Artificial neural network based object tracking

Abstract

Intelligent space is a space which has distributed sensory intelligence and is equipped with actuators. The various devices of sensory intelligence cooperate with each other autonomously, and the whole space has high intelligence, where we can easily interact with computers and robots, and get useful services from them. The most important sensors in intelligent space are video cameras. This paper presents an artificial neural network for tracking objects moving in front of a camera. The task is performed by a biologically inspired artificial neural network, which is a first step toward cognitive systems and vision. An adaptive neural based image memory and a neural matching system are used. The proposed neural structure can be embedded in an analog neural hardware to produce a real time solution for camera motion control in object tracking that is faster and more robust than existing solutions.