Motion analysis for folk dance evaluation

Abstract

Motion capture techniques are becoming a popular method for digitizing folk dances for preservation and dissemination. Although technically the captured data can be of very high quality, folk dancing, in contrast to choreographed performances, allow for stylistic variations and improvisations that cannot be easily captured by the data themselves. The majority of motion analysis and comparison algorithms are explicitly based on quantitative metrics and thus do not usually provide any insight on style qualities of a performance. In this work, we introduce a motion analysis and comparison framework that is based on Laban Movement Analysis (LMA); these algorithms are particularly useful in the context of teaching folk dances. We present a prototype virtual reality simulator in which users can preview segments of folk dance performed by a 3D avatar and repeat them. The users' performances are captured and subsequently compared to the folk dance template motions. The system then provides intuitive feedback about their performance, which is based on the four LMA components (Body, Effort, Shape, Space) and provides both a quantitative and qualitative evaluation of the performance.