Documenting motion sequences with a personalized annotation system

We present a novel technique for motion annotation that adapts to a person's style and vocabulary of basic movements (gestures). The system segments continuous motion sequences into gestures, which it then documents in a personalized annotation with an intuitive hierarchical representation. Initial testing suggests that software based on this technique could be an effective teaching aid for dance and sports.

[1]  Toshi Takamori,et al.  The description of human movement in computer based on the movement score , 2002, Proceedings of the 41st SICE Annual Conference. SICE 2002..

[2]  Sethuraman Panchanathan,et al.  Computational analysis of mannerism gestures , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[3]  Sethuraman Panchanathan,et al.  Automated gesture segmentation from dance sequences , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[4]  Adam Kendon,et al.  How gestures can become like words , 1988 .

[5]  I M Anonymous.  Towards a One-Way American Sign Language Translator , .

[6]  Maxine D. Brown,et al.  A graphics editor for labanotation , 1976, SIGGRAPH.

[7]  Joydeep Ghosh,et al.  HMMs and Coupled HMMs for multi-channel EEG classification , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[8]  Kozaburo Hachimura,et al.  Method of generating coded description of human body motion from motion-captured data , 2001, Proceedings 10th IEEE International Workshop on Robot and Human Interactive Communication. ROMAN 2001 (Cat. No.01TH8591).

[9]  Michael Kipp,et al.  ANVIL - a generic annotation tool for multimodal dialogue , 2001, INTERSPEECH.