Human Silhouette Detection for Occlusion in (Mobile) AR Applications

This work focuses on the occlusions issue in Augmented Reality (AR) applications, in specific domains in which the AR application runs on a mobile handheld device, the scenario is supposed to be an unknown indoor environment, and the positions of the persons walking through it, are known. The aim of this work is to solve the problem of occlusions between virtual objects and persons moving within the camera view of the handheld device using the knowledge of the positions/shape information of the tracked persons. The challenge of this research, concerns the person’s silhouette extraction as foreground from the image frame, using one or more image processing algorithms