Spatiotemporal computation with a general purpose analog neural computer: real-time visual motion estimation

Abstract

An analog neural network implementation of spatiotemporal feature extraction for real-time visual motion estimation is presented. Visual motion can be represented as an orientation in the space-time domain. Thus, motion estimation translates into orientation detection. The spatiotemporal orientation detector discussed is based on Adelson and Bergen's model with modifications to accommodate the computational limitations of hardware analog neural networks. The analog neural computer used here has the unique property of offering temporal computational capabilities through synaptic time-constants. These time-constants are crucial for implementing the spatiotemporal filters. Analysis, implementation and performance of the motion filters are discussed. The performance of the neural motion filters is found to be consistent with theoretical predictions and the real stimulus motion.<>