3D Motion Recognition using HMM and Nearest Neighbor Method

Amin Safaei and Mehran Jahed


Stereo Vision, Motion Evaluation, HMM


Gesture and motion recognition are needed for a variety of applications. The use of human hand motions as a natural interface tool has motivated researchers to conduct research in the modeling, analysis and recognition of various hand movements. In this work, we introduce a 3-D hand motion recognition. We use 3-D landmarked points on finger tips and joints followed by a HMM (Hidden Markov Model) to recognize hand motions. Experimentally, in an effort to evaluate the formation of hand gestures similar to those used in rehabilitation sessions, we studied three hand motions. Using natural hand motion features in an uncontrolled environment, we were able to classify, differentiate and quantify various unnatural slow movements, ranging from 70 to 93%.

Important Links:

Go Back