Deep Joint Source-Channel Coding for Wireless Image Transmission
Deep Joint Source-Channel Coding for Wireless Image Transmission
复制标题
DOI：
10.1109/tccn.2019.2919300
复制
发表时间：
2019-09-01
影响因子：
8.6
通讯作者：
Gunduz, Deniz
中科院分区：
文献类型：
--
作者：
Bourtsoulatze, Eirina;Kurka, David Burth;Gunduz, Deniz
提出了一种用于无线图像传输的联合信源和信道编码(JSCC)技术，该技术不依赖于显式编码进行压缩或纠错，而是直接将图像像素值映射到复值信道输入符号。我们用两个联合训练的卷积神经网络(CNN)对编解码器的功能进行参数化，可以将其视为一个自动编码器，中间有一层不可训练的层，代表了有噪声的通信信道。实验结果表明，在加性高斯白噪声(AWGN)存在的情况下，在低信噪比和低带宽条件下，深JSCC方案的性能优于JPEG2000和JPEG2000级联压缩的数字传输。更引人注目的是，深度JSCC不会受到“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，它提供了一种优雅的性能下降。在慢瑞利衰落信道的情况下，深度JSCC学习抗噪声编码表示，并在所有信噪比和信道带宽值下显著优于基于分离的数字通信。
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.