Robust Moving Object Detection from a Moving Video Camera Using Neural Network and Kalman Filter

Detecting motion of objects in images, while the camera is moving, is a complicated task. In this paper, we propose a novel method to effectively solve this problem by using Neural Networks and Kalman Filter. This technique uses movement parameters of camera to overcome problems caused by error in image processing outputs. We implemented this technique in the MRL Middle Size Soccer Robots. Experimental results are presented and 2.2% achieved error suggests that the combined approach performs significantly better than traditional techniques.