考虑接收机姿态的双ELM室内可见光定位方法

窦道飞; 张素阳

您当前的位置：

首页 >

文章列表页 >

考虑接收机姿态的双ELM室内可见光定位方法

光学传感与测量 | 更新时间：2026-07-23

- 考虑接收机姿态的双ELM室内可见光定位方法
- Indoor visible light positioning based on dual ELM considering receiver orientation
- 光学技术 2026年52卷第4期页码：473-480
- 作者机构：
  
  1.中国铁道科学研究院集团有限公司通信信号研究所，北京 100081
  2.国家铁路智能运输系统工程技术研究中心，北京 100081
  3.国铁通信信号（北京）有限公司，北京 100081
  4.通信信号基础设施智能运维铁路行业工程研究中心，北京 100081
- 作者简介：
  
  窦道飞（1977— ），男，副研究员，从事轨道交通信号系统安全测试的研究。doudaofei_CARS@163.com
- 基金信息：
  
  国家铁路智能运输系统工程技术研究中心开放课题(RITS2025KF08)
- DOI：
  中图分类号： TP394.1;TH691.9
- 收稿：2026-04-10，
  
  修回：2026-05-14，
  
  录用：2026-05-20，
  
  网络首发：2026-07-23，
  
  纸质出版：2026-07-20
- 稿件说明：
移动端阅览
窦道飞,张素阳.考虑接收机姿态的双ELM室内可见光定位方法[J].光学技术,2026,52(04):473-480.

DOU Daofei,ZHANG Suyang.Indoor visible light positioning based on dual ELM considering receiver orientation[J].OPTICAL TECHNIQUE,2026,52(04):473-480.
窦道飞,张素阳.考虑接收机姿态的双ELM室内可见光定位方法[J].光学技术,2026,52(04):473-480. DOI：

DOU Daofei,ZHANG Suyang.Indoor visible light positioning based on dual ELM considering receiver orientation[J].OPTICAL TECHNIQUE,2026,52(04):473-480. DOI：

摘要

针对接收机姿态动态变化引发接收信号特征畸变，导致室内可见光定位精度下降的问题，提出一种全局ELM（极限学习机）粗略定位与局部ELM精确定位相结合的室内可见光定位方法。首先，将接收信号强度与接收机姿态信息作为联合指纹特征，建立指纹特征与物理位置之间的映射关系，离线构建全局指纹数据库；然后，利用全局指纹数据库训练全局ELM模型，粗略确定待测接收机位置；接着，筛选指纹样本，自适应构建局部指纹数据库，并结合接收机实时姿态信息，对局部指纹数据进行方向一致性校正与更新；最后，利用局部指纹数据库训练局部ELM模型，实现在线精确定位。实验结果表明，所提方法在维持较高计算效率的同时，增强了接收机姿态变化的适应能力，可为室内可见光定位提供一种定位精度高、鲁棒性强的参考方案。

Abstract

To solve the problem of accuracy decline of indoor visible light positioning resulting from the distortion of received signal characteristics with dynamic changes of receiver orientation

a practical approach to indoor visible light positioning has been proposed

which combines the global ELM （extreme learning machine） for approximate positioning with local ELM for precise positioning. Firstly

received signal strength and receiver orientation information are used as joint fingerprint features to establish the mapping relationship between fingerprint features and physical position

and a global fingerprint database is constructed offline. Then

the global fingerprint database is adopted to train the global ELM model to roughly determine the position of the receiver under test. Next

fingerprint samples are selected to adaptively construct the local fingerprint database

which is calibrated and updated for direction consistency using the real-time information of receiver orientation. Finally

the local fingerprint database is utilized to train the local ELM model to achieve the online precise position information. Experimental results demonstrate that the proposed method not only maintains high computational efficiency but also enhances the adaptability to the variation of receiver orientation

which can provide a highly accurate and strongly robust reference solution for indoor visible light positioning.

关键词

Keywords

references

Wang R , Niu G , Cao Q , et al . A survey of visible light communication based indoor positioning systems [J ] . Sensors , 2024 , 24 （ 16 ）: 5197 .

Xue J , Zhang J , Gao Z , et al . Enhanced WiFi CSI fingerprints for device-free localization with deep learning representations [J ] . IEEE Sensors Journal , 2022 , 23 （ 3 ）: 2750 — 2759 .

Wu C , Wong I C , Wang Y , et al . Experimental study of bluetooth indoor positioning using rss and deep learning algorithms [J ] . Mathematics , 2024 , 12 （ 9 ）: 1386 .

Gomes E L , Fonseca M S P , Lazzaretti A E , et al . Sliding window, hierarchical classification, regression, and genetic algorithm for RFID indoor positioning systems [J ] . Expert Systems with Applications , 2024 , 238 : 122298 .

Mäkelä M , Olkkonen M K , Kirkko-Jaakkola M , et al . Ubiquitous UWB ranging error mitigation with application to infrastructure- free cooperative positioning [J ] . IEEE Journal of Indoor and Seamless Positioning and Navigation , 2024 , 2 : 143 — 150 .

张雁鹏 , 张容容 , 张宏雁 , 等 . 基于扩展状态观测器的可见光成像通信列车定位光源自适应获取方法 [J ] . 光学学报 , 2025 , 45 （ 11 ）: 1111001 .

Zhang Yanpeng , Zhang Rongrong , Zhang Hongyan , et al . Adaptive light source acquisition method for train positioning based on extended state observer in visible light imaging communication [J ] . Acta Optica Sinica , 2025 , 45 （ 11 ）: 1111001 .

Rekkas V P , Iliadis L A , Sotiroudis S P , et al . Artificial intelligence in visible light positioning for indoor IoT: A methodological review [J ] . IEEE Open Journal of the Communications Society , 2023 , 4 : 2838 — 2869 .

王创世 , 陈勇 , 刘焕淋 , 等 . 基于注意力机制的可见光定位单元模型复制 [J ] . 中国激光 , 2024 , 51 （ 8 ）: 0806002 .

Wang Chuangshi , Chen Yong , Liu Huanlin , et al . Model replication of visible light positioning units based on attention mechanism [J ] . Chinese Journal of Lasers , 2024 , 51 （ 8 ）: 0806002 .

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 ）: 1706008 .

Xu Hao , Wang Xudong , Wu Nan . Indoor visible light fingerprint positioning scheme based on convolution neural network [J ] . Laser & Optoelectronics Progress , 2021 , 58 （ 17 ）: 1706008 .

于建勇 , 胡晓莉 , 王倩 , 等 . 基于指纹修正与网络融合算法的可见光定位系统应用 [J ] . 光学学报 , 2025 , 45 （ 16 ）: 1606005 .

Yu Jianyong , Hu Xiaoli , Wang Qian , et al . Application of visible light positioning system based on fingerprint correction and network fusion algorithms [J ] . Acta Optica Sinica , 2025 , 45 （ 16 ）: 1606005 .

马玉磊 , 张兵 . 基于深度学习的可见光通信系统室内三维定位 [J ] . 光学技术 , 2024 , 50 （ 2 ）: 201 .

Ma Yulei , Zhang Bing . Deep learning based indoors dimensional positioning for visible light communication system [J ] . Optical Technology , 2024 , 50 （ 2 ）: 201 .

许一祎 , 冯莉芳 , 薛卓 . 基于矩阵分解与深度神经网络的室内定位方法 [J ] . 光学学报 , 2025 , 45 （ 10 ）: 1010001 .

Xu Yiyi, Feng Lifang, Xue Zhuo, Indoor positioning system based on matrix factorization and deepneural networks [J ] . Acta Optica Sinica , 2025 , 45 （ 10 ）: 1010001 .

杜聪 , 邵建华 , 杨薇 , 等 . 网格搜索法优化的支持向量机室内可见光定位 [J ] . 激光杂志 , 2021 , 42 （ 3 ）: 104 — 109 .

Du Cong , Shao Jianhua , Yang Wei , et al . Indoor visible light positioning based on support vector machine optimized by grid search [J ] . Laser Journal , 2021 , 42 （ 3 ）: 104 — 109 .

贾科军 , 牛振 , 于凯 , 等 . 基于SSA-ELM神经网络的室内可见光定位系统 [J ] . 光通信研究 , 2025 , 51 （ 1 ）: 230154 .

Jia Kejun , Niu Zhen , Yu Kai , et al . Indoor visible light positioning system based on SSA-ELM neural network [J ] . Optical Communication Research , 2025 , 51 （ 1 ）: 230154 .

曹海锋 , 王晓亮 . 基于深度学习与RSS滤波的可见光室内定位算法 [J ] . 光学技术 , 2024 , 50 （ 3 ）: 361 .

Cao Haifeng , Wang Xiaoliang . Indoor visible light positioning algorithm based on deep learning and RSS filtering [J ] . Optical Technology , 2024 , 50 （ 3 ）: 361 .

Liu R , Liang Z , Li W . Fingerprint-basedv visible light positioning using adaptie WKNN algorithm with reliable reference nodes [J ] . IEEE Transactions on Instrumentation and Measurement , 2025 , 74 : 5506609 .

Deng L , Fan Y , Zhao Q . Indoor visible light tilt-resilient positioning based on RSS fingerprint self-transferability [J ] . IEEE Photonics Technology Letters , 2025 , 37 （ 12 ）: 679 — 682 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于对偶学习的高效可见光通信非线性均衡器

基于双光楔的长波像方扫描光学系统设计

基于单目旋转视觉的几何公差评定方法研究

高校公共实验平台共享管理与运行机制研究

一种基于多光谱偏振信息融合的条纹像自适应重构方法