. Vol.16 No.2 , July - December 2013.

CAMSHIFT-based Algorithm for Multiple Object Tracking

Sorn Sooksatra and Toshiaki Kondo

Abstract

       This paper presents a technique for object tracking by using CAMSHIFT algorithm that tracks an object based on color. We aim to improve the CAMSHIFT algorithm by adding a multiple targets tracking function [1].When one object is selected as a template, it will search objects that have the same hue value and shape by shape recognition. Hence, the inputs of the algorithm are hue values and shape of the object. When all objects are absent in the frame, the algorithm will search whole frame to find most similar-looking objects and track them. The important task of the object tracking is to separate a target from background or frame in some cases where the noise is present in the tracking frame. Then object identification method was added to the algorithm for filtering the noise and counting numbers of objects to make decide how many targets track.

Keywords: CAMSHIFT, Multiple target, Object tracking, Shape recognition

Download Full Paper.