RD-ASVTuw: Receiver-Driven Adaptive Scalable Video Transmission in underwater acoustic networks

Achieving reliable underwater acoustic communications is a challenging task due to the time-varying channels in the underwater acoustic environment. Scalable Video Coding (SVC) has been widely used in video transmissions. However, inappropriate SVC structures can lead to poorer received video quality than user requirements or resource waste, especially in underwater time-varying channels. In this work, an adaptive cross-layering solution is proposed and validated for video transmissions in underwater acoustic multicast networks, namely Receiver-Driven Adaptive Scalable Video Transmission (RD-ASVTuw). In RD-ASVTuw, the decision-making about transmission schemes takes place at the receiver through Machine Learning (ML). The transmitter collects over time the selected transmission scheme indexes and the user's video quality requirements to transmit the SVC video adaptively. At-sea experiments were conducted to collect the required acoustic data. The data collected were then used in MATLAB simulations to validate RD-ASVTuw.