A Study on Data Signal Detection and Demodulation based on Object Detection DNN for Image Sensor-Based Visible Light Communication

Abstract

This study focuses on a visible light communication system using a digital signage as a transmitter and an image sensor as a receiver. The transmitter modulates data signals on the signage image, and the receiver detects and demodulates the data signals from the captured images. In the conventional studies, the detection and demodulation of the data signals are processed independently. In this study, we propose a novel algorithm that simultaneously processes data signal detection and demodulation by applying object detection DNN (Deep Neural Network). Using simplified simulated received images, we investigate and evaluate data signal formats suitable for the detection and demodulation using the object detection DNN. The numerical results show that square-shaped data signal formats achieve better performance than elongated formats, and the arrangement of data cells affects the performance more than the type of detection marker lines.