光通信技术, 2023, 47 (1): 1, 网络出版: 2023-03-30  

基于随机森林算法的室内可见光指纹定位方法

Indoor visible light fingerprint positioning method based on random forest algorithm
作者单位
大连海事大学 信息科学技术学院, 辽宁 大连 116026
摘要
为进一步提高动态目标室内可见光定位追踪系统性能, 提出了一种基于随机森林(RF)算法的室内可见光指纹定位方法。利用发光二极管(LED)的光强信号作为特征构建指纹数据库, 应用指纹库中的数据训练决策树, 引入RF算法进行初始定位, 再通过卡尔曼滤波对初始位置估计进行优化, 从而获得更准确的定位轨迹。仿真结果表明: 在5 m×5 m×3 m的室内场景下, 通过所提定位方法能获得大部分采样点误差分布在4 cm之内的定位效果; 此外, 通过与不同室内可见光定位算法的性能进行对比, 验证了所提算法的技术优势。
Abstract
In order to further improve the performance of dynamic target indoor visible light location and tracking system, a indoor visible light fingerprint location method based on random forest(RF) algorithm was proposed. The light intensity signal of light-emitting diode(LED) was used as the feature to build a fingerprint database, and the data in the fingerprint database was used to train the decision tree. RF algorithm was introduced for initial positioning, and then Kalman filter was used to optimize the initial position estimation, so as to obtain a more accurate positioning trajectory. The simulation results show that in the indoor scene of 5 m×5 m×3 m, the proposed positioning method can obtain the positioning effect that most sampling points error distribution is within 4 cm. In addition, this paper verifies the technical advantages of the proposed algorithm by comparing the performance of different indoor visible light positioning algorithms.
参考文献

[1] SWASTIKASARI M M, SEDIYONO E, ARDJO A S. Design of E-KOST: an android-based mobile application using location based service(Study case:SWCU'S students)[C]//IEEE. proceedings of International Co-nference on Innovative and Creative Information Technology(ICITech). Salatiga: IEEE, 2017: 1-9.

[2] PEI L, CHEN R, LIU J, et al. Inquiry-based bluetooth indoor positioning via RSSI probability distributions[C]//IEEE. proceedings of Second Inter-national Conference on Advances in Satellite and Space Communications. Athens: IEEE, 2010: 151-156.

[3] YAO W, MA L. Research and application of indoor positioning method based on fixed infrared beacon[C]//IEEE. proceedings of 37th Chinese Control Conference(CCC). Wuhan: IEEE, 2018: 5375-5379.

[4] 万伟雄, 李晓东. 基于EKPF的超宽带室内动态目标定位算法[J]. 信息与电脑(理论版), 2021, 33(24): 39-42.

[5] MANZOOR F, YI H, MENZEL K. Passive RFID-based indoor position-ing system, an algorithmic approach[C]//IEEE. proceedings of International Conference on RFID-Technology and Applications. Guangzhou: IEEE, 2010: 112-117.

[6] 张亚鹏. 基于位置指纹的消防员室内定位系统设计与仿真[D]. 西安: 西安科技大学, 2019.

[7] YANG S H, JEONG E M, KIM D R, et al. Three-dimensional localization based on visible light optical wireless communication[J]. World Allergy Organization Journal, 2013, 7(1): 468-469.

[8] 曹燕平, 李晓记, 胡云云. 基于可见光指纹的室内高精度定位方法[J]. 激光与光电子学进展, 2019, 56(16): 16-21.

[9] CHEN L, LAIN J. Two-dimensional indoor visible light positioning using smartphone image sensor[C]//IEEE. proceedings of International Conference on Consumer Electronics-Taiwan(ICCE-TW). Taichung: IEEE, 2018: 1-2.

[10] 党宇超, 曹阳, 彭晓峰, 等. 多LED照明节点的室内可见光定位方法研究[J]. 光通信技术, 2020, 44(2): 1-5.

[11] 郭琛, 邵建华, 柯炜, 等. 基于指纹的可见光室内定位系统融合算法[J]. 南京师范大学学报(工程技术版), 2019, 19(1): 58-64.

[12] 许浩, 王旭东, 吴楠. 基于卷积神经网络的室内可见光指纹定位方法[J]. 激光与光电子学进展, 2021, 58(17): 227-234.

[13] 梁哲豪, 石磊, 唐杰, 等. 室内可见光指纹定位系统中WKNN算法改进研究[J]. 激光与光电子学进展, 2022, 1(1): 1-11.

[14] 赵楚韩, 张洪明, 宋健. 基于指纹的室内可见光定位方法[J]. 中国激光, 2018, 45(8): 202-208.

[15] 刘帅, 王旭东, 吴楠. 一种基于卷积神经网络的CSI指纹室内定位方法[J]. 工程科学学报, 2021, 43(11): 1512-1521.

[16] MAUNG N, LWI B Y, THIDA S. An enhanced RSS finger printing-based wireless indoor positioning using random forest classifier[C]//IEEE. proceedings of International Conference on Advanced Information Technologies(ICAIT). Yangon: IEEE, 2020: 59-63.

曲佳, 王旭东, 吴楠, 许浩. 基于随机森林算法的室内可见光指纹定位方法[J]. 光通信技术, 2023, 47(1): 1. QU Jia, WANG Xudong, WU Nan, XU Hao. Indoor visible light fingerprint positioning method based on random forest algorithm[J]. Optical Communication Technology, 2023, 47(1): 1.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!