Repetitive motion analysis: segmentation and event classification

Acquisition, analysis, and classification of repetitive human motion for the assessment of postural stress is of central importance to ergonomics practitioners. We present a two-threshold, multidimensional segmentation algorithm to automatically decompose a complex motion into a sequence of simple linear dynamic models. No a priori assumptions were made about the number of models that comprise the full motion or about the duration of the task cycle. A compact motion representation is obtained for each segment using parameters of a damped harmonic dynamic model. Event classification was performed using cluster analysis with the model parameters as input. Experiments demonstrate the technique on complex motion.

[1]  P. Perona,et al.  Primitives for Human Motion: a Dynamical Approach , 2002 .

[2]  William T. Freeman,et al.  Bayesian Reconstruction of 3D Human Motion from Single-Camera Video , 1999, NIPS.

[3]  Nicola J. Ferrier,et al.  Multidimensional motion segmentation and identification , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[4]  Thomas D. C. Little,et al.  A Survey of Technologies for Parsing and Indexing Digital Video1 , 1996, J. Vis. Commun. Image Represent..

[5]  S S Ulin,et al.  Development and evaluation of an observational method for assessing repetition in hand tasks. , 1997, American Industrial Hygiene Association journal.

[6]  Vladimir Pavlovic,et al.  Impact of dynamic model learning on classification of human motion , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  Aaron F. Bobick,et al.  Recognition of Visual Activities and Interactions by Stochastic Parsing , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Christoph Bregler,et al.  Learning and recognizing human dynamics in video sequences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Jun Nakanishi,et al.  Movement imitation with nonlinear dynamical systems in humanoid robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[10]  Mitsuo Kawato,et al.  A theory for cursive handwriting based on the minimization principle , 1995, Biological Cybernetics.

[11]  Matthew Brand,et al.  Discovery and Segmentation of Activities in Video , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  M L Lin,et al.  Exposure assessment of biomechanical stress in repetitive manual work using frequency-weighted filters. , 1994, Ergonomics.

[13]  Takeo Kanade,et al.  Intelligent Access to Digital Video: Informedia Project , 1996, Computer.

[14]  H. Damasio,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence: Special Issue on Perceptual Organization in Computer Vision , 1998 .

[15]  Lennart Ljung,et al.  Theory and Practice of Recursive Identification , 1983 .

[16]  T.Y. Yen,et al.  A video-based system for acquiring biomechanical data synchronized with arbitrary events and activities , 1995, IEEE Transactions on Biomedical Engineering.

[17]  E. Bizzi,et al.  Learning Newtonian Mechanics , 1997 .

[18]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[19]  Nicola J. Ferrier,et al.  Automated analysis of repetitive joint motion , 2003, IEEE Transactions on Information Technology in Biomedicine.

[20]  P. Kumar,et al.  Theory and practice of recursive identification , 1985, IEEE Transactions on Automatic Control.