Abstract
A biologically-inspired model of visual attention known as basic saliency model is biased for object detection. It is possible to make this model faster by inhibiting computation of features or scales, which are less important for detection of an object. To this end, we revise this model by implementing a new scale-wise surround inhibition. Each feature channel and scale is associated with a weight and a processing cost. Then a global optimization algorithm is used to find a weight vector with maximum detection rate and minimum processing cost. This allows achieving maximum object detection rate for real time tasks when maximum processing time is limited. A heuristic is also proposed for learning top-down spatial attention control to further limit the saliency computation. Comparing over five objects, our approach has 85.4 and 92.2% average detection rates with and without cost, respectively, which are above 80% of the basic saliency model. Our approach has 33.3 average processing cost compared with 52 processing cost of the basic model. We achieved lower average hit numbers compared with NVT but slightly higher than VOCUS attentional systems.
Similar content being viewed by others
References
Desimone R., Duncan J.: Neural mechanisms of selective visual attention. Ann. Rev. Neurosci. 18, 193–222 (1955)
Li Z.: A saliency map in primary visual cortex. Trends Cogn. Sci. 6, 9–16 (2002)
Corbetta M., Shulman G.L.: Control of goal-directed and stimulus-driven attention in the brain. Nat. Rev. 3, 201–215 (2002)
Posner M.I.: Orienting of attention. Q. J. Exp. Psychol. 32, 3–25 (1980)
Posner, M.I., Cohen, Y.: Components of visual orienting. Attention and Performance X, In: Bouma, H., Hillsdale, B.D. (eds.) Erlbaum, 531–556 (1984)
Maunsell J.H., Treue S.: Feature-based attention in visual cortex, Trends in Neurosciences. Neural Substr. Cogn. 29, 317–322 (2006)
Kanwisher N., Driver J.: Objects, attributes, and visual attention: which, what, and where. Curr. Dir. Psychol. Sci. 1, 26–31 (1992)
Yarbus A.L.: Eye movements during perception of complex objects. In: Riggs, L.A.(eds) Eye Movements and Vision, Chap VII, pp. 171–196. Plenum Press, New York (1967)
Itti L., Koch C., Niebur E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254–1259 (1998)
Nakayama K., Maljkovic V., Kristjansson A.: Short term memory for the rapid deployment of visual attention. In: Gazzaniga, M.S.(eds) The Cognitive Neurosciences, 3rd edn, MIT Press, Cambridge (2004)
Nakayama K., Mackeben M.: Sustained and transient components of focal visual attention. Vis. Res. 29, 1631–1647 (1989)
Kristjansson A., Nakayama K.: A primitive memory system for the deployment of transient attention. Percept. Psychophys. 65, 711–724 (2003)
Maljkovic V., Nakayama K.: Priming of popout I. role of features. Mem. Cogn. 22, 657–672 (1994)
Rybak I.A., Gusakova V.I., Golovan A.V., Podladchikova L.N., Shevtsova N.A.: A model of attention-guided visual perception and recognition. Vis. Res. 38, 2387–2400 (1998)
Klein R.M.: Inhibition of return. Trends Cogn. Sci. 4, 138–147 (2000)
Koch C., Ullman S.: Shifts in selective visual attention: towards the underlying neural circuitry. Hum. Neurobiol. 4, 219–227 (1985)
Peters, R.J., Itti, L.: Applying computational tools to predict gaze direction in interactive visual environments. ACM Trans. Appl. Percept. 5(2), Article 8 (2008)
Navalpakkam V., Itti L.: Modeling the influence of task on attention. Vis. Res. 45, 205–231 (2005)
Frintrop, S.: VOCUS: a visual attention system for object detection and goal-directed search, vol. 3899. PhD thesis, Lecture Notes in Artificial Intelligence (LNAI) (2006)
Navalpakkam, V., Itti, L.: An integrated model of top-down and bottom-up attention for optimizing detection speed. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 2049–2056 (2006)
Gavrila, D.M.: Traffic sign recognition revisited. In: Mustererkennung (DAGM). Springer, Bonn (1999)
Barnes, N., Zelinsky, A.: Real-time radial symmetry for speed sign detection. In: IEEE Intelligent Vehicles Symposium (IV), pp. 566–571, Parma, Italy (2004)
de la Escalera A., Armingol J.M., Mata M.: Traffic sign recognition and analysis for intelligent vehicles. Image Vis. Comput. 21, 247–258 (2003)
Paclik P., Novovicova J., Somol P., Pudil P.: Road sign classification using Laplace kernel classifier. Pattern Recognit. Lett. 21(13–14), 1165–1173 (2000)
Gomez, L.C., Fuentes, O.: Color-based road sign detection and tracking. In: Proceedings Image Analysis and Recognition (ICIAR), Montreal (2007)
Fang C.Y., Chen S.W., Fuh C.S.: Road-sign detection and tracking. IEEE Trans. Vehicular Technol. 52(5), 1329–1341 (2003)
de la Escalera A., Moreno L.: Road traffic sign detection and classification. IEEE Trans. Ind. Electron. 44, 848–859 (1997)
Burt P.J., Adelson E.H.: The Laplacian pyramid as a compact image code. IEEE Trans. Commun. 31(4), 532–540 (1983)
Itti L., Koch C.: Feature combination strategies for saliency-based visual attention systems. J. Electron. Imaging 10(1), 161–169 (2001)
Saliency toolbox homepage. http://www.saliencytoolbox.net/
Liang J.J., Qin A.K., Suganthan P.N., Baskar S.: Comprehensive learning particle swarm optimizer for global optimization of multimodal functions. IEEE Trans. Evol. comput. 10(3), 281–295 (2006)
Wolfe J.M.: Visual search. In: Pashler, H.(eds) Attention, East Sussex, Psychology Press, UK (1998)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Borji, A., Ahmadabadi, M.N. & Araabi, B.N. Cost-sensitive learning of top-down modulation for attentional control. Machine Vision and Applications 22, 61–76 (2011). https://doi.org/10.1007/s00138-009-0192-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-009-0192-0