arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.01733cs.ITcs.LGeess.SPmath.ITstat.ML
收藏

无线图像传输中的深度联合信源-信道编码

Deep Joint Source-Channel Coding for Wireless Image Transmission

University College London(伦敦大学学院);Imperial College London(帝国理工学院)

Eirina Bourtsoulatze, David Burth Kurka, Deniz Gunduz

摘要:

我们提出了一种联合信源和信道编码(JSCC)技术的无线图像传输,不依赖于显式编码的压缩或纠错,而是直接映射的图像像素值的复值信道输入符号。我们通过两个联合训练的卷积神经网络(CNN)来参数化编码器和解码器功能,并且可以被认为是中间具有代表噪声通信信道的不可训练层的自动编码器。我们的研究结果表明,所提出的深度JSCC方案优于数字传输级联JPEG或JPEG 2000压缩,具有在低信噪比(SNR)和信道带宽值下实现信道编码的能力,在存在加性高斯白噪声(AWGN)。更引人注目的是,深度JSCC不受“悬崖效应”的影响,并且当信道SNR相对于训练期间假设的SNR值变化时,它提供了适度的性能降级。在慢瑞利衰落信道的情况下,深度JSCC学习噪声弹性编码表示,并在所有SNR和信道带宽值下显著优于基于分离的数字通信。

英文摘要:

We propose a joint source and channel coding (JSCC) technique for wireless image transmission that does not rely on explicit codes for either compression or error correction; instead, it directly maps the image pixel values to the complex-valued channel input symbols. We parameterize the encoder and decoder functions by two convolutional neural networks (CNNs), which are trained jointly, and can be considered as an autoencoder with a non-trainable layer in the middle that represents the noisy communication channel. Our results show that the proposed deep JSCC scheme outperforms digital transmission concatenating JPEG or JPEG2000 compression with a capacity achieving channel code at low signal-to-noise ratio (SNR) and channel bandwidth values in the presence of additive white Gaussian noise (AWGN). More strikingly, deep JSCC does not suffer from the ``cliff effect'', and it provides a graceful performance degradation as the channel SNR varies with respect to the SNR value assumed during training. In the case of a slow Rayleigh fading channel, deep JSCC learns noise resilient coded representations and significantly outperforms separation-based digital communication at all SNR and channel bandwidth values.

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。

↑