Wearable wireless devices and ubiquitous computing are expected to grow significantly in the upcoming years. Standard inputs such as a mouse and keyboard are not well suited for these more on-The-go style systems. Gestures are seen as an effective alternative to these classical input styles. In this paper we examine two recognition gesture algorithms that use an inertial sensor worn on the forearm. The recognition algorithms use the sensor's quaternion orientation in either a Hidden Markov Model or Markov Chain based approach. A set of six gestures were selected to fit within the context of the active game. Despite the fact that the Hidden Markov Model is one of the most commonly used methods for gesture recognition, our results found that the Markov Chain algorithm outperformed the Hidden Markov Model. The Markov Chain algorithm obtained an average accuracy of 95%, while also having a faster computation time, making it better suited for real time applications.

Additional Metadata
Keywords Active Gaming, gesture recognition, Hidden Markov Model, Markov Chain, Wearable computing, Worn Sensors
Persistent URL dx.doi.org/10.1109/GEM.2014.7048108
Conference 6th IEEE Consumer Electronics Society Games, Entertainment, and Media, IEEE GEM 2014
Citation
Arsenault, D.L. (Dennis L.), & Whitehead, A. (2015). Quaternion based gesture recognition using worn inertial sensors in a motion tracking system. Presented at the 6th IEEE Consumer Electronics Society Games, Entertainment, and Media, IEEE GEM 2014. doi:10.1109/GEM.2014.7048108