Faculty of Engineering and Natural Sciences
Object tracking is a significant task within field of computer vision. Tracking can be defined as the problem of estimating the trajectory of an object in the image plane as it moves around a scene. The applications of visual tracking are far-reaching including automated surveillance, human-computer interaction, traffic monitoring, vehicle navigation and motion-based recognition. However, it is a complex task due to non-rigid nature of objects, complex object motion, partial and full object occlusions, complex object shapes and noise in images. A robust tracking methodology has to cope with all of these difficulties. A large number of tracking methods for object tracking have been proposed in the literature. These approaches differ from each other based on the formulation of tracking. In this talk, some tracking algorithms and their performances will be presented.
March 18, 2009, 13:40,