Classification of phases in human motions by neural networks and hidden Markov models
Gespeichert in:
| Deutscher übersetzter Titel: | Klassifikation der Phasen menschlicher Bewegung mit Hilfe von neuronalen Netzwerken und Hidden Markov Modellen |
|---|---|
| Autor: | Boesnach, Ingo; Moldenhauer, Jörg; Burgmer, C.; Beth, T.; Wank, Veit; Bös, Klaus |
| Erschienen in: | 2004 IEEE Conference on Cybernetics and Intelligent Systems : 1 - 3 December 2004, Singapore |
| Veröffentlicht: | Piscataway (N.J.): 2004, S. 976-981, Lit. |
| Herausgeber: | Institute of Electrical and Electronics Engineers |
| Format: | Literatur (SPOLIT) |
| Publikationstyp: | Sammelwerksbeitrag |
| Medienart: | Elektronische Ressource (online) Gedruckte Ressource |
| Sprache: | Englisch |
| Schlagworte: | |
| Online Zugang: | |
| Erfassungsnummer: | PU201108007168 |
| Quelle: | BISp |
Abstract des Autors
A proper modeling of human motions plays a crucial rule for many motion processing tasks. In particular, models for the automatic classification of elementary motion phases are highly important for the interaction between man and machine. In this work, we present different approaches for this modeling task based on neural networks and hidden Markov models. Both approaches yield reliable classification results. We show that even simple instances of the models work well if proper motion features are determined. A comparison of the different approaches shows the reasons for this behavior and leads to essential consequences for further modeling approaches. Verf.-Referat