WaveApps   About Us / WSA / Our Interests / Cloud Computing Augmented Reality / Projects Contacts   Ru  

Augmented Reality

Augmented reality – with this concept are connected every possible variations which result the combination of reality with any virtual elements. Hence improving day by day technologies and I/O devices represent the fine perspective and fertile environment both for experimental functions, and for deployment of high-grade, shaking on due to convenience and usability services and applications. All the largest manufacturers of mobile devices have provided (or are at a final stage of assemblage) tools, instrumental means and techniques, allowing to develop the most interesting concepts with augmented reality usage.

In line with other modern invents and technologies, the augmented reality allows to look at habitual things in a new way.

A key measure of AR (Augmented Reality) systems is how realistically they integrate augmentations with the real world. The software must derive real world coordinates, independent from the camera, from camera images. That process is called image registration.

Image registration uses different methods of computer vision, mostly related to video tracking. Many computer vision methods of augmented reality are inherited from visual odometry. Usually those methods consist of two parts. First detect interest points, or fiduciary markers, or optical flow in the camera images. First stage can use feature detection methods like corner detection, blob detection, edge detection or thresholding and/or other image processing methods.

The second stage restores a real world coordinate system from the data obtained in the first stage. Some methods assume objects with known geometry (or fiduciary markers) present in the scene. In some of those cases the scene 3D structure should be precalculated beforehand. If part of the scene is unknown simultaneous localization and mapping (SLAM) can map relative positions. If no information about scene geometry is available, structure from motion methods like bundle adjustment are used. Mathematical methods used in the second stage include progective (epipolar) geometry, geometric algebra, rotation representation with exponential map, kalman and particle filters, nonlinear optimization, robust statistics.

/Some another direction:  Cloud Computing/