Abstract
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.
supported by the BMBF, Grant No. 413-5839-01 M 3014C - MIRIS-Project.
Preview
Unable to display preview. Download preview PDF.
References
Allport, A: Selection for action: Some behavioral and neurophysiological considerations of attention and action. Perspectives on Perception and Action., 395–419, 1987.
Amari, S.: Dynamics of pattern formation in lateral-inhibition type neural fields. Biological Cybernatics, vol. 27 (1977), 77–87.
Ballard, D. H.: Deictic codes for the embodiment of cognition. Behavioral and Brain Sciences, to appear 1997.
Böhme, H. J.; GroB, H.-M.; Braumann, U.-D.; Heinke, D.; Pomierski, T.; Brakensiek, A.: Active-Vision zur Selbstorganisation yon Verhalten in senso-motorischen Systemen. In: Proc. Workshop “Aktives Sehen in techn. u. biol. Systemen“, Hamburg, 60–66, 1996.
Desimone, R; Duncan, J.: Neural mechanisms of selective visual attention. Anual Review of Neuroscience, vol. 18 (1995), 193–222.
Grossberg, S.; Mingolla, E.: Neural dynamics of perceptual grouping: textures, boundaries, and emergent segmentations. Percep Psychophys, vol. 38 (1985), 141–171.
Hamker, F.; Gross, H.-M.: Region selection: segmentation, classification and task relevance in a single grouping mechanism. ICNN'96, Washington, 1540–1545, 1996.
Hamker, F.; Gross, H.-M.: Task Relevant Relaxation Network for visuo-motory Systems. ICPR'96, Vienna, 406–410, 1996.
Kaski, S; Kohonen, T.: Winner-take-all networks for physiological models of competitive learning. Neural Networks, vol. 7 (1994), 973–984.
Kohonen, T.: Physiological interpretation of the self-organizing map algorithm. Neural Networks, vol. 6 (1993), 895–905.
Milner, A. D.; Goodale, M. A: Visual pathways to perception and action. Progress in Brain Research, vol. 95 (1993), 317–337.
Neumann, O.: Beyond capacity: A functional view of attention. In: Perspectives on Perception and Action. Lawrence Erlbaum Associates, 361–393, 1987.
Olshausen, B.; Anderson, C.; van Essen, D.: A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. The Journal of Neuroscience, vol. 13, (1993), 4700–4719.
Treisman, A.; Gelade, G.: A feature-integration theory of attention. Cognitive Psychology, vol. 12 (1980), 97–136.
Yantis, S.: Multielement visual tracking: Attention and perceptual organization. Cognitive Psychology, vol. 24 (1992), 295–340.
Rosenfeld, A; Hummel, R. A.; Zucker, S. W.: Scene labeling by relaxation algorithms. IEEE Transactions on Systems, Man and Cybernatics, vol. 6 (1978), 267–287.
Worth, A. J.; Lehar, S.; Kennedy, D. N.: A recurrent cooperative%ompetitive field for segmentation of magnetic resonance brain images. IEEE Transactions on Knowledge and Data Engineering, vol. 4 no 2 (1992), 156–161.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hamker, F.H., Gross, HM. (1997). Object selection with dynamic neural maps. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020270
Download citation
DOI: https://doi.org/10.1007/BFb0020270
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive