Abstract
Visual attention is the ability to rapidly detect the visually salient parts of a given scene. Inspired by biological vision, the saliency-based algorithm efficiently models the visual attention process. Due to its complexity, the saliency-based model of visual attention needs, for a real time implementation, higher computation resources than available in conventional processors. This work reports a real time implementation of this attention model on a highly parallel Single Instruction Multiple Data (SIMD) architecture called ProtoEye. Tailored for low-level image processing, ProtoEye consists of a 2D array of mixed analog-digital processing elements (PE). The operations required for visual attention computation are optimally distributed on the analog and digital parts. The analog diffusion network is used to implement the spatial filtering-based transformations such as the conspicuity operator and the competitive normalization of conspicuity maps. Whereas the digital part of Proto-Eye allows the implementation of logical and arithmetical operations, for instance, the integration of the normalized conspicuity maps into the final saliency map. Using 64 × 64 gray level images, the on ProtoEye implemented attention process operates in real-time. It runs at a frequency of 14 images per second.
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
Ch. Koch and S. Ullman. Shifts in selective visual attention: Towards the underlying neural circuity. Human Neurobiology (1985) 4, pp. 219–227, 1985.
L. Itti, Ch. Koch, and E. Niebur. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 20(11), pp. 1254–1259, 1998.
V. Brajovic and T. Kanade. Computational sensor for visual tracking with attention. IEEE Journal of Solid State Circuits, Vol. 33(8), pp. 1199–1207, 1998.
G. Indiveri. Modeling selective attention using a neuromorphic VLSI device. Neural Computation, 2000. Volume 12, pp.2857–2880, 2000.
L. Itti. Real-time high-performance attention focusing in outdoors color video streams. In: Proc. SPIE Human Vision and Electronic Imaging IV (HVEI’02), San Jose, CA, in press, 2002.
P.-F. Ruedi, P.R. Marchal, and X. Arreguit. A mixed digital-analog SIMD chip tailored for image perception. Proc. of International Conference on Image Processing 96, pp. 1011–1014, Vol. 2, Lausanne, 1996.
E.A. Vittoz and X. Arreguit. Linear networks based on transistors. Electronic Letters, Vol. 29, pp. 297–299, 1993.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ouerhani, N., Hügli, H., Burgi, PY., Ruedi, PF. (2002). A Real Time Implementation of the Saliency-Based Model of Visual Attention on a SIMD Architecture. In: Van Gool, L. (eds) Pattern Recognition. DAGM 2002. Lecture Notes in Computer Science, vol 2449. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45783-6_34
Download citation
DOI: https://doi.org/10.1007/3-540-45783-6_34
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44209-7
Online ISBN: 978-3-540-45783-1
eBook Packages: Springer Book Archive