Cecilia Torralbo Gimeno

MSc Diploma Project


Camera tracking using natural feature point matching for augmented reality


Cecilia Torralbo Gimeno (Exchange student from UPM)


Prof. T. Ebrahimi
Assistant: David Marimon






In recent years, there has been a growing interest in the problem of matching natural features. Establishing the correspondence between lines or points between two or more images is at the core of applications such as simultaneous localisation and mapping (robotics) or augmented reality (human-machine interaction). Our system tracks features points using geometrically known patterns (markers) and camera pose estimation based on this marker. The objective of this project is to improve the tracking of the corners of the marker. For this purpose, the student will use an algorithm created at our lab. Together with this purpose the student will extend the tracking of corners to that of natural feature points around the marker’s environment. Several experiments have to be performed in order to asses the application of our tracking technique for Augmented Reality purposes.