Motion analysis using the neural accelerator board

Abstract

For the analysis of motion in near real-time there are very high computational requirements. This is a limiting factor in the hardware implementation of such real-time systems. This application, however, is possible if implemented in the form of some parallel architecture. Neural network structures comprising a large number of simple processing elements can offer a solution to achieving the performance requirements of real-time motion analysis. This paper describes the Neural Accelerator, which is based on a systolic array architecture, and how it can be set up to sense the position and range of an object relative to the observer who is travelling towards it.<>