Abstract
Studies on visual attention traditionally focus on its physiological and psychophysical nature [16,18,19], or its algorithmic applications [1,9,21]. We here develop a simple, formal mathematical model of the advantage of spatial attention for object detection, in which spatial attention is defined as processing a subset of the visual input, and detection is an abstraction with certain failure characteristics. We demonstrate that it is suboptimal to process the entire visual input given prior information about target locations, which in practice is almost always available in a video setting due to tracking, motion, or saliency. This argues for an attentional strategy independent of computational savings: no matter how much computational power is available, it is in principle better to dedicate it preferentially to selected portions of the scene. This suggests, anecdotally, a form of environmental pressure for the evolution of foveated photoreceptor densities in the retina. It also offers a general justification for the use of spatial attention in machine vision.
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
Tsotsos, J.K., Culhane, S.M., Kei Wai, W.Y., Lai, Y., Davis, N.: Modeling visual attention via selective tuning. Artificial Intelligence (1995)
Amit, Y., Geman, D.: A Computational Model for Visual Selection. Neural Computation (1999)
Yu, A., Dayan, P.: Inference, Attention, and Decision in a Bayesian Neural Architecture. In: Proc. Neural Information Processing Systems (NIPS) (2004)
Bonaiuto, J., Itti, L.: Combining attention and recognition for rapid scene analysis. In: Proc. IEEE-CVPR Workshop on Attention and Performance in Computer Vision (WAPCV 2005) (2005)
Rutishauser, U., Walther, D., Koch, C., Perona, P.: Is attention useful for object recognition? In: Proc. International Conference on Computer Vision and Pattern Recognition (CVPR) (2004)
Miau, F., Papageorgiou, C.S., Itti, L.: Neuromorphic algorithms for computer vision and attention. In: Proceedings of Annual International Symposium on Optical Science and Technology (SPIE) (2001)
Moosmann, F., Larlus, D., Jurie, F.: Learning Saliency Maps for Object Categorization. In: ECCV International Workshop on The Representation and Use of Prior Knowledge in Vision (2006)
Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. Hum. Neurobiol. (1985)
Itti, L., Koch, C.: Computational modeling of visual attention. Nature Reviews Neuroscience (2001)
Ye, Y., Tsotos, J.K.: Where to Look Next in 3D Object Search. In: Proc. of Internat. Symp. on Comp. Vis. (1995)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2006)
Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision (2004)
Waydo, S., Kraskov, A., Quian Quiroga, R., Fried, I., Koch, C.: Sparse Representation in the Human Medial Temporal Lobe. Journal of Neuroscience (2006)
Treisman, A.: How the deployment of attention determines what we see. Visual Cognition (2006)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. Computer Vision and Pattern Recognition (CVPR)(2001)
Pashler, H.E.: The Psychology of Attention. MIT Press, Cambridge (1998)
Braun, J., Koch, C., Davis, J.L. (eds.): Visual Attention and Cortical Circuits. MIT Press, Cambridge (2001)
Walther, D., Koch, C.: Modeling attention to salient proto-objects. Neural Networks (2006)
Mitri, S., Frintrop, S., Pervolz, K., Surmann, H., Nuchter, A.: Robust Object Detection at Regions of Interest with an Application in Ball Recognition. In: Proc. of International Conference on Robotics and Automation (ICRA) (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Harel, J., Koch, C. (2009). On the Optimality of Spatial Attention for Object Detection. In: Paletta, L., Tsotsos, J.K. (eds) Attention in Cognitive Systems. WAPCV 2008. Lecture Notes in Computer Science(), vol 5395. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-00582-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-00582-4_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-00581-7
Online ISBN: 978-3-642-00582-4
eBook Packages: Computer ScienceComputer Science (R0)