普适跟踪中的系统框架开发研究

Research on the Development of Ubiquitous Tracking Formal Framework

普适跟踪结合增强现实和普适计算的多传感器系统成为一个大规模复合跟踪网络,对各种异质源数据进行融合,有效综合利用多种跟踪技术,完成真实世界和虚拟世界的无缝结合和实时交互,是一个新的交叉研究领域。为克服增强现实跟踪平台的可重复利用性差的缺陷,研究普适跟踪中一个关键问题:一个开放式的可重用的系统框架的开发,由跟踪系统硬件抽象归纳出一个可重复利用的基于组件的数据流处理模型,模型对任意几何关系及任意时刻的测量都可以进行融合从而达到最优状态。系统框架,传感器的改变或增减不会对融合结果产生太大影响,复合跟踪系统的动态集成性提高。

Ubiquitous tracking integrates the multi - sensor systems of augmented reality and ubiquitous computing into a large - scale hybrid tracking network, fusing the data from heterogeneous sources automatically and dynamically. It provides the combination of real and virtual objects in a real environment and interaction between them in real time, which is a new interdiscipline research subject. The goal of this paper is to develop an open reusable framework of ubiquitous tracking, to overcome the weakness of classic augmented reality, that it uses static tracking platforms designed exactly for only one purpose and the reuse of tracking components is hard to achieve. In this paper, ubiquitous tracking tries to abstract from tracking hardware a reusable, component based model of data flow processing. With this formal framework, the arbitrary sensors are integrated dynamically and flexibly.