Aligned Cluster Analysis for temporal segmentation of human motion

Temporal segmentation of human motion into actions is a crucial step for understanding and building computational models of human motion. Several issues contribute to the challenge of this task. These include the large variability in the temporal scale and periodicity of human actions, as well as the exponential nature of all possible movement combinations. We formulate the temporal segmentation problem as an extension of standard clustering algorithms. In particular, this paper proposes aligned cluster analysis (ACA), a robust method to temporally segment streams of motion capture data into actions. ACA extends standard kernel k-means clustering in two ways: (1) the cluster means contain a variable number of features, and (2) a dynamic time warping (DTW) kernel is used to achieve temporal invariance. Experimental results, reported on synthetic data and the Carnegie Mellon Motion Capture database, demonstrate its effectiveness.

[1]  Donald E. Knuth.  The Stanford GraphBase: a platform for combinatorial algorithms , 1993, SODA '93.

[2]  Lance Williams,et al.  Motion signal processing , 1995, SIGGRAPH.

[3]  Paul S. Bradley,et al.  Refining Initial Points for K-Means Clustering , 1998, ICML.

[4]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[5]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[6]  R. Bowden.  Learning Statistical Models of Human Motion , 2000 .

[7]  Richard Szeliski,et al.  Video textures , 2000, SIGGRAPH.

[8]  Aaron Hertzmann,et al.  Style machines , 2000, SIGGRAPH 2000.

[9]  Jitendra Malik,et al.  Normalized Cuts and Image Segmentation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[11]  Lihi Zelnik-Manor,et al.  Event-based analysis of video , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Shigeki Sagayama,et al.  Dynamic Time-Alignment Kernel in Support Vector Machine , 2001, NIPS.

[13]  Ronald L. Rivest,et al.  Introduction to Algorithms, Second Edition , 2001 .

[14]  Maja J. Mataric,et al.  Automated Derivation of Primitives for Movement Classification , 2000, Auton. Robots.

[15]  Harry Shum,et al.  Motion texture: a two-level statistical model for character motion synthesis , 2002, ACM Trans. Graph..

[16]  Maja J. Mataric,et al.  Deriving action and behavior primitives from human motion data , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Jernej Barbic,et al.  Segmenting Motion Capture Data into Distinct Behaviors , 2004, Graphics Interface.

[18]  Eamonn J. Keogh,et al.  Exact indexing of dynamic time warping , 2002, Knowledge and Information Systems.

[19]  Eamonn J. Keogh,et al.  On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration , 2002, Data Mining and Knowledge Discovery.

[20]  Michael Gleicher,et al.  Automated extraction and parameterization of motions in large data sets , 2004, SIGGRAPH 2004.

[21]  Jianbo Shi,et al.  Detecting unusual activity in video , 2004, CVPR 2004.

[22]  Eugene Fiume,et al.  An efficient search algorithm for motion data using weighted PCA , 2005, SCA '05.

[23]  Yiannis Aloimonos,et al.  Understanding visuo‐motor primitives for motion synthesis and analysis , 2006, Comput. Animat. Virtual Worlds.

[24]  Yiannis Aloimonos,et al.  Understanding visuo-motor primitives for motion synthesis and analysis: Research Articles , 2006 .

[25]  Philip S. Yu,et al.  Global distance-based segmentation of trajectories , 2006, KDD '06.

[26]  Fernando De la Torre,et al.  Temporal Segmentation of Facial Behavior , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[27]  Philippe Beaudoin,et al.  Motion-motif graphs , 2008, SCA '08.