A tunable perceptual microsystem for stereo depth estimation

The paper presents the design and analyzes the applications of a microsystem to be used for emulating, in real time, early vision tasks, such as stereo depth estimation and motion analysis. All the required computations are based on linear filtering operations with Gabor-like kernels. Full control on the parameters (phase, frequency, and spatial extension) of the kernel can be obtained by introducing a 2nd-order 1-D lattice network that can be mapped with efficiency on an array of simple cells, implemented as analog CMOS VLSI circuits, using continuously adjustable transconductors.