A Deep Learning-Assisted Visible Light Positioning Scheme for Vehicles With Image Sensor

Abstract

Visible light communication (VLC) based on image sensor (IS) as the receiver is one of the supplementary technologies of radio frequency communication. By combining with image processing technology, VLC has various applications in smart home, underwater communication and intelligent transportation system (ITS). In the paper, it focuses on the vehicle positioning service provided by VLC in ITS. For the weak image spatial separability caused by long-distance VLC transmission between the vehicle and the infrastructure, it will lead to serious deterioration in communication and positioning performance. Thus, a deep learning-assisted IS-based visible light positioning (VLP) scheme is proposed and experimentally demonstrated. At the transmitter, a novel coding method is proposed to support both short-distance and long-distance communication based on VLC in ITS. Meanwhile, it can meet the dimming requirements of LED road infrastructure. In addition, in the proposed VLP scheme, it uses an artificial neural network (ANN) to predict the location of the vehicle. It is demonstrated that long-distance communication, high-accuracy positioning, and LED dimming can be realized simultaneously. The results show that, by using the proposed scheme, as the transmission distance is 2 m, the bit error rate (BER) of system is 1.25×10 -4 . And the average positioning error is 19.8 mm at the maximum simulated distance of 30 m.

ViRSMALNet: A Twin-Tier LSTM-Based Deep Learning Network for Indoor MIMO RSMA VLC Systems

“…Now, focusing on VLC, research efforts in the area of signal detection using DL techniques is quite limited. The available research focuses on developing DL-based methods for LED positioning [41], [42], resource allocation [43], [44], LSTM-based techniques for reducing peak-to-averagepower ratio [45], etc. Although, few DL-based receiver architectures are proposed in [46]- [48], to the best of our knowledge, a dedicated DL-based receiver, which bypasses the SIC operations for an indoor MIMO RSMA VLC system is not yet investigated in literature.…”

A Survey of Visible Light Communication Based Indoor Positioning Systems

“…Besides, deep learningbased algorithms have been widely explored in recent years. For instance, [106][107][108] propose several DL-based algorithms with diverse sensors.…”

A Review on Image Sensor Communication and Its Applications to Vehicles

“…Machine learning or deep learning techniques have been increasingly used for range estimation in vehicular ISC systems [56,82,87]. In [82], a back-propagation (BP) neuralnetwork learning method has been used for positioning and range estimation.…”

“…In [82], a back-propagation (BP) neuralnetwork learning method has been used for positioning and range estimation. In [87], a coding approach is proposed to provide short-distance and long-distance communication. The authors used an artificial neural network (ANN) to forecast the vehicle's location.…”