A system for automatic generation of labanotation from motion capture data

Labanotation is a kind of action notation as similar as staff notation of music. Moreover, it is intuitive, convenient and easy to read. So Labanotation has been widely recognized and used. In order to extract and make use of motion data effectively, this paper proposed a method to generate Labanotation from motion capture data. Firstly, motions are identified by key frame sequence similarity matching with standard basic motions in the library. Secondly, the data is converted into world coordinate and offset data. Then the long motion string is segmented into basic motions. After moving and supporting parts of body are determined, key frame of the motions is extracted. Finally, similarity matching will be done and Labanotation could be obtained. More importantly, experimental results using a large database show the superiority of the proposed method.