FUVC: A Flexible Codec for Underwater Video Transmission
Yannan Zheng, Jiawei Luo, Weiling Chen, Zuoyong Li, Tiesong Zhao
Abstract
Smart oceanic exploration has greatly benefitted from AI-driven underwater image and video processing. However, the volume of underwater video content is subject to narrow-band and time-varying underwater acoustic channels. How to support high-utility video transmission at such a limited capacity is still an open issue. In this paper, we propose a Flexible Underwater Video Codec (FUVC) with separate designs for targets-of-interest regions and backgrounds. The encoder locates all targets-of-interests, compresses their corresponding regions with x.265 and if bandwidth allows, compresses the background with a lower bitrate. The decoder reconstructs both streams, identifies clean targets-of-interest and fuses them with the background via a Mask Detection and Background Recovery (MDBR) network. When the background stream is unavailable, the decoder adapts all targets-of-interest to a virtual background via Poisson blending. Experimental results show that FUVC outperforms other codecs with a lower bitrate at the same quality. It also supports a flexible codec for underwater acoustic channels. The database and source code are available at https://github.com/z21110008/FUVC.