数据与计算发展前沿 ›› 2025, Vol. 7 ›› Issue (5): 138-152.

CSTR: 32002.14.jfdc.CN10-1649/TP.2025.05.011

doi: 10.11871/jfdc.issn.2096-742X.2025.05.011

• 技术与应用 • 上一篇    下一篇

基于浅层-深层卷积循环神经网络的多光谱遥感图像全色锐化方法

王鹏1,2,*(),杨霄凤1,何忠臣1,杜君1,3   

  1. 1.南京航空航天大学，深圳研究院，广东 深圳 518057
    2.国家空间科学数据中心，北京 100190
    3.上海航天无线电设备研究所, 上海 200090
  • 收稿日期:2025-04-27 出版日期:2025-10-20 发布日期:2025-10-23
  • 通讯作者: 王鹏
  • 作者简介:王鹏，副教授，南京航空航天大学，主要研究方向为遥感数据处理。
    本文中主要负责方法研究与实验，论文撰写。
    WANG Peng is an associate professor at Nanjing University of Aeronautics and Astronautics. His main research direction is remote sensing data processing.
    In this paper, he is responsible for method research, experimental design, and paper writing.
    E-mail: Pengwang_B614080003@nuaa.edu.cn
  • 基金资助:
    国家空间科学数据中心课题(NSSDC2303001);上海航天科技创新基金(SAST2024-052);广东省基础与应用基础研究基金项目(2025A1515010258);深圳市科技计划项目(JCYJ20240813180005007);国家自然科学基金(61801211)

Multispectral Remote Sensing Image Pansharpening Method Based on Shallow-Deep Convolutional Recurrent Neural Network

WANG Peng1,2,*(),YANG Xiaofeng1,HE Zhongchen1,DU Jun1,3   

  1. 1. Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics, Shenzhen, Guangdong 518057, China
    2. National Space Science Data Center, Beijing 100190, China
    3. Shanghai Aerospace Radio Equipment Research Institute, Shanghai 200090, China
  • Received:2025-04-27 Online:2025-10-20 Published:2025-10-23
  • Contact: WANG Peng

RichHTML

7

PDF

15

摘要：

【目的】 多光谱图像全色锐化是指融合高空间分辨率全色图像（PAN）和低空间分辨率的多光谱图像（MS）以获得高光谱和空间分辨率多光谱图像。现有的很多基于深度学习的全色锐化方法容易忽略全色图像和多光谱图像各波段间的局部依赖性和全局相关性。【方法】 针对以上问题，本文提出了一种基于浅层-深层卷积循环神经网络的多光谱图像全色锐化网络，该网络包含浅层特征提取子网络和深层特征融合子网络，通过利用循环神经网络模拟波段间的相互作用，有效增强了融合效果。【结果】 在降分辨率和全分辨率实验中对多个数据集进行了测试，实验结果表明所提出的方法在融合结果质量上优于传统的全色锐化方法。【结论】 浅层特征提取子网络从PAN和MS图像中提取浅层特征。深度特征融合子网络通过建立波段间的视图内和视图间关系来捕获局部和全局相关性，提高了多光谱图像全色锐化的性能。

关键词: 全色锐化技术, 深度学习, 卷积循环神经网络, 卫星遥感图像

Abstract:

[Objective] Multispectral image panchromatic sharpening refers to the fusion of high spatial resolution panchromatic images (PAN) and low spatial resolution multispectral images (MS) to obtain hyperspectral and spatially resolution multispectral images. Many existing panchromatic sharpening methods based on deep learning tend to ignore the local dependence and global correlation among various bands of panchromatic images and multispectral images. [Methods] In response to the above problems, this paper proposes a multispectral image pansharpening method based on a shallow-deep convolutional recurrent neural network, which consists of a shallow feature extraction sub-network and a deep feature fusion sub-network. By using recurrent neural networks to simulate the interaction between bands, the fusion effect is effectively enhanced. [Results] Tests were conducted on multiple datasets in the resolution reduction and full resolution experiments. The experimental results show that the proposed method is superior to the traditional full-color sharpening method in the quality of the fusion results. [Conclusion] The shallow feature extraction subnetwork extracts shallow features from PAN and MS images. The deep feature fusion subnetwork captures local and global correlations by establishing intra-view and inter-view relationships between bands, improving the performance of panchromatic sharpening of multispectral images.

Key words: pansharpening technology, deep learning, convolutional recurrent neural network, satellite remote sensing image