A Multi-ring Color Fiducial System and A Rule-Based Detection Method for Scalable Fiducial-tracking Augmented Reality
A Multi-ring Color Fiducial System and A Rule-Based Detection Method for Scalable Fiducial-tracking Augmented Reality
复制标题
用于可扩展基准跟踪增强现实的多环彩色基准系统和基于规则的检测方法
DOI：
--
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
U. Neumann
中科院分区：
文献类型：
--
作者：
Youngkwan Cho;Jongweon Lee;U. Neumann
在增强现实（AR）中，用户可以看到虚拟世界以及真实的世界。为了避免虚拟世界和真实的世界之间的配准问题，用户在两个世界中的姿势应该完全相同。基准跟踪AR是一种有吸引力的配准问题的方法，但大多数开发的基准跟踪AR系统具有非常有限的跟踪范围，并需要精心准备的环境，特别是照明条件。为了在大规模应用中提供宽视图和详细视图，AR系统应该在变化的光照条件下具有可扩展的跟踪能力。在本文中，我们提出了多环彩色基准系统和光不变的基准检测方法可扩展的基准跟踪AR系统。我们分析了最佳的环宽度，并开发公式，以获得最佳的基准集与系统特定的输入。我们提出了一种光不变的圆形基准检测方法，利用基准和它们的背景之间的关系分割图像的区域。我们的工作提供了一个简单方便的方法来实现广域跟踪的AR。
In Augmented Reality (AR), a user can see a virtual world as well as a real world. To avoid the registration problem between the virtual world and the real world, the user’s pose in both worlds should be exactly the same. Fiducial tracking AR is an attractive approach to the registration problem, but most of the developed fiducial tracking AR systems have very limited tracking ranges and require carefully prepared environments, especially lighting conditions. To provide for wide views and detailed views in large-scale applications, an AR system should have a scalable tracking capability under varying light condition. In this paper, we propose multi-ring color fiducial systems and a light-invariant fiducial detection method for scalable fiducial tracking AR systems. We analyze the optimal ring width, and develop formulas to obtain the optimal fiducial set with system specific inputs. We present a light-invariant circular fiducial detection method that uses relations among fiducials and their backgrounds for segmenting regions of an image. Our work provides a simple and convenient way to achieve wide-area tracking for AR.