Visible light camera communication method based on convolutional neural network

• Main Authors: LIN BANGJIANG, WAN XIANGYU, LUO JIABIN, HUANG TIANMING, JIANG NINGCONG
• Format: Patent
• Language: Chinese; English
• Published: 05.09.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; TRANSMISSION

The invention is suitable for the technical field of visible light communication, and provides a visible light camera communication method based on a convolutional neural network, and the method comprises the steps: generating a pseudo-random binary sequence through Matlab at a transmitting end; the pseudo-random binary sequence is mapped into a PWM symbol through a microcontroller unit, and the modulated PWM symbol is sent to a free space through RGB-LED three color channels; and at a receiving end, separating a red channel, a green channel and a blue channel in the CMOS camera through a hardware component of a Bayer color filter array, separating PWM symbols with different duty ratios in the same color channel by adopting a convolutional neural network as a classifier, and realizing real-time demodulation of a signal at the transmitting end through a mobile phone application program based on the convolutional neural network. And a receiving end uses an application program based on the convolutional neural n