Learning Features of Intermediate Complexity for the Recognition of Biological Motion

Humans can recognize biological motion from strongly impoverished stimuli, like point-light displays. Although the neural mechanism underlying this robust perceptual process have not yet been clarified, one possible explanation is that the visual system extracts specific motion features that are suitable for the robust recognition of both normal and degraded stimuli. We present a neural model for biological motion recognition that learns robust mid-level motion features in an unsupervised way using a neurally plausible memory-trace learning rule. Optimal mid-level features were learnt from image motion sequences containing a walker with, or without background motion clutter. After learning of the motion features, the detection performance of the model substantially increases, in particular in presence of clutter. The learned mid-level motion features are characterized by horizontal opponent motion, where this feature type arises more frequently for the training stimuli without motion clutter. The learned features are consistent with recent psychophysical data that indicates that opponent motion might be critical for the detection of point light walkers.

[1]  B. Hassenstein,et al.  Systemtheoretische Analyse der Zeit-, Reihenfolgen- und Vorzeichenauswertung bei der Bewegungsperzeption des Rüsselkäfers Chlorophanus , 1956 .

[2]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[3]  D H HUBEL,et al.  RECEPTIVE FIELDS AND FUNCTIONAL ARCHITECTURE IN TWO NONSTRIATE VISUAL AREAS (18 AND 19) OF THE CAT. , 1965, Journal of neurophysiology.

[4]  G. Johansson.  Visual perception of biological motion and a model for its analysis , 1973 .

[5]  A. J. Mistlin,et al.  Visual analysis of body movements by neurones in the temporal cortex of the macaque monkey: A preliminary report , 1985, Behavioural Brain Research.

[6]  J Allman,et al.  Direction- and Velocity-Specific Responses from beyond the Classical Receptive Field in the Middle Temporal Visual Area (MT) , 1985, Perception.

[7]  K. Tanaka,et al.  Analysis of motion of the visual field by direction, expansion/contraction, and rotation cells clustered in the dorsal part of the medial superior temporal area of the macaque monkey. , 1989, Journal of neurophysiology.

[8]  Peter Földiák,et al.  Learning Invariance from Transformation Sequences , 1991, Neural Comput..

[9]  G. Mather,et al.  Low-level visual processing of biological motion , 1992, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[10]  D. V. van Essen,et al.  Selectivity for polar, hyperbolic, and Cartesian gratings in macaque visual cortex. , 1993, Science.

[11]  W. Dittrich.  Action Categories and the Perception of Biological Motion , 1993, Perception.

[12]  Andrew T. Smith,et al.  Visual detection of motion , 1994 .

[13]  N. Logothetis,et al.  View-dependent object recognition by monkeys , 1994, Current Biology.

[14]  N. Logothetis,et al.  Shape representation in the inferior temporal cortex of monkeys , 1995, Current Biology.

[15]  G. Orban,et al.  Spatial heterogeneity of inhibitory surrounds in the middle temporal visual area. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[16]  C. Gross.  Brain Mechanisms of Perception and Memory: From Neuron to Behavior.Taketoshi Ono , Larry R. Squire , Marcus E. Raichle , David I. Perrett , Masaji Fukuda , 1995 .

[17]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[18]  D. Perrett,et al.  Integration of form and motion in the anterior superior temporal polysensory area (STPa) of the macaque monkey. , 1996, Journal of neurophysiology.

[19]  Keiji Tanaka,et al.  Inferotemporal cortex and object vision. , 1996, Annual review of neuroscience.

[20]  R. Blake,et al.  Perception of Biological Motion , 1997, Perception.

[21]  M. Livingstone,et al.  Mechanisms of Direction Selectivity in Macaque V1 , 1998, Neuron.

[22]  Paul Mineiro,et al.  Analysis of Direction Selectivity Arising from Recurrent Cortical Interactions , 1998, Neural Computation.

[23]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[24]  R. Wurtz,et al.  Response to motion in extrastriate area MSTl: center-surround interactions. , 1998, Journal of neurophysiology.

[25]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[26]  A. L. Humphrey,et al.  Inhibitory contributions to spatiotemporal receptive-field structure and direction selectivity in simple cells of cat area 17. , 1999, Journal of neurophysiology.

[27]  J. Hegdé,et al.  Selectivity for Complex Shapes in Primate Visual Area V2 , 2000, The Journal of Neuroscience.

[28]  Tomaso Poggio,et al.  Models of object recognition , 2000, Nature Neuroscience.

[29]  R. Born.  Center-surround interactions in the middle temporal visual area of the owl monkey. , 2000, Journal of neurophysiology.

[30]  Thomas Serre,et al.  Component-based face detection , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[31]  P. Sinha,et al.  Functional neuroanatomy of biological motion perception in humans , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[32]  Yang Song,et al.  Unsupervised Learning of Human Motion Models , 2001, NIPS.

[33]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[34]  G. Rizzolatti,et al.  Neurophysiological mechanisms underlying the understanding and imitation of action , 2001, Nature Reviews Neuroscience.

[35]  Stanley M. Bileschi,et al.  Advances in Component-Based Face Detection , 2002, SVM.

[36]  M. Lappe,et al.  Measurement of generalization fields for the recognition of biological motion , 2002, Vision Research.

[37]  Thomas Serre,et al.  On the Role of Object-Specific Features for Real World Object Recognition in Biological Vision , 2002, Biologically Motivated Computer Vision.

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

[39]  M. Tarr,et al.  Visual Object Recognition , 1996, ISTCS.

[40]  Stanley M. Bileschi,et al.  Advances in component based face detection , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[41]  Jennifer Louie.  A biological model of object recognition with feature learning , 2003 .

[42]  Martin A. Giese,et al.  Roles of Motion and Form in Biological Motion Recognition , 2003, ICANN.

[43]  T. Poggio,et al.  Cognitive neuroscience: Neural mechanisms for the recognition of biological movements , 2003, Nature Reviews Neuroscience.

[44]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[45]  H. Rodman,et al.  Single-unit analysis of pattern-motion selective properties in the middle temporal visual area (MT) , 2004, Experimental Brain Research.

[46]  Brian Leung,et al.  Component-based Car Detection in Street Scene Images , 2004 .

[47]  L. Chalupa,et al.  The visual neurosciences , 2004 .

[48]  Antonino Casile,et al.  Critical features for the recognition of biological motion. , 2005, Journal of vision.

[49]  Tomaso Poggio,et al.  Learning a dictionary of shape-components in visual cortex: comparison with neurons, humans and machines , 2006 .