Digital implementation of a bio-inspired neural model for motion estimation

Motion estimation is a fundamental step to understand the dynamics of a scene to allow intelligent systems interact with their environment. Motion computation is usually restricted by real time requirements that need the design and implementation of specific hardware architectures. In this paper, the design of a digital hardware architecture for a bio-inspired neural model for motion estimation is presented. The motion estimation is based on a strongly localized bio-inspired connectionist model with a particular adaptation of spatio-temporal Gabor-like filtering, commonly used for early visual perception. The architecture is constituted by three main modules that perform three different kinds of processing: spatial, temporal, and excitatory-inhibitory connectionist processing. The architecture is modeled, simulated and validated in VHDL. Synthesis results of the spatial and temporal processing modules of the bio-inspired model on a field programmable gate array (FPGA) device are presented to validate the architecture. The results show the potential achievement of real-time performance at an affordable silicon area.