MSG: Robust Multimodal Remote Sensing Image Matching Using Side Window Gaussian Space

Abstract

Robust and accurate image matching and registration are foundational tasks for numerous applications. However, current methods often fail when dealing with multimodal remote sensing images (MRSIs) that exhibit significant spatial geometric differences (SGDs) and nonlinear radiometric differences (NRDs). To address these challenges, this article proposes a novel MRSI matching (MRSIM) method: matching using side window Gaussian space (MSG). MSG leverages an intuitive concept that human visual perception relies heavily on salient features at image edges for precise matching. Specifically, the proposed method: 1) constructs a multiscale side window Gaussian filter scale space (MSGSS) that preserves edge information at different scales while blurring the image; 2) enhances the repeatability of keypoints by performing corner detection on edge maps; 3) increases descriptor robustness by using second-order gradients combined with steerable filtering; and 4) further utilizes a two-stage matching strategy within a constrained search space and designs a new distance, making full use of densely distributed edge keypoints. Quantitative and qualitative experiments conducted on five datasets spanning 957 image pairs across nine multimodal types demonstrate that MSG outperforms nine advanced algorithms (six feature-based methods: SIFT, OS-SIFT, RIFT, CoFSM, HOWP, and POS-GIFT; and three deep learning-based methods: SuperPoint + SuperGlue, LoFTR, and ReDFeat). The results indicate that MSG achieved a number of correct matches (NCMs) much higher than the compared algorithms, with the highest success rate (SR), lowest RMSE, and good time efficiency while achieving both scale and rotation invariance. Codes are available at https://github.com/ZCYla/MSG