Visual tracking in unconstrained environments is very challenging due to the existence of several sources of varieties such as changes in appearance, varying lighting conditions, cluttered background, and frame-cuts.

One of the key requirements for an augmented reality system is a tracking system that determines the user's viewpoint accurately.

This project addresses several research topics related to virtual reality, augment reality, geometry modeling, motion tracking, and visualization.

Nowadays, the importance of the automatic face detection and tracking system has increased as it is needed for video surveillance and new user interfaces.

The project addresses the problem of visual motion analysis by establishing a voting-based computational framework.

Human body motion tracking and analysis has received a significant amount of attention in the computer vision research community in the past decade.

Imagery data is an important component of multimedia content and appears commonly in the Internet domain, TV programs and movies.

A real time 3D human body reconstruction is performed using two to four synchronized cameras.

This project aims to investigate human capacity to decode the communication delivered via body action in virtual human representations (avatars/agents).

Quality of service (QoS) in streaming of continuous media over the Internet is still poor and inconsistent.