A Single-Anchor Visible Light Positioning System Based on Fingerprinting and Deep Learning

Abstract

Due to severe signal obstruction, the global navigation satellite system is unable to work indoors. Visible light positioning, as an alternative technology for indoor positioning, has gained widespread attention in recent years due to its low cost and environmental friendliness. Among these, the visible light single anchor positioning method based on light-emitting diode arrays has shown great potential as it can simultaneously provide lighting and positioning. The rise of artificial intelligence has provided new methods for indoor positioning.This article focuses on the single anchor visible light fingerprinting-based positioning technology and uses a multi-layer perceptron-based method to maximize its performance. In addition, in terms of hardware design, we focus on improving the receiver's integration, making it applicable to a wider range of scenarios through size reduction and cost control. Finally, the designed hardware and the proposed method are evaluated in the space range of 320 cm* 560 cm* 270 cm. When compared with the traditional nearest neighbor, k-nearest neighbor, and weighted k-nearest neighbor methods, the experimental results show that the proposed method exhibits significant advantages in performance. The average positioning accuracy in the real scene can reach 34cm.