Deep learning approaches that jointly learn feature extraction have achieved remarkable progress in image matching. However, current methods often treat central and neighboring pixels homogeneously and rely on static feature selection strategies, which fail to account for environmental variations. This results in limited robustness of descriptors and keypoints, thereby affecting matching accuracy. To address these limitations, we propose a robust joint optimization network for feature detection and description in optical and SAR image matching. A Center-Weighted Module (CWM) is designed to enhance local feature representation by emphasizing the hierarchical relationship between central and surrounding features. Furthermore, a Multi-Scale Gated Aggregation (MSGA) module is introduced to suppress redundant responses and improve keypoint discriminability through a gating mechanism. To address the inconsistency of score maps across heterogeneous modalities, we design a position-constrained repeatability loss to guide the network in learning stable and consistent keypoint correspondences. Experimental results across various scenarios demonstrate that the proposed method outperforms state-of-the-art techniques in terms of both matching accuracy and the number of correct matches, highlighting its robustness and effectiveness.

Soil organic carbon density (SOCD) in swamp wetlands is a critical indicator for assessing global carbon stocks. In plateau wetlands, challenges such as dense vegetation cover and fragmented land distribution complicate SOCD research. The availability of high-resolution optical and radar satellite data introduces new possibilities for precise carbon stock predictions. This study proposes a framework that combines multisource remote sensing data with the sparrow search algorithm random forest (SSA-RF) algorithm to predict SOCD in plateau swamp wetlands. It also compares the effectiveness of laboratory spectroscopy and multisource remote sensing in monitoring SOCD. We integrated 24 features from Sentinel-1 (S1), Sentinel-2 (S2), topographic, and climatic data, along with spectral data ranging from 550 to 1400 nm, to construct the SSA-RF model and map the SOCD distribution of swamp wetlands in Dianchi Basin. Additionally, we estimated the total soil organic carbon (SOC) stock in these wetlands. The results indicate that the multisource remote sensing SSA-RF model (S1+ S2+ topographic + climatic SSA-RF) achieved an$R ^{2}$of 0.76, a root-mean-square error (RMSE) of 1.14, a mean absolute error (MAE) of 0.65, and a residual predictive deviation (RPD) of 1.98. Compared to the spectral model, this model improved the$R ^{2}$by 0.24 and the RPD by 0.5. Relative to the S1+ S2 SSA-RF model, the$R ^{2}$is increased by 0.15, and the RMSE is decreased by 0.46. The total SOC stock of the swamp wetlands in the Dianchi Basin was estimated to be$1.32\times 10^{5}~t$. This study provides a new framework for predicting carbon stocks in plateau wetlands, offering a reference for global wetland carbon sink assessments.

This study presents a framework for predicting the total carbon storage of wetlands based on machine learning models that integrate Sentinel-1 (S1), Sentinel-2 (S2), the Digital Elevation Model (DEM), and climatic data. The results indicated that the Random Forest (RF) model outperformed the Support Vector Machine (SVM) and Extreme Gradient Boosting (XGB) models in prediction accuracy. With an R-squared value of 0.67 for aboveground biomass carbon density, 0.75 for belowground biomass carbon density, and 0.65 for soil organic carbon density. The predictive performance utilizing multi-source data is significantly superior to that of single indicators, and the inclusion of climate data enhances the model’s predictive capabilities. The total carbon storage of wetlands in the Yunnan-Kweichow Plateau is estimated at 55.5 MtC, comprising 13.8 MtC in aboveground biomass carbon, 7.6 MtC in belowground biomass carbon, and 34.1 MtC in soil organic carbon.

Mountainous land surface temperature (MLST) is a key parameter for the research of mountainous climate change. In this study, an improved method was developed to retrieve the MLST by considering the multiple scattering between pixels over rugged mountainous surfaces based on sky view factors (SVF). The method was applied to the Landsat-9 thermal infrared (TIR) remote sensing data by using the single channel (SC) algorithm. Due to the lack of measured data, the discrete anisotropic radiative transfer (DART) model is used to validate the accuracy of MLST retrieved by the proposed method. The results show that the MLST retrieved has high precision. The findings demonstrated the need for multiple scattering between pixels was taken into account in the retrieval of high-precision MLST under certain conditions.

Estimating the orientations of remote sensing images is a very important step in remote sensing image matching and is now gradually receiving widespread attention. However, due to the inability to explicitly define the standard orientations of feature points, the current methods still produce feature point orientation estimation errors, resulting in reduced matching accuracy. In this letter, we propose a multiscale unsupervised orientation estimation method with transformers, in which we use a multiscale feature extraction module to aggregate rich semantic features and a transformer-based attention mechanism module to address robust feature extraction in weakly textured regions while predicting the orientations of feature points through a carefully designed loss function. We set up image matching experiments on remote sensing images in different scenes for comparison purposes, and the experimental results show that our proposed method achieves substantially improved orientation estimation accuracy and improved image matching performance.

Optical and synthetic aperture radar (SAR) image keypoint detection is an important foundation for multimodal remote sensing image matching. The influence of nonlinear radiometric differences and geometric deformation between optical and SAR images leads to low repeatability of existing keypoint detection methods. To address the problem that existing keypoint detection methods cannot provide the required homonymous points for heterogenous image matching, we propose a keypoint detection method (SKD-Net) for optical and SAR images, and improve it in terms of both network structure and network optimization. First, we propose a multilevel attention Siamese network, which is composed of multiple convolutional modules and transformer modules with shared weights to extract common features at different levels for keypoint detection. We introduce a transformer module in the keypoint detection pipeline and fuse shallow and deep features to obtain more spatial and rich semantic information to facilitate heterogeneous image keypoint detection. Then, to ensure that the detected keypoints have more homonymous points and localization accuracy, we propose a position consistent loss. Unlike previous loss functions, our designed position-consistent loss function takes the differences between heterogeneous image score maps into account, and it autonomously selects the optimized correct point pairs to enable the network to perform correct learning. Finally, extensive experiments show that our detection method outperforms the current state-of-the-art keypoint detection methods in terms of repeatability, localization accuracy, and matching performance. Our source code is available at https://github.com/zhangschen/ SKD-Net.

Due to the significant nonlinear intensity changes of multispectral images, automatic image feature point matching is a challenging task. This letter addresses the problem and proposes a novel descriptor combining the structure and texture information to solve the nonlinear intensity variations of multispectral images. We first propose directional maps, i.e., the directional response maps (DMs) and the directional response binary maps (DBMs), which can capture the common structure and texture properties of multispectral images, respectively. We then use the spatial pooling pattern of the histogram of oriented gradients to separately describe the local region of each point of interest based on the DMs and DBMs. In order to speed up the calculation, we apply Gaussian filters to the DMs and average filters to the DBMs to construct the per-pixel histogram bins. Finally, we conjoin the normalized feature vectors corresponding to the structure description and texture description of each point of interest to obtain the histograms of directional maps (HoDMs). The proposed HoDM descriptor was evaluated using three data sets composed of images obtained in both visible light and infrared spectra. The experimental results confirm that the proposed HoDM descriptor is robust to the nonlinear intensity changes of multispectral images and has a superior matching performance as well as a much higher computational efficiency.

As a fundamental problem, spatial resection based on collinearity equations has been a subject of study since the beginning of photogrammetry. Owing to the nonlinearity of collinearity equations, the standard Newton-Raphson method requires approximate values for unknown parameters. Therefore, the method is inapplicable to modern oblique photogrammetry. In this letter, we propose a new altitude spatial resection algorithm that combines closed-form solutions and iterative solutions. In this algorithm, a set of homotopy algorithm solutions is first selected as the initial value on the basis of the minimum sum of the squared errors. Quasi-Newton method is then used for nonlinear iteration. Experimental results obtained from different data sets indicate excellent performance compared with serial implement.

Inclined imaging is an advanced sensing technique, and has been extensively used. Therefore, large-rotation angle photogrammetric resection has become an important topic. However, traditional iterative methods are limited by requiring good initial values. By contrast, noniterative methods do not require an initial value, although they exhibit relatively low accuracy and robustness. To obtain results with superior precision and universality, this letter proposes an improved approach by modifying the initial value acquisition and iterative methods. This algorithm uses nonlinear iteration to reduce the model error, thereby possibly achieving an exceptional convergence for large-rotation-angle photogrammetric resection. Experimental results on the real data indicate that the proposed algorithm outperforms the previous methods.