Mapping Virtual Objects into Real Scene

摘要

This paper presents a computer vision based framework for mapping virtual objects into a real scene captured by a video camera. Virtual objects are objects contained in a virtual scene stored in a virtual database. This technology has a number of applications including visually-guided robotic navigation, surveillance, military training and operation. The fundamental problem involves several challenging research issues including finding corresponding points between the virtual and the real scene and camera calibration. This paper focuses on our research in selecting reliable control points for the construction of intrinsic and extrinsic camera parameters, which is a vital portion for mapping virtual objects into a real scene.