An intelligent vision system for motion detection using a neural network

This paper presents a neural network-based motion detector system of an object. The system consists of two components: a preprocessing and data compression part and a decision making subsystem that provides information about the motion of an object. A neural network is used as a decision making subsystem. The network is trained with a general object motion and tested on a specific unseen motion by the network. The training and testing errors were used to judge the performance of the network. The result is promising and shows the potential application of neural network to design a motion detection system.<>