Experimental Research on Image Transmission Over One Hundred Metres With Limited Bandwidth in a Semantic Ultraviolet Communication System

ABSTRACT Currently, ultraviolet (UV) communication is proposed for use in unmanned aerial vehicle (UAV) communication, while the efficient transmission of images with limited bandwidth has posed a persistent challenge. This paper introduces a light‐emitting diode‐based UV communication system combined with semantic compression for image transmission. The experimental results show that the proposed semantic UV communication (SUC) system could transform a 7.19 MB image to a file of approximately 304 kB with the aid of deep learning, effectively reducing the bandwidth required for transmission. In addition, by jointly designing the encoding and modulation process and incorporating the interference light signals from the receiver’s detector into the joint coding‐modulation (JCM) system for training, the resulting modulation strategy is matched with the actual transmission conditions. The experimental results demonstrated that the system could work well over 100 m while sending images with good quality in the face of error bits interference.