对比五种匹配算法在月球多源图像中的表现，发现深度学习方法更优。
Comparative Evaluation of Traditional and Deep Learning Feature Matching Algorithms using Chandrayaan-2 Lunar Data
- 提出预处理流水线提升多模态月球图像对齐效果
- SuperGlue在极地和赤道均表现最佳，误差最低且速度最快
- 传统算法受光照影响大，需依赖预处理增强
精确的图像配准对月球探测至关重要，可用于表面制图、资源定位和任务规划。由于光学（如轨道高分辨率相机、窄/宽角相机）、红外光谱（成像红外光谱仪）和雷达（如双频合成孔径雷达、嫦娥二号/辉神任务）传感器之间存在分辨率、光照和畸变差异，跨模态图像配准极具挑战。本文评估了五种特征匹配算法：SIFT、ASIFT、AKAZE、RIFT2 和 SuperGlue（基于深度学习的匹配器），使用来自赤道和极区的多模态图像对。提出了一套预处理流程，包括地理定位、分辨率对齐、强度归一化，以及自适应直方图均衡化、主成分分析和阴影校正等增强技术。结果表明，SuperGlue 在所有条件下均实现最低的均方根误差和最快的运行时间；传统方法如 SIFT 与 AKAZE 在赤道表现良好，但在极地光照下性能显著下降。研究强调了预处理和基于学习的方法在复杂条件下实现鲁棒月球图像配准的重要性。
原文摘要 · Abstract (English)
Accurate image registration is critical for lunar exploration, enabling surface mapping, resource localization, and mission planning. Aligning data from diverse lunar sensors -- optical (e.g., Orbital High Resolution Camera, Narrow and Wide Angle Cameras), hyperspectral (Imaging Infrared Spectrometer), and radar (e.g., Dual-Frequency Synthetic Aperture Radar, Selene/Kaguya mission) -- is challenging due to differences in resolution, illumination, and sensor distortion. We evaluate five feature matching algorithms: SIFT, ASIFT, AKAZE, RIFT2, and SuperGlue (a deep learning-based matcher), using cross-modality image pairs from equatorial and polar regions. A preprocessing pipeline is proposed, including georeferencing, resolution alignment, intensity normalization, and enhancements like adaptive histogram equalization, principal component analysis, and shadow correction. SuperGlue consistently yields the lowest root mean square error and fastest runtimes. Classical methods such as SIFT and AKAZE perform well near the equator but degrade under polar lighting. The results highlight the importance of preprocessing and learning-based approaches for robust lunar image registration across diverse conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。