents and format |
|
| |
| Return
to Contents |
