Name
Abstract | ||
|---|---|---|
In this paper, we consider how low cost wearable sensors may be used to enhance mobile interactions with learning and games multimedia. Unlike camera and single accelerometer based systems, the sensors developed provide measurements for all of the user's limb movements and this data can then be used to recognize what the user is doing anytime anywhere. The movements may then drive a game or may be used in an educative or artistic experience. The aim here is to report on work done using the Hidden Markov Model method for gesture recognition applied as a component within an exemplary Tai Chi training system. The intention is to demonstrate a practical result which could form the basis for other researchers involved in future mobile applications such as dance training, martial arts and sports. We also look at an extension of this work in the field of interactive dance multimedia. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1145/1821748.1821760 | MoMM |
Keywords | Field | DocType |
hidden markov model method,multimedia application,exemplary tai chi training,future mobile application,games multimedia,dance training,interactive dance multimedia,enhanced motion interaction,artistic experience,limb movement,gesture recognition,mobile interaction,martial art,motion capture,wearables,hidden markov model | Motion capture,Dance,Accelerometer,Training system,Wearable computer,Computer science,Gesture recognition,Martial arts,Hidden Markov model,Multimedia | Conference |
Citations | PageRank | References |
3 | 0.44 | 5 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dennis Majoe | 1 | 68 | 10.20 |
| Lars Widmer | 2 | 16 | 3.05 |
| Juerg Gutknecht | 3 | 5 | 0.93 |