Retrieving and exploring ontology-based human motion sequences

Abstract

A framework for semantic annotation of human motion sequences is proposed in this paper. Motion capture technology is widely used for manufacturing animation but it has a significant weakness due to the lack of an industry wide standard for archiving and retrieving motion capture data. It is difficult for animators to retrieve the desired motion sequences from motion capture files as there is no semantic annotation on already captured motion data. Our goal is to improve the reusability of motion capture data. To archive our goal first, we propose a standard format for integrating different motion capture file formats. Second, we define motion ontologies that are used to annotate and semantically organize human motion sequences. This ontology-based approach provides the means for discovering and exploiting the information and knowledge surrounding motion capture data. © Springer-Verlag Berlin Heidelberg 2005.