Abstract

This paper presents an algorithm to track moving objects in a real time video and to store co-ordinate values of the centroid of those objects in a vector for future use. Finally paths of those moving objects are plotted using the stored co-ordinate values. The proposed algorithm in this paper is based on background subtraction where tracking objects is performed in a sequence of video frames and its processing mainly consists of two main stages: isolation of objects from background in each frames and association of objects in successive frames to trace them. In this approach, moving objects can be tracked accurately, then an accurate record of their motion can be made and their path of movement can be plotted. Such tracking system is required in sensitive areas such as bank, departmental stores, parking lots and country border to determine whether one or more human beings engaged are suspicious or under criminal activity. Experimental results, which demonstrate the system’s performance, are also shown in this paper.

Keyword

Object Tracking, Moving Objects, Reference frame, Current frame, Background Subtraction, Inter-frame Differentiation(IFD), Laplacian Filter.

Cite this article

Refference