Posture recognition plays an important role in three-dimensional virtual experiments, it means that to complete its specific function by a particular posture to control program in responding an action. In order to easy use and making the posture recognition more accurate, this article proposed the use of Kinect sensor to get articulation point information, through its the Euclidean distance and angle of the articular point to distinguish a particular posture. The results show that this method can get higher recognition rate, and expand action library at any time to meet the decision requirements of different postures. Its helpful to reuse software and improve the efficiency in the use of virtual experiment.
No takes yet. Share an insight, caveat, or question.
Xie et al. (2014) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: