基于空间分割的无线室内定位方法研究

Indoor localization has become of great importance to a wide range of applications in the era of mobile computing. Current mainstream solutions rely on Received Signal Strength (RSS) of wireless signals as fingerprints to infer locations. However, it is still an open problem to construct a representative fingerprint database efficiently. Though pioneering efforts have resorted to storing finer-grained information, adaptive sampling/reporting strategy, and crowdsourcing the labor to the public, they all rely on human participation, which introduces extra costs and constraints, and thus degrades their practicality. In this project, we will propose a human-sampling-free localization framework for mobile devices. The basic idea of framework is to automatically generate a fingerprint database through space partition, of which each cell is fingerprinted by its maximum influence APs. Based on this robust location indicator, fine-grained localization can be achieved by a discretized particle filter utilizing sensor data fusion. We devise techniques for CIVD-based field division, discretized graph-based particle filter, and build a prototype that runs on commodity mobile smart devices. The research will have great significance that it provides a comparable performance to classic RSS-based methods while relieving it of prior human participation.

随着移动计算的兴起，室内定位的应用越来越广泛。主流方案依赖于无线信号的接收信号强度作为指纹来推断定位。然而，有效地构建具有代表性指纹数据库仍是开放问题。虽然先前的成果采用存储更细粒度信息，适应性抽样、报告策略和众包等各种形式来构建指纹数据库，其共同特征是依赖人工参与，引入额外的成本和约束从而降低其实用性。本项目拟提出一种基于移动设备的无人工参与采样的定位框架。框架的基本思想是通过空间分割自动生成指纹数据库，其中每个单元通过其最大影响APs作为指纹。基于这种鲁棒的位置指纹信息，细粒度定位拟结合多传感器数据融合的离散粒子滤波来实现。我们提出基于CIVD的空间分割方法和基于图形的离散粒子滤波方法，并构建在商用移动智能设备上运行的原型。与经典基于RSS室内定位方法相比，增强其定位性能并减轻人工参与的约束。本研究为基于WiFi室内定位提供一种新的方法和技术手段，为室内定位技术成熟推进具有重要价值。

基于无线信号的定位技术是室内定位主流技术，利用无线信号的接收信号强度作为指纹实现定位是主流研究方向。项目围绕基于空间分割的自动生成指纹数据库机制和基于空间分割图和多传感器数据融合的定位机制开展研究，提出一种自动指纹数据库构造的室内定位方案。在获取室内空间结构和AP位置的情形下，构造无线WiFi信号的室内定位的指纹数据库所花费的人工费用减低了近60%。定位精度在1-1.5m，在工程应用上满足日常的室内定位和导航。并自主开发一套室内定位系统，将其部署在郑州高新区、皖西学院和清华大学软件学院办公区，其实用效果较好。与经典基于RSS室内定位技术相比，增强了定位性能并减少了人工参与近50%，为室内定位技术趋向成熟推进了一步。为了更好地将室内定位研究成果进行转化和应用，下一步将室内定位与传统行业融合，争取在智慧消防、智慧导览领域有突破性进展。