A YOLOv5 and Improved Perspective-4-Points Algorithm Based Indoor LOS and NLOS Adaptive Visible Light Positioning System - Details

author：

Indexed by：

EI

Abstract：

Visible　light　positioning　systems　(VLPs)　that　are　based　on　line-of-sight　(LOS)　are　highly　accurate;　however,　they　cannot　operate　under　shadowing/blocking　conditions　commonly　encountered　in　indoor　environments.　Relaying　on　non-line-of-sight　(NLOS)　transmission　paths　can　resolve　this　problem　at　the　cost　of　poor　performance.　In　this　paper,　we　propose　an　indoor　LOS　and　NLOS　adaptive　VLP　system　that　overcomes　shadowing/blocking　and　maintain　a　high　level　of　performance.　To　achieve　dynamic　algorithm　switching　and　position　estimation,　the　proposed　system　uses　an　improved　perspective-4-points　(P4P)　algorithm.　Further,　a　deep　learning　(DL)　model,　YOLOv5,　is　designed　to　detect　the　highlight　spots　formed　by　light　emitting　diodes　(LEDs)　over　LOS　or　NLOS　paths　due　to　its　improved　accuracy　and　generalization.　Experimental　results　show　that　the　proposed　system　can　provide　a　good　three-dimensional　positioning　accuracy,　with　mean　square　errors　of　13.2　cm　for　LOS　and　28.1　cm　for　NLOS,　respectively.　©　2024　IEEE.

Keyword：

Deep learning Mean square error

Community：

[ 1 ] [Yang, Jingxian]School of Advanced Manufacturing, Fuzhou University, Quanzhou, China
[ 2 ] [Huang, Weijie]Quanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou, China
[ 3 ] [Ding, Yongqi]Quanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou, China
[ 4 ] [Luo, Jiabin]Quanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou, China
[ 5 ] [Yu, Hongtao]Quanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou, China
[ 6 ] [Yan, Shujie]Quanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou, China
[ 7 ] [Huang, Yixiang]Quanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou, China
[ 8 ] [Lin, Bangjiang]Quanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou, China
[ 9 ] [Ghassemlooy, Zabih]Northumbria University, Faculty of Engineering and Environment, Newcastle upon Tyne, United Kingdom

Reprint 's Address：

Email：

Related Keywords：

MSRCN: Multi-task Learning Network for Cell Segmentation and Regression Counting
2022，3rd International Symposium on Artificial Intelligence for Medical Sciences, ISAIMS 2022
A New CNN-based Joint Network for Brain Tumor Denoising and Classification
2022，2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2022
A two-stage deep counting for bacterial colonies from multi-sources
2022，Applied Soft Computing
Deep learning detection of shrimp freshness via smartphone pictures
2022，JOURNAL OF FOOD MEASUREMENT AND CHARACTERIZATION
Deep learning methods for atmospheric PM2.5 prediction: A comparative study of transformer and CNN-LSTM-attention
2023，Atmospheric Pollution Research

Type
Departments

All Years Choose Year From to