MOTION SENSITIVE FILTERS

Abstract

Biological organisms excel at processing large amount of data in real time whereas computers usually are not good at such tasks. Thus a great deal of effort has been spent on the development of machines that mimic biological systems in computer vision. Such vision machines require the simple low-level feature detectors similar in that of the retina. It has been shown that active resistive diffusion networks offer a common framework for the implementation of the low-level feature detectors commonly used in vision. Cellular Neural Networks consist of regular arrays of simple processing units that interact with only their nearest neighbors. The CNN architecture bears striking resemblance to aforementioned biological organisms and they are tailor-made for analog VLSI implementations because of their nearest neighbor connections and usually space invariant connection weights. The scope of this study is motion detection via CNN architecture. There are three main methods of motion detection using CNN, namely Gabor type filters (frequency tuned filters), velocity tuned filters and time derivative CNN bandpass filters. All of these filters are analyzed and simulated in detail.