基于结构特征保持网络的遥感地图压缩方法

王璐; 赵娜; 汤恒先

doi:10.12382/bgxb.2025.0692

您当前的位置：

首页 >

文章列表页 >

基于结构特征保持网络的遥感地图压缩方法

更新时间：2026-04-03

- 基于结构特征保持网络的遥感地图压缩方法
- Remote Sensing Map Compression Method Based on Structure Feature Preserving Network
- 兵工学报 2026年
- 作者机构：
- 作者简介：
- 基金信息：
  
  陕西省科技厅科技发展计划项目（2024GX-YBXM-139）
- DOI：10.12382/bgxb.2025.0692
  中图分类号： TP391.41
- 收稿：2025-07-29，
  
  网络首发：2026-04-03，
- 稿件说明：
移动端阅览
王璐，赵娜，汤恒先. 基于结构特征保持网络的遥感地图压缩方法[J]. 兵工学报, 2026(2026-04-03). https://doi.org/10.12382/bgxb.2025.0692.

WANG L, ZHAO N, TANG H X. Remote sensing map compression method based on structure feature preserving network[J/OL]. Acta Armamentarii, 2026(2026-04-03). https://doi.org/10.12382/bgxb.2025.0692. (in Chinese)
王璐，赵娜，汤恒先. 基于结构特征保持网络的遥感地图压缩方法[J]. 兵工学报, 2026(2026-04-03). https://doi.org/10.12382/bgxb.2025.0692. DOI：

WANG L, ZHAO N, TANG H X. Remote sensing map compression method based on structure feature preserving network[J/OL]. Acta Armamentarii, 2026(2026-04-03). https://doi.org/10.12382/bgxb.2025.0692. (in Chinese) DOI：

摘要

遥感地图在实际应用中往往需要丰富的结构与纹理信息，然而在传输过程中由于图像压缩，部分结构信息会被忽略或平滑处理，导致边缘模糊或空间关系扭曲。针对上述问题，提出基于结构特征保持网络的遥感地图压缩方法。该网络包括边缘纹理保持子网络与全局结构融合子网络。边缘纹理保持子网络采用灰度共生矩阵与边缘检测引导神经网络的方式，保存图像的显著边缘与细节纹理特征，同时利用空间结构增强模块丰富细节信息。全局结构融合子网络采用由粗到细的网络架构设计，充分理解图像的全局结构相关性，更有效地去除冗余信息。将上述子网络的输出特征进行融合，兼顾遥感地图的局部边缘纹理以及全局结构相关性。实验结果表明，所提方法在遥感地图的压缩过程中结构特征损失明显降低。

Abstract

In the practical applications of remote sensing maps

rich structural and texture information is often required. However

some structural information may be ignored or smootheddue toimagecompressionduring the transmission process

resulting intheblurred edges or distorted spatial relationshipsin the remote sensingmaps. To address theaforementionedissues

this paper proposes a remote sensing map compression method based on a structure feature preservingnetwork.This network consists of an edge texture preservingsub-network and a global structure fusion sub-network.In theedge texture preservingsub-network

the significant edges and detailed texture features of the image are preserved by using a gray-level co-occurrence matrix and edge feature extraction to guide the neural network

anda spatial structure enhancement moduleis usedto enrich the detailed information.In theglobal structure fusion sub-network

a coarse-to-fine network architecture designis usedto fully understand the global structural correlation of the image and more effectively remove redundant information. Finally

the output features of the above sub-networks are fused to take into account both the local edge texture and the global structural correlation of the remote sensing map. Experimental results show that the proposed method significantly reduces the loss of structural features in the compression process of remote sensing maps.

关键词

Keywords

references

张兰, 王光霞, 安利, 等. 基于改进层次分析法的遥感影像压缩质量评价[J]. 测绘与空间地理信息, 2023, 46(4): 8-12.

ZHANG L, WANG G X, AN L, et al. Remote sensing image compression quality evaluation based on improved analytic hierarchy process [J].Geomatics & Spatial Information Technology, 2023, 46(4): 8-12. (in Chinese)

徐德枭, 孔繁锵, 王坤, 等. 频率分解双支特征提取的多光谱图像压缩网络[J]. 中国激光, 2024, 51(21): 2109001.

XU D X, KONG F Q, WANG K, et al. Frequency decomposition and double-branch feature extraction for multispectral-image-compression network[J].Chinese Journal of Lasers, 2024, 51(21):2109001. (in Chinese)

石杰, 戚国庆, 盛安冬. 考虑目标尺寸情况下的水面目标跟踪参数估计[J].兵工学报, 2013, 34(4):494-500. SHI J, QI G Q, SHENG A D. Estimation of motion parameters by considering the size of surface target [J]. Acta Armamentarii, 2013, 4(4):494-500. (in Chinese)

吴伟超.高精度遥感影像在城市规划中的测绘工程应用[J].城市建设理论研究(电子版), 2024(30): 175-177.

WU W C. Surveying and mapping engineering applications of high-precision remote sensing images in urban planning[J].Theoretical Research in Urban Construction, 2024(30): 175-177. (in Chinese)

WEINBERGER M J, SEROUSSI G, SAPIRO G. The LOCO-I lossless image compression algorithm:Principles and standardization into JPEG-LS[J]. IEEE Transactions on Image Processing,2000, 9(8): 1309-1324.

MENTZER F, AGUSTSSON E, TSCHANNEN M, et al. Conditional probability models for deep image compression[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, US:IEEE, 2018: 4394-4402.

SHEN M H, GAN H P, NING C, et al.TransCS: a transformer-based hybrid architecture for image compressed sensing[J]. IEEE Transactions on Image Processing, 2022, 31: 6991-7005.

XU H, HAI B W, TANG Y S, et al. Window-based channel attention for wavelet-enhanced learned image compression:arXiv:2409.14090[R]. Ithaca,NY,US:Cornell University, 2024:2409.14090.

LI W G, SUN W Y, ZHAO Y D, et al. Deep image compression with residual learning[J]. Applied Sciences, 2020, 10(11): 4023.

XIAO L C, WANG H R, LING N. Image compression with deeper learned transformer[C]//Proceedings of 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.Lanzhou, China:IEEE,2019.

贾佳. 面向任务的端到端遥感图像压缩算法研究[D]. 西安:西安电子科技大学, 2024.

JIA J. Research on task-oriented end-to-end remote sensing image compression algorithms[D].Xi’an:Xidian University,2024. (in Chinese)

ZHAO J W, YAN K, ZHAO Y F, et al. Transformer-based dual relation graph for multi-label image recognition:arXiv:2110.04722[R].Ithaca,NY,US:Cornell University, 2021: 2110.04722.

高昕, 甄国涌, 储成群, 等. 基于改进Canny算子的齿轮边缘缺陷检测方法[J].工具技术,2024, 58(9): 145-151.

GAO X, ZHEN G Y, CHU C Q, et al. Image edge detection method based on improved canny algorithm [J].Tool Engineering, 2024, 58(9): 145-151. (in Chinese)

DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, US: IEEE, 2009:248-255.

WANG X Y, YAN H P, HUO C L, et al. Enhancing pix2pix for remote sensing image classification[C]//Proceedings of 2018 24th International Conference on Pattern Recognition. Beijing, China: IEEE, 2018: 2332-2336.

TODERICI G, VINCENT D, JOHNSTON N, et al. Full resolution image compression with recurrent neural networks:arXiv:1608.05148[R].Ithaca,NY,US:Cornell University,2016:1608.05148.

JOHNSTON N, VINCENT D, MINNEN D, et al. Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City, UT, US:IEEE, 2018: 4385-4393.

TODERICI G, SHI W, TIMOFTE R, et al. Workshop and challenge on learned image compression(CLIC2020)[C]//Proceedings of the IEEE/CVF on Computer Vision and Pattern Recognition. Seattle, WA, US:IEEE, 2020: 1654-1684.

CHENG Z X, SUN H M, TAKEUCHI M, et al. Learned image compression with discretized gaussian mixture likelihoods and attention modules[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, US:IEEE, 2020: 7939-7948.

XIE Y Q, CHENG K L, CHEN Q F. Enhanced invertible encoding for learned image compression:arXiv:2108.03690[R].Ithaca,NY,US:Cornell University, 2021: 2108.03690.

CHEN F D, XU Y M, WANG L. Two-stage octave residual network for end-to-end image compression[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2022,36(4): 3922-3929.

HE D L, YANG Z M, PENG W K, et al. ELIC: efficient learned image compression with unevenly grouped space-channel contextual adaptive coding[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, LA, US :IEEE,2022: 5718-5727.

LIU J M, SUN H M, KATTO J. Learned image compression with mixed transformer-CNN architectures[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington，D.C.,US:IEEE, 2023: 14388-14397.

LI C, YIN S Z, JIA C M, et al. Multirate progressive entropy model for learned image compression[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(8): 7725-7741.

WANG J Q, LING Q. Learned image compression with adaptive channel and window-based spatial entropy models[J]. IEEE Transactions on Consumer Electronics, 2024,70(4): 6430-6441.

WANG Y Q, LIANG F, WANG S, et al. Towards an efficient remote sensing image compression network with visual state space model[J]. Remote Sensing, 2025, 17(3): 425.

LI J H, HOU X S. Object-fidelity remote sensing image compression with content-weighted bitrate allocation and patch-based local attention[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 1-14.

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于Transformer-LSTM混合神经网络的迫弹外弹道及落点预测方法

基于多尺度双重注意力网络的雷达信号调制识别方法

暗环境下红外目标检测跟踪方法研究

复杂场景伪装小目标机载偏振遥感检测方法

基于深度学习的联合等式状态约束辨识与递推滤波