Gender Recognition from Walking Movements using Adaptive Three-Mode PCA

We present an adaptive three-mode PCA framework for recognizing gender from walking movements. Prototype female and male walkers are initially decomposed into a sub-space of their three-mode components (posture, time, gender). We then assign an importance weight to each motion trajectory in the sub-space and have the model automatically learn the weight values (key features) from labeled training data. We present experiments of recognizing physical (actual) and perceived (from perceptual experiments) gender for 40 walkers. The model demonstrates greater than 90% recognition for both contexts and shows greater flexibility than standard PCA.

[1]  J. Cutting,et al.  Recognizing the sex of a walker from a dynamic point-light display , 1977 .

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

[3]  Hui Gao,et al.  A three-mode expressive feature model of action effort , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[4]  J E Cutting,et al.  A biomechanical invariant for gait perception. , 1978, Journal of experimental psychology. Human perception and performance.

[5]  S. Runeson,et al.  Visual perception of lifted weight. , 1981, Journal of experimental psychology. Human perception and performance.

[6]  J. Leeuw,et al.  Principal component analysis of three-mode data by means of alternating least squares algorithms , 1980 .

[7]  G. Mather,et al.  Gender discrimination in biological motion displays based on dynamic cues , 1994, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[8]  M. Alex O. Vasilescu.  Human motion signatures for character animation , 2001, SIGGRAPH 2001.

[9]  Norman I. Badler,et al.  The EMOTE model for effort and shape , 2000, SIGGRAPH.

[10]  Hui Gao,et al.  Recognizing human action efforts: an adaptive three-mode PCA framework , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[11]  N. Troje.  Decomposing biological motion: a framework for analysis and synthesis of human gait patterns. , 2002, Journal of vision.

[12]  Martin A. Giese,et al.  Morphable Models for the Analysis and Synthesis of Complex Motion Patterns , 2000, International Journal of Computer Vision.

[13]  Demetri Terzopoulos,et al.  Multilinear Analysis of Image Ensembles: TensorFaces , 2002, ECCV.

[14]  L. Tucker,et al.  Some mathematical notes on three-mode factor analysis , 1966, Psychometrika.

[15]  J. Cutting,et al.  Temporal and spatial factors in gait perception that influence gender recognition , 1978, Perception & psychophysics.

[16]  Michael J. Black,et al.  Parameterized Modeling and Recognition of Activities , 1999, Comput. Vis. Image Underst..

[17]  J. Miller.  Numerical Analysis , 1966, Nature.

[18]  Pieter M. Kroonenberg,et al.  Three-mode principal component analysis : theory and applications , 1983 .

[19]  Stephanie R. Taylor,et al.  Analysis and recognition of walking movements , 2002, Object recognition supported by user interaction for service robots.

[20]  G. Bingham,et al.  Kinematic form and scaling: further investigations on the visual perception of lifted weight. , 1987, Journal of experimental psychology. Human perception and performance.

[21]  Aaron F. Bobick,et al.  Parametric Hidden Markov Models for Gesture Recognition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  W. Eric L. Grimson,et al.  Gait analysis for recognition and classification , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[23]  James W. Davis,et al.  Visual Categorization of Children and Adult Walking Styles , 2001, AVBPA.

[24]  J. Cutting,et al.  Recognizing friends by their walk: Gait perception without familiarity cues , 1977 .

[25]  J. Douglas Faires,et al.  Numerical Analysis , 1981 .

[26]  Ken-ichi Anjyo,et al.  Fourier principles for emotion-based human figure animation , 1995, SIGGRAPH.

[27]  James W. Davis,et al.  Expressive features for movement exaggeration , 2002, SIGGRAPH '02.

[28]  T. Beardsworth,et al.  The ability to recognize oneself from a video recording of one’s movements without seeing one’s body , 1981 .

[29]  Hui Gao,et al.  An expressive three-mode principal components model of human action style , 2003, Image Vis. Comput..