Efficient and robust 3D indoor visible light positioning via uniform and power-of-two quantization on multi-head ResNet50
Authors:
- Zhan WangZWZhan Wang
- Jiongnan LouJLJiongnan Lou
- Yiqian QianYQYiqian Qian
- Haifei ShenHSHaifei Shen
- Lianxin HuLHLianxin Hu
- 3 April 2026
- journal article
- Published by Optica Publishing Group in Applied Optics
- Vol. 65 (11) , 3654-3663
Abstract
Existing indoor positioning methods in visible light communication systems typically rely on large databases, powerful signal processing units, and additional sensors such as gyroscopes, which limit their applicability in efficiency-sensitive scenarios. To address this issue and achieve an optimal balance between positioning accuracy, inference time, and model size, we propose uniform and power-of-two quantization on a multi-head ResNet50 (UPU-MH-ResNet50) algorithm in this paper. The proposed algorithm does not require additional sensors and can accurately estimate the three-dimensional coordinates of the receiver, including X and Y coordinates and rotation angle. It effectively mitigates the impact of random angle changes on positioning accuracy, significantly enhancing the system’s robustness. Additionally, the algorithm is further optimized through model quantization to reduce computational costs. We conducted validation on a self-built experimental testbed in a laboratory environment with dimensions of 2.6m×2.6m×2.2m and a receiver rotation angle range of ±30 ∘ . Within this tilt range, 90% of the 3D positioning errors are controlled within 2 cm. Moreover, the proposed 4-bit UPU-MH-ResNet50 achieves a 7.7× reduction in model size and a 2.7× speedup in inference, where the acceleration and efficiency results are measured from the GPU-based implementation using real captured data collected on the developed testbed, indicating high energy efficiency.Keywords
Funding Information
- Huzhou Key Laboratory of Waters Robotics Technology, Huzhou Science and Technology Bureau (2022-3)
- Zhejiang-French Digital Monitoring Lab for Aquatic Resources and Environment, Department of Science and Technology of Zhejiang Province (2023-70)
This publication has 27 references indexed in Scilit:
- ASQ & POST: A synergistic framework for adaptive and non-uniform quantizationNeurocomputing, 2025
- WISDOM: A framework for scaling on-device Wi-Fi sensing solutionsAd Hoc Networks, 2025
- High-Accuracy Visible Light Positioning Algorithm Using Single LED Lamp With a BeaconIEEE Access, 2024
- Indoor positioning system for single LED light based on deep residual shrinkage networkOptics Communications, 2024
- Localization as a Key Enabler of 6G Wireless Systems: A Comprehensive Survey and an OutlookIEEE Open Journal of the Communications Society, 2023
- Indoor Localization for the Blind Based on the Fusion of a Metaheuristic Algorithm with a Neural Network Using Energy-Efficient WSNArabian Journal for Science and Engineering, 2022
- Teacher–student knowledge distillation based on decomposed deep feature representation for intelligent mobile applicationsExpert Systems with Applications, 2022
- BiQGEMM: Matrix Multiplication with Lookup Table for Binary-Coding-Based Quantized DNNs2020
- Three-Dimensional VLC Positioning Based on Angle Difference of Arrival With Arbitrary Tilting Angle of ReceiverIEEE Journal on Selected Areas in Communications, 2017
- A hybrid power line and visible light communication system for indoor hospital applicationsComputers in Industry, 2015