Autonomous dance avatar for generating stylized dance motion from simple dance notations

To read the full-text of this research, you can request a copy directly from the authors.


When producing the animation of a body motion from the dance notation, the dance knowledge is a key for accomplishing high-quality movement. This knowledge enables the dancer to know how to perform the correct movement from a movement notation score. This paper presents an approach for automatically simulating a CG animation from Labanotation scores. We achieve this goal by the integration of a CG animation with a dance-style interpretation module which is called an autonomous dance avatar. In our experiment, we implemented an autonomous dance avatar to perform Japanese stylized traditional dance Noh plays. The result shows that the autonomous dance avatar can reproduce Noh play satisfactory from Labanotation after it has been trained with the style of Noh play.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... There are some works using dance notations and application software [3], [4]. By using them, one can simulate already captured or strictly described dance animation. ...
This paper reports an assessment of the feasibility and the practicality of a creation support system for contemporary dance e-learning. We developed a Body-part Motion Synthesis System (BMSS) that allows users to create choreographies by synthesizing body-part motions to increase the effect of learning contemporary dance choreography. Short created choreographies can be displayed as animation using 3DCG characters. The system targets students who are studying contemporary dance and is designed to promote the discovery learning of contemporary dance. We conducted a series of evaluation experiments for creating contemporary dance choreographies to verify the learning effectiveness of our system as a support system for discovery learning. As a consequence of experiments with 26 students who created contemporary dances, we verified that BMSS is a helpful creation training tool to discover new choreographic methods, new dance movements, and new awareness of their bodies.
This paper describes a new method of dance e-learning by which students can learn to create contemporary dance choreography using 3D motion data. The method is designed to promote discovery learning of contemporary dance. 'Body-part Motion Synthesis System (BMSS) ' is implemented on tablets, which allows users to select body-part motion clips of basic dance movement and preview a short dance sequence synthesizing them by 3DCG in real time. Body-part motions of contemporary dance performed by a professional dancer are captured and prepared as 3D motion clips. To evaluate the feasibility of the learning effects of the e-learning method using BMSS two evaluation experiments were conducted. In the first experiment, 18 students who majored in contemporary dance at universities in Japan and the U.S. Created short dance pieces using the system and performed them by themselves. In the second experiment, five Japanese dance critics evaluated the video of their performances comparing 3DCG animation. As a consequence of the experiments, we verified that our e-learning method for contemporary dance is effective as a trigger of discovery learning to find both a new choreographic method and original dance movements.
Labanotation, invented for describing human body movement, is a dance notation system widely used in Western dance communities. The notation is very useful for composing a dance as well as performing it. This paper covers applications for recording and generating human body motion with Labanotation. The paper is divided into two parts: The first part describes a Labanotation editing tool named LabanEditor. LabanEditor includes the functionalities of both preparing Labanotation scores and displaying character animation so that beginners who are not familiar with Labanotation can study its description using a trial-and-error approach. The applicability of LabanEditor is shown by applying it to Noh-plays, a Japanese stylized traditional dance. The second part is an approach for generating Labanotation scores from motion capture data. The system consists of selecting key-frames of motion capture data, encoding posture for the key-frames, and generating Labanotation data. The experiments showed that for dancers, dance instructors and choreographers, both systems are potential tools for notating dance movements with Labanotation scores.
We give polynomial time algorithms for the maximum independent set and maximum clique problems for classes of overlap graphs, assuming an overlap model is provided as input. The independent set algorithm applies to any class of overlap graphs for which the maximum weight independent set problem is polynomially solvable on the corresponding intersection graph class, where the vertex weights are nonnegative integers on which arithmetic operations can be performed in constant time. The maximum clique algorithm requires only that the overlap model satisfy the Helly property. In both cases, the size of the overlap model must be bounded by a polynomial in the size of the graph. The conditions for both algorithms are satisfied by the class of overlap graphs of subtrees in a tree, which contains chordal graphs, circle graphs, circular-arc graphs, cocomparability graphs, and polygon-circle graphs.
Symbolic systems such as Labanotation for notating dance and choreography provide a critical tool for the preservation of cultural heritage in what once was considered an ‘illiterate’ art form. While the goals of such notation systems are laudable, the unfortunate reality is that most dancers and choreographers cannot read or write the notation; that is, they are loath to take the considerable effort to learn a rich, but complex methodology. To make Labanotation scores more accessible the LabanDancer system has been developed to translate Labanotation scores recorded in the LabanWriter editor into 3-d human figure animations. A major challenge in the development of this translator has been to find approaches that are general enough to create reasonable animations for a wide variety of different movements. Any translator must also take account of the context of a movement since this can affect the interpretation of the Labanotation scores. Copyright © 2005 John Wiley & Sons, Ltd.