Object tracking has become one of the most important problem domains in computer vision during the last decade. It creates basics for many applications, such as automatic video surveillance, autonomous robotic systems, human-computer interfaces, augmented reality, and e-healthcare. A number of different tracking techniques have been developed. However, there are still some limitations that arise from problems such as illuminations and occlusion. In this paper, we review and experiment Kanade–Lucas–Tomasi (KLT) feature tracker. Then, we try to implement a simple object tracker algorithm based on background subtraction technique.