Discovery of Skills from Motion Data
In this paper, we discuss how to discover “skills” from motion data. Being able to understand how a skilled person moves enables beginners to make better use of their bodies and to become experts easier. However, only few attempts have so far been made for discovering skills from human motion data. To extract skills from motion data, we employ three approaches. As a first approach, we present association rule approach which extracts the dependency among the body parts to find the movement of the body parts performed by the experts. The second is an approach that extracts frequent patterns (motifs) from motion data. Recently, many researchers propose algorithms for discovering motifs. However, these algorithms require that users define the length of the motifs in advance. Our algorithm uses the MDL principle to overcome this problem so as to discover motifs with optimal length. Finally, we compare the motions of skilled tennis players and beginners, and discuss why skilled players can better serve.
KeywordsAssociation Rule Time Series Data Motion Data Frequent Pattern Dynamic Time Warping
Unable to display preview. Download preview PDF.
- 1.Gavrila, D.M., Davis, L.S.: 3D Model-based Tracking of Humans in Action: A Multi-view Approach. In: Proc. of Computer Vision and Pattern Recognition, pp. 73–80 (1996)Google Scholar
- 2.Bradski, G.R., Davis, J.: Motion Segmentation and Pose Recognition with Motion History Gradients. In: Proc. of IEEE Workshop on Detection and Recognition of Events in Video, IEEE Computer Society Press, Los Alamitos (2001)Google Scholar
- 4.Widmer, G., Dixon, S., Goebl, W., Pampalk, E.: In Search of the Horowitz Factor. AI Magazine 24(3), 111–130 (2003)Google Scholar
- 5.Osaki, R., Shimada, M., Uehara, K.: A Motion Recognition Method by Using Primitive Motions. In: Proc. of 5th IFIP 2.6 Working Conference on Visual Database Systems, pp. 117–128 (2000)Google Scholar
- 6.Mori, T., Uehara, K.: Extraction of Primitive Motion and Discovery of Association Rules from Human Motion. In: Proc. of 10th IEEE International Workshop on Robot and Human Communication, pp. 200–206. IEEE Computer Society Press, Los Alamitos (2001)Google Scholar
- 8.Tanaka, Y., Iwamoto, K., Uehara, K.: Discovery of Time-Series Motif from Multi-Dimensional Data Based on MDL Principle. Machine Learning (to appear)Google Scholar
- 9.Lin, J., Keogh, E., Lonardi, S., Patel, P.: Finding Motifs in Time Series. In: Proc. of the 2nd Workshop on Temporal Data Mining, pp. 53–68 (2002)Google Scholar
- 10.Lin, J., Keogh, E., Lonardi, S., Chiu, B.: A Symbolic Representation of Time Series with Implications for Streaming Algorithms. In: Proc. of the 8th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery, ACM Press, New York (2003)Google Scholar
- 11.Heras, D.B., Cabaleiro, J.C., Perez, V.B., Costas, P., Rivera, F.F.: Principal Component Analysis on Vector Computers. In: Palma, J.M.L.M., Dongarra, J.J. (eds.) VECPAR 1996. LNCS, vol. 1215, pp. 416–428. Springer, Heidelberg (1997)Google Scholar
- 15.Kruskal, J.B., Wish, M.: Multidimensional Scaling. Sage Publication, Thousand Oaks (1978)Google Scholar