Traditional image feature matching methods cannot obtain satisfactory results for multimodal images in most cases because different imaging mechanisms bring significant nonlinear radiation distortion differences and geometric distortion. The key to multimodal image matching is trying to eliminate the nonlinear radiation distortion and extract more robust features. This article proposes a new robust feature matching method for multimodal images. Our method starts by detecting feature points on phase congruency maps in nonlinear scale space and then removing mismatches by progressive filtering. Specifically, the phase congruency maps are generated by the Log-Gabor filter (LGF). Then, the feature points on phase congruency maps are detected in nonlinear scale space constructed by the nonlinear diffusion filter. Subsequently, the structure descriptor is established by the LGF, and the initial correspondences are constructed by bilateral matching. Finally, an iterative strategy is used to remove mismatches by progressive filtering. We perform comparison experiments on our proposed method with the SIFT, RIFT, VFC, LLT, LPM, and mTopKPR methods using multimodal images. The algorithms of each method are comprehensively evaluated both qualitatively and quantitatively. Our experimental results indicate the superiority of our method over the other six matching methods.

Digital elevation models (DEMs) are indispensable in the fields of photogrammetry and remote sensing. During generating DEMs from multiview satellite images, nonvalues often occur in areas with cloud cover or water bodies, resulting in void areas. The existing interpolation or fusion methods for filling DEMs often struggle with the challenge of ensuring smooth elevation transitions at the seams, while deep-learning-based methods are encumbered by substantial memory and computational demands. To address these issues, this study proposes a simple adaptive DEM void filling method based on raster distance transform to reconstruct a complete topographic surface, using publicly available global DEMs as auxiliary data. First, an initial weight grid is created by performing distance transform on the mask of void areas. Then, the buffer zone and weight map for DEM fusion are adaptively determined by setting appropriate threshold in the initial weight grid. Finally, the target DEM is seamlessly fused with the auxiliary DEM according to the weight map. Comparative experiments conducted across different topographic terrains demonstrate the effectiveness of the proposed method in seamless DEM void filling. It achieves a substantial reduction in root mean square error (RMSE) of elevation differences at seams from 4.27 to 1.47 m, significantly mitigating the staircase effect in visual, and the simulation experiments also prove that this method has a higher terrain fidelity.

Due to different imaging mechanisms bringing significant nonlinear radiation differences, traditional feature matching methods are difficult to obtain satisfactory results for multispectral images. The key to multispectral image matching is eliminating the nonlinear radiation differences and extracting more robust features. This letter proposed a novel descriptor combining the phase consistency (PC) gradient and log-polar coordinates to solve the nonlinear radiation differences of multispectral images. Firstly, the nonlinear weighted moment (NWM) is constructed for detecting feature points. Then, the PC model is extended to construct the absolute phase consistency orientation gradient. Combined with the log-polar description, the histogram of phase consistency gradients (HPCG) is established. Finally, a purification algorithm with dynamic adaptive Euclidean distance and FSC constraints is proposed to eliminate mismatches while retaining the correct matches. The proposed HPCG descriptor was evaluated using six groups of multispectral images. The experimental results show that our method is better than the other seven descriptors (i.e., SIFT, EOH, EHD, LGHD, PCEHD, OSSIFT, and HOSS), which have strong adaptability and robustness.

The multi-source remote sensing images in mountainous areas are affected by variations in resolution, imaging angles, and atmospheric conditions, resulting in significant nonlinear radiation and geometric distortion discrepancies among the images, which pose a huge challenge to image matching. This article introduces a multi-source remote sensing image matching method specifically for mountainous areas based on spatial structural features. By mining stable structural information and combining multi-scale feature expression with log-polar coordinate measurement, the accuracy of the matching algorithm is improved. Firstly, we calculate the phase consistency structure map and use bilateral filtering to extract spatial structural features from the multi-source remote sensing images. Secondly, a nonlinear scale space is constructed using a nonlinear diffusion function, and a nonlinear weighted moment map is generated using the Log-Gabor filtering. The Harris algorithm is utilized to detect feature points within the nonlinear weighted moment map. Subsequently, the phase consistency direction is extended to generate absolute phase consistency direction features, and then the log-polar coordinate description framework is combined to calculate the feature vectors. Finally, the bilateral matching method is applied to obtain the initial feature correspondence, and the fast sample consensus algorithm is used to eliminate mismatches and achieve highprecision feature correspondence. The experimental results show that our proposed method significantly enhances both the number of correct matches as well as the correct matching rate and overall matching accuracy when compared with traditional methods, providing effective technical support for applications such as remote sensing image fusion and change detection in mountainous areas.

Significant nonlinear radiation differences and weak texture differences exist between multimodal weak texture remote sensing images (MWTRSIs). When using traditional methods to match MWTRSIs, the low distinguishability of descriptors in weak texture regions results in poor matching performance. A robust matching method is proposed based on normalized structural feature transform (NSFT), which can extract spatial structural features of images while mitigating nonlinear radiation differences between weak texture regions. First, the bilateral filter is used to transform the weak texture remote sensing image into a normalized image, which not only greatly weakens the nonlinear radiation difference but also retains most of the structural information. Then, the UC-KAZE detector is designed to extract many evenly distributed feature points on the normalized image. Subsequently, a multimodal weak texture feature descriptor with rotation invariance is designed based on the self-similarity of the weak texture image. Finally, the initial correspondences are constructed by bilateral matching, and the mismatches are removed by the fast sample consensus (FSC) algorithm. We perform comparison experiments on eight types of MWTRSIs. The results show that the proposed method has good scale and rotation invariance and good resistance to nonlinear radiation differences and weak texture differences.

The equator’s unique combination of high humidity and temperature renders optical satellite imagery highly susceptible to persistent cloud cover. In contrast, synthetic aperture radar (SAR) offers a robust alternative due to its ability to penetrate clouds with microwave imaging. This study addresses the challenges of cloud-induced data gaps and cross-sensor geometric biases by proposing an advanced optical and SAR image-matching framework specifically designed for cloud-prone equatorial regions. We use a prompt-driven visual segmentation model with automatic prompt point generation to produce cloud masks that guide cross-modal feature-matching and joint adjustment of optical and SAR data. This process results in a comprehensive digital orthophoto map (DOM) with high geometric consistency, retaining the fine spatial detail of optical data and the all-weather reliability of SAR. We validate our approach across four equatorial regions using five satellite platforms with varying spatial resolutions and revisit intervals. Even in areas with more than 50 percent cloud cover, our method maintains sub-pixel edging accuracy under manual check points and delivers comprehensive DOM products, establishing a reliable foundation for downstream environmental monitoring and ecosystem analysis.