Visual Immersion

Computer vision is a field of artificial intelligence (AI) that enables computational systems to interpret and understand the visual world. In virtual reality (VR) and augmented reality (AR) systems and applications, computer vision techniques have become ubiquitous and indispensable. In VR and AR applications, key milestones include the development of marker-based tracking systems, which allowed for the precise positioning of virtual objects in real-world environments. This chapter explores the fundamental principles and advanced techniques of computer vision that power immersive experiences in virtual and augmented reality systems. The selection of cameras in virtual and augmented reality systems is crucial for achieving high-quality, immersive experiences. Monocular cameras are single-lens cameras commonly used in basic imaging applications. Depth cameras are essential for gesture recognition, 3D scanning, and room-scale VR and AR experiences. 360-degree cameras capture panoramic images or videos covering a full 360-degree field of view.