刘阳,宋钰,胡敬芳,李延生,高国伟

• 1:北京信息科技大学北京市传感器重点实验室
• 2:北京信息科技大学现代测控技术教育部重点实验室

摘要(Abstract)：

光学影像与合成孔径雷达（synthetic aperture radar, SAR）影像成像机制不同，简单融合或拼接方式无法自适应分配权重，会造成边界特征模糊、粘连等问题。为此，提出了渐进选择性融合网络（progressive selective fusion network,PSFNet）。在浅层保留各模态的原始纹理特征，在深层利用四元注意力模块（quaternion attention module, QAttn）进行跨模态语义的深度交互。同时，渐进式解码器可以逐级恢复空间细节，解决边缘模糊问题。在WHU-OPT-SAR数据集上的实验结果表明，PSFNet的总体准确率达86.2%，平均交并比达59.5%，与DeepLabv3、MCANet、CFFormer等主流分类模型相比有显著提升，且在结构复杂道路与细长水体等小尺度地物的识别上优势更加明显，为多源遥感数据的精细化分类提供了解决方案。

关键词(KeyWords)： 多源遥感融合;土地利用分类;注意力机制;语义分割

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(61901042,62071455)

作者(Author): 刘阳,宋钰,胡敬芳,李延生,高国伟

DOI: 10.16508/j.cnki.11-5866/n.2026.03.008

参考文献(References)：

• [1]严毅，邓超，李琳，等.深度学习背景下的图像语义分割方法综述[J].中国图象图形学报，2023,28(11):3342-3362.YAN Y,DENG C,LI L,et al. Survey of image semantic segmentation methods in the deep learning era[J]. Journal of Image and Graphics,2023,28(11):3342-3362.(in Chinese)
• [2]朱锦钊.基于深度学习的遥感图像语义分割技术研究与应用[J].价值工程，2023,42(34):109-111.ZHU J Z. Research and application of remote sensing image semantic segmentation technology based on deep learning[J].Value Engineering,2023,42(34):109-111.(in Chinese)
• [3]CHENG F F,FU Z T,HUANG L,et al. Review of deep learning in optical and SAR image fusion[J]. National Remote Sensing Bulletin,2022,26(9):1744-1756.
• [4]WANG X L,LIU B Z,GOU S P,et al. Cross-modal transformer and optimal transport for SAR-optical image matching[C]//IGARSS 2025:2025 IEEE International Geoscience and Remote Sensing Symposium. New York,USA:IEEE,2025:3034-3038.
• [5]WU W F,GUO S J,SHAO Z F,et al. CroFuseNet:a semantic segmentation network for urban impervious surface extraction based on cross fusion of optical and SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2023,16:2573-2588.
• [6]王关茗.基于深度学习的自然灾害遥感影像语义分割算法研究[D].青岛：青岛科技大学，2023.WANG G M. Research on semantic segmentation algorithm of natural disaster remote sensing image based on deep learning[D]. Qingdao:Qingdao University of Science and Technology,2023.(in Chinese)
• [7]ZHANG Y F,SIDIB??D,MOREL O,et al. Deep multimodal fusion for semantic image segmentation:a survey[J]. Image and Vision Computing,2021,105:104042.
• [8]张瑞，董张玉.一种改进的SAR与可见光图像融合算法[J].雷达科学与技术，2020,18(6):645-650.ZHANG R,DONG Z Y. An improved fusion of SAR and visible images[J]. Radar Science and Technology,2020,18(6):645-650.(in Chinese)
• [9]刘立，董先敏，刘娟.顾及地学特征的遥感影像语义分割模型性能评价方法[J].自然资源遥感，2023,35(3):80-87.LIU L,DONG X M,LIU J. A performance evaluation method for semantic segmentation models of remote sensing images considering surface features[J]. Remote Sensing for Natural Resources,2023,35(3):80-87.(in Chinese)
• [10]HUGHES L H,SCHMITT M,MOU L C,et al. Identifying corresponding patches in SAR and optical images with a pseudoSiamese CNN[J]. IEEE Geoscience and Remote Sensing Letters,2018,15(5):784-788.
• [11]GUO M H,XU T X,LIU J J,et al. Attention mechanisms in computer vision:a survey[J]. Computational Visual Media,2022,8(3):331-368.
• [12]SU H C, LIN B, HUANG X S, et al. MBFFNet:multi-branch feature fusion network for colonoscopy[J]. Frontiers in Bioengineering and Biotechnology, 2021, 9:696251.
• [13]LI X,ZHANG G,CUI H,et al. MCANet:a joint semantic segmentation framework of optical and SAR images for land use classification[J]. International Journal of Applied Earth Observation and Geoinformation,2022,106:102638.
• [14]CHEN L C,PAPANDREOU G,KOKKINOS I,et al. DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
• [15]LI R, ZHENG S Y,ZHANG C,et al. Multiattention network for semantic segmentation of fine-resolution remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing,2022,60:5607713.
• [16]CHEN L C,ZHU Y K,PAPANDREOU G,et al. Encoderdecoder with atrous separable convolution for semantic image segmentation[C]//Computer Vision-ECCV 2018. Berlin,Germany:Springer Verlag,2018:833-851.
• [17]FU J,LIU J,TIAN H J,et al. Dual attention network for scene segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Los Alamitos, CA,USA:IEEE Computer Society, 2019:3141-3149.
• [18]HOU Q B,ZHOU D Q,FENG J S. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Los Alamitos, CA, USA:IEEE Computer Society,2021:13708-13717.
• [19]HE K M,ZHANG X Y,REN S Q,et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Los Alamitos, CA,USA:IEEE Computer Society, 2016:770-778.
• [20]WANG J D,SUN K,CHENG T H,et al. Deep high-resolution representation learning for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,43(10):3349-3364.
• [21]HOSSEINPOUR H,SAMADZADEGAN F,JAVAN F D.CMGFNet:a deep cross-modal gated fusion network for building extraction from very high-resolution remote sensing images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2022,184:96-115.
• [22]ZHANG J M,LIU H Y,YANG K L,et al. CMX:cross-modal fusion for RGB-X semantic segmentation with transformers[J].IEEE Transactions on Intelligent Transportation Systems,2023,24(12):14679-14694.
• [23]YANG X,LI S S,CHEN Z C,et al. An attention-fused network for semantic segmentation of very-high-resolution remote sensing imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2021,177:238-262.
• [24]ZHAO J Q,ZHANG M,ZHOU Z H,et al. CFFormer:a crossfusion transformer framework for the semantic segmentation of multisource remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing,2025,63:4401117.