通信学报2025，Vol.46Issue(5)：29-46,18.DOI:10.11959/j.issn.1000-436x.2025094
基于深度灵活编码策略与性能预测的无线语义图像传输系统
Wireless semantic image transmission system based on deep flexible coding strategy and performance prediction
摘要
Abstract
To improve adaptivity and coding flexibility for diverse image content under complex and dynamic wireless channel conditions,a deeply flexible joint source-channel coding(DF-JSCC)scheme and a transmission performance prediction network(PreNet)for semantic image transmission(SIT)were proposed.Specifically,a multi-scale feature fu-sion module(MS-FFM)was incorporated into DF-JSCC to enhance detailed feature extraction.A feature enhancement module(FEM)was also designed to adaptively adjust channel weights in the feature maps to reinforce critical informa-tion.Additionally,PreNet was introduced to accurately predict the peak signal-to-noise ratio(PSNR)performance of re-constructed images by modeling feature distribution in detail-rich feature maps and utilizing multidimensional feature fu-sion and learning.Experimental results demonstrate that,compared with the existing state-of-the-art DeepJSCC method,DF-JSCC achieves at least 1.03 dB improvement in PSNR across various communication scenarios,while reducing band-width consumption by over 50%under equivalent transmission conditions.The PreNet effectively improves the predic-tion quality and robustness of the SIT in complex environments by reducing the mean squared error(MSE)by 20%.关键词
编码灵活性/语义图像传输/信源信道联合编码/性能预测Key words
coding flexibility/semantic image transmission/joint source-channel coding/performance prediction分类
电子信息工程引用本文复制引用
杨舒涵,申滨,黄晓舸..基于深度灵活编码策略与性能预测的无线语义图像传输系统[J].通信学报,2025,46(5):29-46,18.基金项目
国家自然科学基金资助项目(No.62371082) （No.62371082）
重庆市自然科学基金资助项目(No.CSTB2023NSCQ-MSX0726)The National Natural Science Foundation of China(No.62371082),The Natural Science Foundation of Chongq-ing(No.CSTB2023NSCQ-MSX0726) （No.CSTB2023NSCQ-MSX0726）
