| 摘要: |
| 高精度室内定位有着广阔的市场前景.针对传统的WKNN室内定位方法所面临的在处理面积较大目标区域时，位置估计结果跳动跨度较大、精度不高等问题，提出了一种基于空间特征分区和前点约束的WKNN室内定位方法.该方法通过将面积较大的目标区域按其空间特征划分为多个分区，解决了指纹数据库无法实现全域覆盖的问题；又通过考虑行人在相邻时刻所处位置之间的空间约束关系，缩小了参考点的候选范围，很好地提升了位置估计的平顺性.大量真实环境下室内定位实验的结果表明，该方法可以有效地解决大面积目标区域内的室内定位问题；且与传统方法相比，定位精度大幅度提升. |
| 关键词: 室内定位 WiFi定位 空间分区 前点约束 WKNN |
| DOI：10.13328/j.cnki.jos.005569 |
| 分类号:TP393 |
| 基金项目:国家重点研发计划（2018YFF0216004） |
|
| WKNN Indoor Positioning Algorithm Based on Spatial Characteristics Partition and Former Location Restriction |
|
YANG Hai-Feng1, ZHANG Yong-Bo1,2, HUANG Yu-Liang1, FU Hui-Min1
|
|
1.Research Center of Small Sample Technology, Beihang University, Beijing 100191, China;2.Ningbo Institute of Technology, Beihang University, Ningbo 315800, China
|
| Abstract: |
| High-precision indoor positioning has broad market prospect. In traditional indoor positioning algorithm based on WKNN, it is difficult to deal with a target space of large area, and its position estimation results face the matters of inaccurate and instability as rebounding or clustering. To solve these problems, this study proposes a WKNN indoor positioning algorithm based on spatial characteristics partition and former location restriction. According to the proposed algorithm, target space of large area is divided into multiple partitions by its spatial characteristics, which solved the problem that one fingerprint database cannot achieve total coverage. It also introduced the restricted relationship between the former and the present position, which improved the quality of candidate reference points and thus improved the smoothness of the estimation results. Results of a large number of indoor positioning experiments in real environment show that the proposed algorithm can effectively improve the indoor positioning accuracy when compared with the traditional WKNN. |
| Key words: indoor positioning WiFi positioning space partition former location restriction WKNN |
