Journal
IEEE JOURNAL OF OCEANIC ENGINEERING
Volume 48, Issue 3, Pages 925-945Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JOE.2023.3249243
Keywords
Image coding; Training; Quantization (signal); Robustness; OFDM; Image reconstruction; Channel coding; Autoencoder; deep learning; underwater communication; underwater image compression
Ask authors/readers for more resources
This article proposes an effective and robust underwater image compression scheme, utilizing an autoencoder for extreme bit rate compression and a multistep training strategy to improve decoder robustness. Experimental results show that the content of the reconstructed image can still be recognized under high compression ratios and average bit error rates.
Images occupy a prominent place in data because they are more visually appealing than sounds or texts. Acoustic waves are the only feasible alternative for long-distance underwater transmission since seawater has a high absorption impact on lighting and electromagnetic signals. However, underwater acoustic (UWA) communication technology can only provide relatively limited bandwidth (low effectiveness) and insufficiently stable links (low reliability). As a result, it is challenging to send high-resolution underwater images via the UWA channel. This article proposes an effective and robust underwater image compression scheme. First, an autoencoder is used for underwater image extreme bit rate compression. Then, a multistep training strategy is proposed to improve the robustness of the decoder by gradually learning channel degradation features. Finally, the autoencoder encodes images in two paths to achieve efficient compression and higher image quality when reconstructing images. The main path completes the compression task with a low bit rate and high robustness, while the branching path implements the image block retransmission compensation through the feedback signal. The experimental results demonstrate that the content of the reconstructed image can still be recognized under the conditions of a compression ratio of up to 1/768 and an average bit error rate of up to 10(-1). The joint multistep training strategy and multidescription coding achieve a low bit rate and high robustness for underwater image communication, which has good application prospects.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available