Saved in:
Bibliographic Details
Main Authors: Lin, Jie, Lee, Hsun-Yu, Li, Ho-Ming, Wu, Fang-Jing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.03024
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912677871222784
author Lin, Jie
Lee, Hsun-Yu
Li, Ho-Ming
Wu, Fang-Jing
author_facet Lin, Jie
Lee, Hsun-Yu
Li, Ho-Ming
Wu, Fang-Jing
contents Accurate and robust indoor localization is critical for smart building applications, yet existing Wi-Fi-based systems are often vulnerable to environmental conditions. This work presents a novel indoor localization system, called LiGen, that leverages the spectral intensity patterns of ambient light as fingerprints, offering a more stable and infrastructure-free alternative to radio signals. To address the limited spectral data, we design a data augmentation framework based on generative adversarial networks (GANs), featuring two variants: PointGAN, which generates fingerprints conditioned on coordinates, and FreeGAN, which uses a weak localization model to label unconditioned samples. Our positioning model, leveraging a Multi-Layer Perceptron (MLP) architecture to train on synthesized data, achieves submeter-level accuracy, outperforming Wi-Fi-based baselines by over 50\%. LiGen also demonstrates strong robustness in cluttered environments. To the best of our knowledge, this is the first system to combine spectral fingerprints with GAN-based data augmentation for indoor localization.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03024
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LiGen: GAN-Augmented Spectral Fingerprinting for Indoor Positioning
Lin, Jie
Lee, Hsun-Yu
Li, Ho-Ming
Wu, Fang-Jing
Robotics
I.2.9; C.3
Accurate and robust indoor localization is critical for smart building applications, yet existing Wi-Fi-based systems are often vulnerable to environmental conditions. This work presents a novel indoor localization system, called LiGen, that leverages the spectral intensity patterns of ambient light as fingerprints, offering a more stable and infrastructure-free alternative to radio signals. To address the limited spectral data, we design a data augmentation framework based on generative adversarial networks (GANs), featuring two variants: PointGAN, which generates fingerprints conditioned on coordinates, and FreeGAN, which uses a weak localization model to label unconditioned samples. Our positioning model, leveraging a Multi-Layer Perceptron (MLP) architecture to train on synthesized data, achieves submeter-level accuracy, outperforming Wi-Fi-based baselines by over 50\%. LiGen also demonstrates strong robustness in cluttered environments. To the best of our knowledge, this is the first system to combine spectral fingerprints with GAN-based data augmentation for indoor localization.
title LiGen: GAN-Augmented Spectral Fingerprinting for Indoor Positioning
topic Robotics
I.2.9; C.3
url https://arxiv.org/abs/2508.03024