High Quality Compression and Transmission of Remote Sensing Images Based on Semantic Communication

doi:10.1109/TSUSC.2025.3544249

	High Quality Compression and Transmission of Remote Sensing Images Based on Semantic Communication
	Jiang, Yan 1,2; Xie, Kun 1,2; Ouyang, Yudian 1,2; Wen, Jigang 3; Zhang, Guangxing 4; Liang, Wei 3; Feng, Quan 5
	2025-09-01
发表期刊	IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING
ISSN	2377-3782
卷号	10 期号:5 页码:843-857
摘要	Remote sensing imagery plays a crucial role in areas such as environmental monitoring and urban planning. However, due to fragile communication links, limited bandwidth and harsh wireless environments, transmitting data from remote locations to ground applications faces the dilemma of high bit-error rates, which have a poor impact on downstream missions. Semantic communication is a feasible solution that transmits only the semantic features of the raw data extracted using neural networks. Although effective, existing semantic communication methods cannot cope with high compression rate requirements and complex communication environments. Therefore, in this paper, an effective image compression and transmission framework ASE-JSCC is proposed. To minimize the transmitted data, we design a semantic extraction module and an important feature selection module to efficiently extract, select, and compress critical semantic features required for downstream tasks. To improve the communication robustness of the model in complex environments affected by variable channels, we optimize the source-channel joint coding technique by randomly adding noise with different types and sizes. Finally, we deploy ASE-JSCC to the scene classification task of remote sensing images and conduct extensive experiments on four real datasets, achieving classification accuracy of 84.29%--88.62% under 384 times compression ratio, verifying the excellent performance of the proposed framework.
关键词	Data transmission image compression remote sensing remote sensing semantic communication semantic communication scene classification scene classification scene classification
DOI	10.1109/TSUSC.2025.3544249
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62025201] ; National Natural Science Foundation of China[62402172] ; National Natural Science Foundation of China[62472167] ; Hunan Provincial Natural Science Foundation[2024JJ5165] ; Hunan Provincial Key Research and Development Program[2023GK2001] ; Postdoctoral Science Foundation[2024M750878]
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Information Systems ; Telecommunications
WOS记录号	WOS:001591666600006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41669
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xie, Kun
作者单位	1.Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410082, Peoples R China 2.Minist Educ, Key Lab Fus Comp Supercomp & Artificial Intelligen, Changsha 410082, Peoples R China 3.Hunan Univ Sci & Technol, Sch Comp Sci & Engn, Xiangtan 411199, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100864, Peoples R China 5.Hunan Vanguard Grp Corp Ltd, Changsha 410000, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Yan,Xie, Kun,Ouyang, Yudian,et al. High Quality Compression and Transmission of Remote Sensing Images Based on Semantic Communication[J]. IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING,2025,10(5):843-857.
APA	Jiang, Yan.,Xie, Kun.,Ouyang, Yudian.,Wen, Jigang.,Zhang, Guangxing.,...&Feng, Quan.(2025).High Quality Compression and Transmission of Remote Sensing Images Based on Semantic Communication.IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING,10(5),843-857.
MLA	Jiang, Yan,et al."High Quality Compression and Transmission of Remote Sensing Images Based on Semantic Communication".IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING 10.5(2025):843-857.