Limb-based feature description of human motion

Authors

Kevin Adi Adistambha, University of WollongongFollow
Stephen J. Davis, University of WollongongFollow
Christian H. Ritz, University of WollongongFollow
David A. Stirling, University of WollongongFollow

RIS ID

52735

Publication Details

Adistambha, K., Davis, S. J., Ritz, C. H. & Stirling, D. A. (2011). Limb-based feature description of human motion. ICSPCS'2011: 5th International Conference on Signal Processing and Telecommunication Systems (pp. 1-6). New York: IEEE.

Abstract

This paper proposes a novel limb-based technique for semantic description of motion capture data. The goal is to create a motion segmentation and classification technique that is easily extensible by recognizing the actions of a limb instead of the whole body. This provides a highly detailed metadata that can be extended as needed to include additional motion classes by either adding a new limb submotion or by defining a new full-body motion class that combines existing known limb movements. The results of the initial implementation for annotating the leg movements (forward and backward) of walking and running show that such a system is feasible, with annotation accuracy of more than 98%.