Abstract
Artificial visual attention is one of the key methodologies inspired from nature that can lead to robust and efficient visual search by machine vision systems. A novel approach is proposed for modeling of top-down visual attention in which separate saliency maps for the two attention pathways are suggested. The maps for the bottom-up pathway are built using unbiased rarity criteria while the top-down maps are created using fine-grain feature similarity with the search target as suggested by the literature on natural vision. The model has shown robustness and efficiency during experiments on visual search using natural and artificial visual input under static as well as dynamic scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lanyon, L., Denham, S.: A model of object-based attention that guides active visual search to behaviourally relevant locations. In: Paletta, L., Tsotsos, J.K., Rome, E., Humphreys, G.W. (eds.) WAPCV 2004. LNCS, vol. 3368, pp. 42–56. Springer, Heidelberg (2005)
Laar, P., Heskes, T., Gielen, S.: Task-dependent learning of attention. Neural Networks 10, 981–992 (1997)
Hamker, F.H.: 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. 118–132. Springer, Heidelberg (2005)
Deco, G.: The computational neuroscience of visual cognition: Attention, memory and reward. In: Paletta, L., Tsotsos, J.K., Rome, E., Humphreys, G.W. (eds.) WAPCV 2004. LNCS, vol. 3368, pp. 100–117. Springer, Heidelberg (2005)
Navalpakkam, V., Itti, L.: Top-down attention selection is fine-grained. Journal of Vision 6, 1180–1193 (2006)
Itti, L., Koch, U., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. Transactions on PAMI 20, 1254–1259 (1998)
Itti, L., Koch, C.: A saliency based search mechanism for overt and covert shifts of visual attention. Vision Research, pp. 1489–1506 (2000)
Navalpakkam, V., Itti, L.: Modeling the influence of task on attention. Vision Research, pp. 205–231 (2005)
Navalpakkam, V., Itti, L.: Optimal cue selection strategy. In: NIPS 2006, pp. 1–8. MIT Press, Cambridge (2006)
Frintrop, S., Backer, G., Rome, E.: Goal-directed search with a top-down modulated computational attention system. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds.) DAGM 2005. LNCS, vol. 3663, pp. 117–124. Springer, Heidelberg (2005)
Michalke, T., Gepperth, A., Schneider, M., Fritsch, J., Goerick, C.: Towards a human-like vision system for resource-constrained intelligent cars. In: ICVS 2007, Bielefeld University eCollections, Germany, pp. 264–275 (2004)
Hawes, N., Wyatt, J.: Towards context-sensitive visual attention. In: Second International Cognitive Vision Workshop (ICVW 2006) (2006)
Tagare, H.D., Toyama, K., Wang, J.G.: A maximum-likelihood strategy for directing attention during visual search. Transactions on PAMI 23, 490–500 (2001)
Peters, R.J., Itti, L.: Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention. In: CVPR 2007, IEEE, Los Alamitos (2007)
Sun, Y., Fischer, R.: Object-based visual attention for computer vision. Artificial Intelligence 146, 77–123 (2003)
Backer, G., Mertsching, B., Bollmann, M.: Data- and model-driven gaze control for an active-vision system. Transactions on PAMI 23, 1415–1429 (2001)
Aziz, M.Z., Mertsching, B., Shafik, M.S., Stemmer, R.: Evaluation of visual attention models for robots. In: ICVS 2006, IEEE, New York (2006) index–20
Aziz, M.Z., Mertsching, B.: Color segmentation for a region-based attention model. In: 12. Workshop Farbbildverarbeitung (FWS 2006), pp. 74–83 (2006)
Aziz, M.Z., Mertsching, B.: Color saliency and inhibition in region based visual attention. In: WAPCV 2007, Hyderabad, India, pp. 95–108 (2007)
Aziz, M.Z., Mertsching, B.: Fast and robust generation of feature maps for region-based visual attention. In: IEEE Transactions on Image Processing (2008)
Aziz, M.Z., Mertsching, B.: Pop-out and IOR in static scenes with region based visual attention. In: WCAA-ICVS 2007, Bielefeld University eCollections (2007)
Aziz, M.Z., Mertsching, B.: Region-based top-down visual attention through fine grain color map. In: 13 Workshop Farbbildverarbeitung (FWS 2007), pp. 83–92 (2007)
Aziz, M.Z., Mertsching, B.: Color saliency and inhibition using static and dynamic scenes in region based visual attention. In: Attention in Cognitive Systems. LNCS (LNAI), vol. 4840, pp. 234–250 (2007)
Kutter, O., Hilker, C., Simon, A., Mertsching, B.: Modeling and Simulating Mobile Robots Environments. In: 3rd International Conference on Computer Graphics Theory and Applications (GRAPP 2008) (2008)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aziz, M.Z., Mertsching, B. (2008). Visual Search in Static and Dynamic Scenes Using Fine-Grain Top-Down Visual Attention. In: Gasteratos, A., Vincze, M., Tsotsos, J.K. (eds) Computer Vision Systems. ICVS 2008. Lecture Notes in Computer Science, vol 5008. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-79547-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-540-79547-6_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-79546-9
Online ISBN: 978-3-540-79547-6
eBook Packages: Computer ScienceComputer Science (R0)