BS in Computer Engineering
Computer Engineering Department
Due to the advancements in mobile computing hardware and the inclusion of cameras in many computing platforms, augmented reality systems have become widely available. This paper presents a real-time implementation of a novel markerless augmented reality algorithm which is able to track two-dimensional affine regions without a priori information of the environment or computing a world model. The implementation consists of the MAR library; a modular software library which performs the region detection, identification, and tracking; and the Lighthouse application; a program which uses the MAR library to allow the user to augment scenes viewed from a camera. The algorithm used in this paper is able to track textured affinely invariant planar regions using the maximally stable extremal region (MSER) detector to detect the regions and scale-invariant feature transform (SIFT) detector to identify the regions. If three or more points from the region are matched across frames, an affine transformation is calculated which can be used to augment the scene by transforming a two-dimensional virtual image, causing it to appear to be stationary with respect to the region being tracked. Testing found that the system is robust at tracking translation, scale, and rotational changes in regions at a frame-rate adequate for real-time applications and is able to handle changes in angle and illumination.