Bubble-Wave-Mitigation Algorithm and Transformer-Based Neural Network Demodulator for Water-air Optical Camera Communications

Optical camera communication (OCC) has been widely employed in various applications as a flexible and cost-effective means of communication both on land and underwater. However, the performance of the OCC system through the water-air interface has not been thoroughly investigated. In this paper, we explore the performance of the OCC system in a water-air environment and propose a bubble-wave-mitigation algorithm to pre-process the captured frames of received video. Moreover, we propose a transformer-based neural network to demodulate the transmitted signal, mitigating the deterioration in transmission performance caused by inter-symbol interference (ISI). The experimental results demonstrate that a robust transmission can be achieved in the water-air environment by applying our proposed algorithms and neural network demodulator.