Object Selection with Dynamic Neural Maps

This contribution presents an approach for object selection. It is based on the functional role of attention in its control of action, that is the selection in space and the selection at the object level to serve the extraction of further object related features. The selection is performed on topographic maps which describe by their local activation the existence of an object hypothesis and is achieved by a dynamical two step process of i) competition and ii) region aggregation. The neural dynamics is based on analog neurons, mathematically described with a nonlinear activation dynamic. This method is appropriate for all objects which are detected by their local features, like color or texture. The performance is demonstrated on two real world selection problems.

[1]  Samuel Kaski,et al.  Winner-take-all networks for physiological models of competitive learning , 1994, Neural Networks.

[2]  David N. Kennedy,et al.  A recurrent cooperative/competitive field for segmentation of magnetic resonance brain imagery , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[3]  Horst-Michael Groß,et al.  Region selection: segmentation, classification and task relevance in a single grouping mechanism , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[4]  R. Desimone,et al.  Neural mechanisms of selective visual attention. , 1995, Annual review of neuroscience.

[5]  S. Yantis.  Multielement visual tracking: Attention and perceptual organization , 1992, Cognitive Psychology.

[6]  Horst-Michael Groß,et al.  Task-relevant relaxation network for visuo-motory systems , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[7]  S Grossberg,et al.  Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations , 1985, Perception & psychophysics.

[8]  Deictic codes, embodiment of cognition, and the real world , 1997, Behavioral and Brain Sciences.

[9]  A. Allport,et al.  Selection for action: Some behavioral and neurophysiological considerations of attention and action , 1987 .

[10]  Teuvo Kohonen,et al.  Physiological interpretation of the Self-Organizing Map algorithm , 1993, Neural Networks.

[11]  Rajesh P. N. Rao,et al.  Embodiment is the foundation, not a level , 1996, Behavioral and Brain Sciences.

[12]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[13]  Teuvo Kohonen,et al.  Physiological interpretationm of the self-organizing map algorithm , 1993 .

[14]  D. V. van Essen,et al.  A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[15]  O. Neumann.  Beyond capacity: A functional view of attention , 1987 .

[16]  H. Heuer,et al.  Perspectives on Perception and Action , 1989 .

[17]  M. Goodale,et al.  Chapter 28 Visual pathways to perception and action , 1993 .