Three-Dimensional Indoor Visible Light Localization: A Learning-Based Approach

Su, Danping; Liu, Xianbin

doi:10.1145/3460418.3480406

Cited by 6 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, machine learning-based localization methods have also been proposed. For instance, there are machine learning and deep learning-based 3D indoor visible light positioning methods [24]. However, this approach is also unsuitable for our problem because additional environmental modifications are required such as ceiling LEDs.…”

Section: Related Work 21 Simultaneous Localization and Mappingmentioning

confidence: 99%

A Drone’s 3D Localization and Load Mapping Based on QR Codes for Load Management

Kang,

Jung

2024

Drones

View full text Add to dashboard Cite

The ongoing expansion of the Fourth Industrial Revolution has led to a diversification of drone applications. Among them, this paper focuses on the critical technology required for load management using drones. Generally, when using autonomous drones, global positioning system (GPS) receivers attached to the drones are used to determine the drone’s position. However, GPS integrated into commercially available drones have an error margin on the order of several meters. This paper, proposes a method that uses fixed-size quick response (QR) codes to maintain the error of drone 3D localization within a specific range and enable accurate mapping. In the drone’s 3D localization experiment, the errors were maintained within a specific range, with average errors ranging from approximately 0 to 3 cm, showing minimal differences. During the mapping experiment, the average error between the actual and estimated positions of the QR codes was consistently around 0 to 3 cm.

show abstract

Section: Related Work 21 Simultaneous Localization and Mappingmentioning

confidence: 99%

A Drone’s 3D Localization and Load Mapping Based on QR Codes for Load Management

Kang,

Jung

2024

Drones

View full text Add to dashboard Cite

show abstract

“…Different from radio frequency wireless channels, the visible light channel is mainly dominant by the line-of-sight (LoS) link [6], which effectively mitigates the impact of multipath interference and thus improves the positioning accuracy significantly. Existing VLP methods are mainly based on RSS [7], time-of-arrival (ToA) [8] and angle-of-arrival (AoA) [9], etc. However, most of the existing schemes of VLP are aimed at single-target localization.…”

Section: Introductionmentioning

confidence: 99%

Multi-Target Cooperative Visible Light Positioning: A Compressed Sensing Based Framework

Xy¹

2023

Preprint

View full text Add to dashboard Cite

In this paper, a compressed sensing (CS) based framework of multi-target cooperative visible light positioning (VLP) is formulated to realize simultaneous highaccuracy localization of multiple targets. The light emitting diodes (LEDs) intended for illumination are utilized to locate multiple target mobile terminals equipped with photodetectors. The indoor area can be divided into a two-dimensional grid of discrete points, and the targets are located in only a few grid points, which has a sparse property. Thus, the multitarget localization problem can be transferred into a sparse recovery problem. Specifically, a CS-based framework is formulated exploiting the superposition of the received visible light signals at the multiple targets to be located via intertarget cooperation. Then it can be efficiently resolved using CS-based algorithms. Moreover, inter-anchor cooperation is introduced to the CS-based framework by the crosscorrelation between the signals corresponding to different LEDs, i.e., anchors, which further improves the localization accuracy. Enabled by the proposed CS-based framework and the devised cooperation mechanism, the proposed scheme can simultaneously locate multiple targets with high precision and low computational complexity. Simulation results show that the proposed schemes can achieve centimeter-level multitarget positioning with sub-meter accuracy, which outperforms existing benchmark schemes.

show abstract