首页|期刊导航|太赫兹科学与电子信息学报|EnhancedXFeat:一种SAR图像和光学图像配准方法

EnhancedXFeat:一种SAR图像和光学图像配准方法OA

EnhancedXFeat:a registration method for SAR image and optical image

中文摘要英文摘要

针对合成孔径雷达(SAR)与光学图像因成像机理、噪声特性和纹理差异导致的跨模态配准难题,特别是低纹理SAR图像特征提取困难、域差异大以及现有方法计算开销高等问题,提出一种基于快速图像特征匹配(XFeat)网络的改进算法EnhancedXFeat.该算法通过倍增主干网络关键模块通道数增强浅层细节保留和深层语义区分能力,引入跨模态双分支结构独立处理模态特异性特征,并两次应用双注意力机制有效解决域差异问题,提升对低纹理图像的特征提取与融合效果.在自建数据集上的对比实验结果表明,EnhancedXFeat的平均检测特征点数达37.0个,远高于尺度不变特征变换(SIFT)的4.3、定向FAST和旋转BRIEF(ORB)的6.2和SAR与光学配准网络(OSMNet)的 17.9;匹配正确率达 88.1%,显著优于 SIFT 的 9.2%、ORB 的 12.7%、OSMNet 的68.0%和视觉几何组16(VGG-16)的68.7%;同时单次运算时间控制在0.801 2 s,在精度和效率上实现了良好平衡.EnhancedXFeat算法有效提升了SAR与光学图像配准的精度和鲁棒性,其轻量化架构为资源受限环境下的多源遥感图像配准应用提供了高效可靠的解决方案.

To address the cross-modal registration challenges between Synthetic Aperture Radar(SAR)and optical images,which arise from differences in imaging mechanisms,noise characteristics,and textures—particularly the difficulties in feature extraction from low-texture SAR images,significant domain disparities,and high computational costs of existing methods—this study proposes an improved algorithm named EnhancedXFeat based on the Accelerated Features(XFeat)network.The algorithm enhances the ability to preserve shallow-level details and distinguish deep-level semantics by doubling the number of channels in key modules of the backbone network;introduces a cross-modal dual-branch structure to independently process modality-specific features;and applies a dual attention mechanism twice.These designs effectively resolve the domain difference issue and improve the performance of feature extraction and fusion for low-texture images.Comparative experimental results on a self-constructed dataset demonstrate that EnhancedXFeat outperforms mainstream algorithms significantly:the average number of detected feature points reaches 37.0,which is much higher than 4.3 of Scale-Invariant Feature Transform(SIFT),6.2 of Oriented FAST and Rotated BRIEF(ORB),and 17.9 of Optical-SAR Match Net(OSMNet);the matching accuracy achieves 88.1%,remarkably superior to 9.2%of SIFT,12.7%of ORB,68.0%of OSMNet and 68.7%of VGG-16;meanwhile,the single-operation time is controlled to 0.801 2 s,achieving a favorable balance between accuracy and efficiency.The conclusion indicates that EnhancedXFeat effectively improves the accuracy and robustness of SAR-optical image registration through its targeted design,and its lightweight architecture provides an efficient and reliable solution for multi-source remote sensing image registration applications in resource-constrained environments.

周郁植;张海洋;李元吉;辛乐;赵长明

光电成像技术与系统教育部重点实验室,北京 100081||北京理工大学 光电学院,北京 100081光电成像技术与系统教育部重点实验室,北京 100081||北京理工大学 光电学院,北京 100081南京电子技术研究所,江苏 南京 210039||雷达探测感知全国重点实验室,江苏 南京 210039南京电子技术研究所,江苏 南京 210039||雷达探测感知全国重点实验室,江苏 南京 210039光电成像技术与系统教育部重点实验室,北京 100081||北京理工大学 光电学院,北京 100081

信息技术与安全科学

图像配准合成孔径雷达(SAR)跨模态融合

image registrationSynthetic Aperture Radar(SAR)cross-modal fusion

《太赫兹科学与电子信息学报》 2026 (8)

909-918,10

10.11805/TKYDA2025202

评论