Background/Objectives: Human movements in dance are difficult to train without taking an actual class. In this paper, an interactive system of dance guidance is proposed to teach dance motions using examples.Methods/Statistical analysis: In the proposed system, a set of example motions are captured from experts through a method of marker-free motion capture, which consists of multiple Kinect cameras. The captured motions are calibrated and optimally reconstructed into a motion database. For the efficient exchange of motion data between a student and an instructor, a posture-based motion search and multi-mode views are provided for online lessons.Findings: To capture accurate example motions, the proposed system solves the joint occlusion problem by using multiple Kinect cameras. An iterative closest point (ICP) method is used to unify the multiple camera data into the same coordinate system, which generates an output motion in real time. Comparing to a commercial system, our system can capture various dance motions over an average of 85% accuracy, as shown in the experimental results. Using the touch screen devices, a student can browse a desired motion from the database to start a dance practice and send own motion to an instructor for feedback. By conducting online dance lessons such as ballet, K-pop, and traditional Korean, our experimental results show that the participating students can train their dance skills over a given period.Improvements/Applications: Our system is applicable to any student who wants to learn dance motions without taking an actual class andto receive online feedback from a distant instructor.
Dance motion capture and composition using multiple RGB and depth sensors
