Implementing object tracking in head-mounted video capture for eyegaze tracking

Head-mounted eyegaze tracking allows experimenters to record the eye movements of a wearer while he interacts with a real situated environment. Analysis of the eye movements however, is difficult since motion of the wearer’s head causes objects to move relative to the head-mounted video camera. The focus of this project is to implement object recognition and motion tracking in video recorded from the head-mounted camera. Motion in the recorded environment will be matched to user’s eye movements to determine which particular object a person is looking at.

Efficient Object Segmentation and Video Compression for Eye Tracking Applications

The main objective of this research project is to propose and develop efficient image segmentation methods for measuring the location of the center of the pupil in video frames captured by a real-time eye-tracker system, and to design an overall software program in order to investigate the performance of the developed methods in real situations. Based on the obtained results, we would be able to suggest which method would be the best choice for the proposed application.