Comparative Evaluation of Traditional and Deep Learning Feature Matching Algorithms using Chandrayaan-2 Lunar Data
This work addresses image registration challenges for lunar exploration, enabling better surface mapping and mission planning, but it is incremental as it applies existing methods to new lunar data.
The study tackled the problem of aligning lunar images from diverse sensors by evaluating five feature matching algorithms, finding that the deep learning-based SuperGlue method achieved the lowest root mean square error and fastest runtimes, while classical methods like SIFT and AKAZE performed well near the equator but degraded under polar lighting conditions.
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.