Abstract
Multiresolution foveal imaging offers a field-of-view × acuity × frame rate product much greater than that of uniform acuity imaging, and can reduce the computational complexity of vision in dynamic scenarios with localized relevance. The latter requires space variant retinotopic processing with results that are consistent between different resolutions. A physiologically inspired connectionist model is presented which yields local speed estimates consistent between coarse resolution peripheral vision and fine resolution central vision. A non-uniform acuity profile across the field-of-view is compensated by an inverse profile of weights in the model. This model demonstrates the efficiency of multiresolution vision when processing and retinotopology are properly matched.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bandera, C. & Scott, P., “Foveal Machine Vision Systems,” Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Cambridge, MA, November 1989, pp. 596–599.
Kreider, Van der Spiegel, J., Born, I., Claeys, C., Debusschere, I., Sandini, G. & Dario, P., “The Design and Characterization of a Space Variant CCD Sensor,” SPIE vol. 1381 Intelligent Robots and Computer Vision IX: Algorithms and Techniques, pp. 242–249, 1990.
Vico, F.J., Garrido, F.J., Sandoval, F. & Leibovic, K.N., “A Connectionist Model for Local Speed Estimation,” Proceedings of the ICIP94, 1994.
Yeshurun, & Schwartz, E.L., “Shape Description With a Space-Variant Sensor: Algorithms For Scanpath, and Convergence Over Multiple Scans,” IEEE Trans. PAMI, vol. 11, no. 11, pp. 1217–1222, November 1989.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bandera, C., Conde, I.M., Jerez, J., González, M., Vico, F.J., Ortega, F. (1995). A multiacuity connectionist model for local speed estimation. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_276
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_276
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive