arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.00202eess.SPeess.IV
收藏

无线图像传输中信噪比自适应的深度联合信源信道编码

SNR-adaptive deep joint source-channel coding for wireless image transmission

Mingze Ding, Jiahui Li, Mengyao Ma, Xiaopeng Fan

摘要:

针对噪声信道下多用户图像传输的联合信源信道编码(JSCC)问题,提出了一种基于自编码器的深度联合信源信道编码方案。在所提出的JSCC方案中,解码器可以估计信噪比(SNR),并使用它来自适应解码传输的图像。实验结果表明,该方案对不同信噪比的适应性较好,对解码端信噪比估计误差具有较强的鲁棒性。据我们所知,这是第一个深度JSCC方案,专注于对不同SNR的适应性,并可应用于多用户场景。

英文摘要:

Considering the problem of joint source-channel coding (JSCC) for multi-user transmission of images over noisy channels, an autoencoder-based novel deep joint source-channel coding scheme is proposed in this paper. In the proposed JSCC scheme, the decoder can estimate the signal-to-noise ratio (SNR) and use it to adaptively decode the transmitted image. Experiments demonstrate that the proposed scheme achieves impressive results in adaptability for different SNRs and is robust to the decoder's estimation error of the SNR. To the best of our knowledge, this is the first deep JSCC scheme that focuses on the adaptability for different SNRs and can be applied to multi-user scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑