Programmable retinal dynamics in a CMOS mixed-signal array processor chip

Abstract

The low-level image processing that takes place in the retina is intended to compress the relevant visual information to a manageable size. The behavior of the external layers of the biological retina has been successfully modelled by a Cellular Neural Network, whose evolution can be described by a set of coupled nonlinear differential equations. A mixed-signal VLSI implementation of the focal-plane low-level image processing based upon this biological model constitutes a feasible and cost effective alternative to conventional digital processing in real-time applications. For these reasons, a programmable array processor prototype chip has been designed and fabricated in a standard 0.5μm CMOS technology. The integrated system consists of a network of two coupled layers, containing 32 × 32 elementary processors, running at different time constants. Involved image processing algorithms can be programmed on this chip by tuning the appropriate interconnections weights. Propagative, active wave phenomena and retina-like effects can be observed in this chip. Design challenges, trade-offs, the buildings blocks and some test results are presented in this paper.