PROJECT TITLE :

The Variable Markov Oracle: Algorithms for Human Gesture Applications

ABSTRACT:

This text introduces the Variable Markov Oracle (VMO) data structure for multivariate time series indexing. VMO will identify repetitive fragments and find sequential similarities between observations. VMO will conjointly be viewed as a combination of online Clustering algorithms with variable-order Markov constraints. The authors use VMO for gesture question-by-content and gesture following. A probabilistic interpretation of the VMO query-matching algorithm is proposed to find an analogy to the inference downside during a hidden Markov model (HMM). This probabilistic interpretation extends VMO to be not only a data structure however conjointly a model for time series. Question-by-content experiments were conducted on a gesture database that was recorded employing a Kinect 3D camera, showing state-of-the-art performance. The question-by-content experiments' results are compared to previous works using HMM and dynamic time warping. Gesture following is described within the context of an interactive dance atmosphere that aims to integrate human movements with computer-generated graphics to create an augmented reality performance.