Hidden Markov models for speech recognition
Technometrics
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Vision-based human motion analysis: An overview
Computer Vision and Image Understanding
Gesture recognition with a Wii controller
Proceedings of the 2nd international conference on Tangible and embedded interaction
Learning and Inferences of the Bayesian Network with Maximum Likelihood Parameters
ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
Guest Editorial: State of the Art in Image- and Video-Based Human Pose and Motion Estimation
International Journal of Computer Vision
A survey on vision-based human action recognition
Image and Vision Computing
Advanced Data Mining Techniques
Advanced Data Mining Techniques
gRmobile: A Framework for Touch and Accelerometer Gesture Recognition for Mobile Games
SBGAMES '09 Proceedings of the 2009 VIII Brazilian Symposium on Games and Digital Entertainment
| Hi-index | 0.00 |
A majority of systems that take advantage of human motion in order to recognize gestures are developed through temporal image processing algorithms. However, thanks to the increasing development of acceleration sensors in recent years, it has become possible to use actual arm movements as an acquisition system. This feature could be used in more intuitive systems to communicate reach-to-grasp movements. This research proposes placing an accelerometer on a user's arm to recognize grasping movements in an unique way. The most complex part of this problem revolves around the fact that an accelerometer is unable to evaluate whether a user is performing an reach-to-grasp movement. Given that the movement involves a temporary action, it is possible to use a hidden Markov system to dynamically predict user grasping movements. The results indicate that the model can correctly predict all movements with an F-score = 99% on average.