This paper presents a linguistically motivated approach for dance gesture performance evaluation using skeleton tracking to robustly classify arbitrary dance gesture into one of predefined gesture classes and provide performance score in regards to the dance master's gesture. The gesture classes were a set of dance gesture. The gesture classes were a set of dance gesture elements that represent common gestures of bali traditional dance. In this approach, a gesture was represented as a set of skeleton features descriptors with the input data captured using kinect depth sensor. Gramatical rules was inferred from the training examples to capture the structure of the gesture motion using grammar inference method. The empiric results showed that dance gesture model based on ALERGIA and Reguler positive and Negative Inference (RPNT) achieved promising results.
|
|