Markerless real-time Object Detection and Tracking

Abstract

Augmented reality (AR) is an increasingly recognized paradigm of information visualization that merges a computergenerated virtual object onto a real scene to visually augment reality. With recent and continued increases in computing power, and advances in the field of computer graphics, realistic augmented reality environments can now offer inexpensive and powerful solutions in a whole range of training, simulation and leisure applications. One key challenge to maintaining convincing augmentation, and therefore tracking real objects from natural features, is decoupling the rendering process of the augmented information from the displaying system, by which we can augment the scene using computationally expensive rendering techniques that requires high computational power.