Abstract
In this paper we present VOCUS: a robust computational attention system for goal-directed search. A standard bottom-up architecture is extended by a top-down component, enabling the weighting of features depending on previously learned weights. The weights are derived from both target (excitation) and background properties (inhibition). A single system is used for bottom-up saliency computations, learning of feature weights, and goal-directed search. Detailed performance results for artificial and real-world images are presented, showing that a target is typically among the first 3 focused regions. VOCUS represents a robust and time-saving front-end for object recognition since by selecting regions of interest it significantly reduces the amount of data to be processed by a recognition system.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Backer, G., Mertsching, B., Bollmann, M.: Data- and model-driven Gaze Control for an Active-Vision System. IEEE Trans. on PAMI 23(12), 1415–1429 (2001)
Corbetta, M., Shulman, G.L.: Control of goal-directed and stimulus-driven attention in the brain. Nature Reviews 3, 201–215 (2002)
Frintrop, S.: VOCUS: A Visual Attention System for Object Detection and Goal-directed Search. PhD thesis University of Bonn Germany (2005) (to appear)
Frintrop, S., Backer, G., Rome, E.: Selecting what is Important: Training Visual Attention. In: Furbach, U. (ed.) KI 2005. LNCS (LNAI), vol. 3698, pp. 351–365. Springer, Heidelberg (2005)
Hamker, F.: Modeling Attention: From computational neuroscience to computer vision. In: Paletta, L., Tsotsos, J.K., Rome, E., Humphreys, G.W. (eds.) WAPCV 2004. LNCS, vol. 3368, pp. 59–66. Springer, Heidelberg (2005)
Itti, L., Koch, C., Niebur, E.: A Model of Saliency-Based Visual Attention for Rapid Scene Analysis. IEEE Trans. on PAMI 20, 1254–1259 (1998)
Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. Human Neurobiology 4, 219–227 (1985)
Navalpakkam, V., Rebesco, J., Itti, L.: Modeling the influence of task on attention. Vision Research 45, 205–231 (2005)
Neisser, U.: Cognitive Psychology. Appleton-Century-Crofts, New York (1967)
Palmer, S.E.: Vision Science, Photons to Phenomenology. MIT Press, Cambridge (1999)
Sun, Y., Fisher, R.: Object-based visual attention for computer vision. Artificial Intelligence 146, 77–123 (2003)
Theeuwes, J.: Top-down search strategies cannot override attentional capture. Psychonomic Bulletin & Review 11, 65–70 (2004)
Treisman, A.M., Gelade, G.: A feature integration theory of attention. Cognitive Psychology 12, 97–136 (1980)
Tsotsos, J.K., Culhane, S.M., Wai, W.Y.K., Lai, Y., Davis, N., Nuflo, F.: Modeling Visual Attention via Selective Tuning. AI 78, 507–545 (1995)
Wolfe, J.: Guided Search 2.0: A Revised Model of Visual Search. Psychonomic Bulletin & Review 1, 202–238 (1994)
Wolfe, J.M., Horowitz, T., Kenner, N., Hyle, M., Vasan, N.: How fast can you change your mind? The speed of top-down guidance in visual search. Vision Research 44, 1411–1426 (2004)
Yarbus, A.L.: Eye Movements and Vision. Plenum Press, New York (1969)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Frintrop, S., Backer, G., Rome, E. (2005). Goal-Directed Search with a Top-Down Modulated Computational Attention System. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds) Pattern Recognition. DAGM 2005. Lecture Notes in Computer Science, vol 3663. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550518_15
Download citation
DOI: https://doi.org/10.1007/11550518_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28703-2
Online ISBN: 978-3-540-31942-9
eBook Packages: Computer ScienceComputer Science (R0)Springer Nature Proceedings Computer Science
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.