New Approach for Detecting and Tracking a Moving Object

Abstract

This article presents the implementation of a tracking system for a moving target using a fixed camera. The objective of this work is the ability to detect a moving object and locate their positions. In picture processing, tracking moving objects in a known or unknown environment is commonly studied. It is based on invariance properties of objects of interest. The invariance can affect the geometry of the scene or the objects. The proposed approach is composed of several steps; the first is the extraction of points of interest in the current image. Then, these points will be tracked in the following image by using techniques for calculating the optical flow. After this step, the static points will be removed to focus on moving objects, That is to say, there is only the characteristic points belonging to moving objects. Now, to detect moving targets using images of the video, the background is first extracted from the successive images. In our approach, a method of the average values of every pixel has been developed for modeling background. The last step which stays before switching to tracking moving object is the segmentation which allows identifying every moving object. And by using the characteristic points in the previous steps.