23-10-2009, 04:09 PM
[attachment=130]
field of computer vision, tracking and motion estimation of 3D objects take on a significant place. Object tracking is the process of identifying an object of interest, finding position of that object, and following the motion of the object. A lot of applications, especially in robotics, transport or in the military domain, require an accurate knowledge of localization and motion of the objects in the scene. Many works were carried out on the subject, from which emerge 3 classes of methods. Feature-based methods aim at extracting characteristics such as points, line segments from image sequences, tracking stage is then ensured by a matching procedure at every time instant. Differential methods are based on the optical flow computation, i.e. on the apparent motion in image sequences, under some regularization assumptions. The third class uses correlation to measure interimage displacements. Selection of a particular approach largely depends on the domain of the problem. The seminar takes a brief overview of important steps in object tracking. It also takes a look at certain methods employed by various researchers to solve particular problems in the field. The basic objective of this discussion is to understand what object tracking is and what are the fundamental operations involved in the process of tracking.
