基于深度学习的非视距可见光定位系统

黄伟杰; 林邦姜; 丁永棋; 骆加彬; 黄天明

doi:10.13756/j.gtxyj.2024.230091

您当前的位置：

首页 >

文章列表页 >

基于深度学习的非视距可见光定位系统

无线通信技术 | 更新时间：2024-12-05

- 基于深度学习的非视距可见光定位系统
- Non-line-of-sight Visible Light Positioning System based on Deep Learning
- 光通信研究 2024年第6期页码：23009101-23009107
- 作者机构：
  
  1.福建农林大学　机电工程学院，福州　350100
  2.中国科学院海西研究院　泉州装备制造研究中心，福建　泉州　362200
- 作者简介：
  
  黄伟杰（1999-），男，福建莆田人。硕士，主要研究方向为室内可见光定位。
  林邦姜，副研究员，硕士生导师。E-mail：linbangjiang@fjirsm.ac.cn
- 基金信息：
  
  欧盟科研计划基金资助项目(CA19111);福建省自然科学基金资助项目(2022J01499);福建省住房和建设厅科技发展资助项目(2022K52);区域光纤通信网与新型光通信系统国家重点实验室开放基金资助项目
- DOI：10.13756/j.gtxyj.2024.230091
  中图分类号： TN929.1
- 纸质出版日期：2024-12-10，
  
  收稿日期：2023-08-13，
  
  修回日期：2023-08-29，
- 稿件说明：
移动端阅览
黄伟杰，林邦姜，丁永棋，等. 基于深度学习的非视距可见光定位系统[J]. 光通信研究，2024(6):230091.

Huang W J, Lin B J, Ding Y Q, et al. Non line of sight Visible Light Positioning System based on Deep Learning [J]. Study on Optical Communications, 2024(6):230091.
黄伟杰，林邦姜，丁永棋，等. 基于深度学习的非视距可见光定位系统[J]. 光通信研究，2024(6):230091. DOI： 10.13756/j.gtxyj.2024.230091.

Huang W J, Lin B J, Ding Y Q, et al. Non line of sight Visible Light Positioning System based on Deep Learning [J]. Study on Optical Communications, 2024(6):230091. DOI： 10.13756/j.gtxyj.2024.230091.

摘要

【目的】

可见光定位（VLP）技术在提供低成本、高精度的室内位置服务方面极具潜力，受到越来越多的关注。然而，传统的VLP系统依赖于直接视距（LOS）路径，在有障碍物遮挡的情况下无法正常进行工作。

【方法】

针对这一问题，文章提出了一种基于深度学习的非视距（NLOS）VLP系统，该系统创新地利用一次反射光来进行VLP，克服了LOS路径被遮挡的挑战，提高了VLP系统的鲁棒性。考虑到反射光信号信噪比较低，通过传统的图像检测方法来提取发光二极管（LED）光斑的准确度较低并且环境适应性较差，导致NLOS VLP的定位精度下降。因此，文章所提系统通过深度学习模型U型网络（U-Net）来检测LED光斑，通过采集不同环境下的数据集进行训练，U-Net模型表现出了很高的准确度和环境适应性，从而改善了系统的性能。在此基础上，文章所提系统利用三点透视几何（P3P）算法来估计接收端的三维（3D）位置。

【结果】

文章搭建了1.84 m×1.84 m×1.96 m的立体空间模拟室内环境，用于室内定位实验，实验结果表明，在NLOS路径下，系统3D平均误差和均方根误差（RMSE）分别为16.09和17.18 cm，二维（2D）定位误差小于21 cm时有90%的置信度，3D定位误差小于24 cm时有90%的置信度。

【结论】

文章所提系统具有较高的精度和鲁棒性，能够满足室内大多数应用场景的定位需求。

Abstract

【Objective】

Visible Light Positioning (VLP) technology has gained increasing attention due to its potential for providing low-cost

high-precision indoor location services. However

traditional VLP systems rely on Line-of-Sight (LOS) paths and cannot function properly when obstructed by obstacles.

【Methods】

To address this issue

we propose a novel Non-Line-of-Sight (NLOS) VLP system based on deep learning. This system utilizes reflected light for VLP

overcoming the challenge of LOS obstruction and enhancing the robustness of the VLP system. Considering the low signal-to-noise ratio of the reflected light

the accuracy and adaptability of conventional image detection methods for extracting Light Emitting Diode (LED) spots are limited

resulting in reduced positioning accuracy for NLOS VLP. Therefore

the proposed system employs the deep learning model U-shaped Network (U-Net) to detect LED spots

which demonstrates high accuracy and adaptability after being trained on datasets collected from various environments

thereby improving the system performance. In the simulation

the system estimates the Three-Dimensional (3D) position of the receiver using the Perspective-Three-Point (P3P) algorithm.

【Results】

This paper constructed a 1.84 m×1.84 m ×1.96 m 3D space simulating an indoor environment for indoor positioning experiments. The experimental results show that under NLOS paths

the system's 3D mean error and Root Mean Square Error (RMSE) are 16.09 and 17.18 cm

respectively. The Two-Dimensional (2D) positioning error has a 90% confidence level at less than 21 cm

and the 3D positioning error has a 90% confidence level at less than 24 cm.

【Conclusion】

The proposed system has high positioning accuracy and robustness

which can meet the positioning requirements of most indoor applications.

关键词

可见光定位非视距深度学习三点透视几何算法

Keywords

VLPNLOSdeep learningP3P algorithm

references

Hassan N U, Naeem A, Pasha M A, et al. Indoor Positioning Using Visible LED Lights[J]. ACM Computing Surveys, 2015, 48(2):1-32.

Bernardini F, Buffi A, Fontanelli D, et al. Robot-based Indoor Positioning of UHF-RFID Tags: The SAR Method with Multiple Trajectories[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70:8001415.

Yao C Y, Hsia W C. An Indoor Positioning System based on the Dual-channel Passive RFID Technology[J]. IEEE Sensors Journal, 2018, 18(11):4654-4663.

Dinh T M T, Duong N S, Sandrasegaran K. Smartphone-based Indoor Positioning Using BLE iBeacon and Reliable Lightweight Fingerprint Map[J]. IEEE Sensors Journal, 2020, 20(17):10283-10294.

Liu F, Zhang J, Wang J, et al. An UWB/Vision Fusion Scheme for Determining Pedestrians' Indoor Location[J]. Sensors, 2020, 20(4):1139.

Do T H, Yoo M. An In-depth Survey of Visible Light Communication based Positioning Systems[J]. Sensors, 2016, 16(5):678.

Maheepala M, Kouzani A Z, Joordens M A. Light-based Indoor Positioning Systems: a Review[J]. IEEE Sensors Journal, 2020, 20(8):3971-3995.

Gligoric K, Ajmani M, Vukobratovic D, et al. Visible Light Communications-based Indoor Positioning via Compressed Sensing[J]. IEEE Communications Letters, 2018, 22(7):1410-1413.

Hsu L S, Tsai D C, Chow C W, et al. Using Data Pre-processing and Convolutional Neural Network (CNN) to Mitigate Light Deficient Regions in Visible Light Positioning (VLP) Systems[J]. Journal of Lightwave Technology, 2022, 40(17):5894-5900.

Steendam H, Wang T Q, Armstrong J. Cramer-Rao Bound for AOA-based VLP with an Aperture-based Receiver[C]//2017 IEEE International Conference on Communications (ICC). Paris, France: IEEE, 2017:7996691.

Bai L, Yang Y, Feng C, et al. Novel Visible Light Communication Assisted Perspective-four-line Algorithm for Indoor Localization[C]//GLOBECOM 2020 - 2020 IEEE Global Communications Conference. Taipei, China: IEEE, 2020:9322127.

Liang Q, Sun Y, Liu C, et al. LedMapper: Toward Efficient and Accurate LED Mapping for Visible Light Positioning at Scale[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:8500612.

Huang T M, Lin B J, Ghassemlooy Z, et al. Three-dimensional NLOS VLP based on a Luminance Distribution Model for Image Sensor[J]. IEEE Internet of Things Journal, 2022, 10(8):6902-6914.

Huang T, Lin B, Ghassemlooy Z, et al. Indoor 3D NLOS VLP Using a Binocular Camera and a Single LED[J]. Optics Express, 2022, 30(20):35431-35443.

Chen J, Sun W, Ma L, et al. Anti-shadowing Design of Visible Light Communication and Positioning Systems with Equivalent Virtual Lamps[C]//2020 22nd International Conference on Transparent Optical Networks (ICTON). Bari, Italy: IEEE, 2020:9203330.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进LSTM的FBG传感网络光谱基线校正方法

电力线载波通信中基于深度学习的信道估计

深度学习在光纤通信系统损伤补偿中的应用

基于深度学习的电光调制型可编程光学频率梳

非视距水下无线光通信技术的研究进展