Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost aggregation, whereas the latter often lacks the ability to model non-local contextual information. These methods exhibit poor compatibility on resource-constrained mobile devices, limiting their deployment in real-time applications. To address this, we propose a Multi-frequency Adaptive Fusion Network (MAFNet), which can produce high-quality disparity maps using only efficient 2D convolutions. Specifically, we design an adaptive frequency-domain filtering attention module that decomposes the full cost volume into high-frequency and low-frequency volumes. Subsequently, we introduce a Linformer-based low-rank attention to adaptively aggregation high- and low-frequency information, yielding more robust disparity estimation. Extensive experiments demonstrate that the proposed MAFNet significantly outperforms existing real-time methods on public datasets such as Scene Flow and KITTI 2015, showing a favorable balance between accuracy and real-time performance.

Accurate lunar rock detection is vital for lunar exploration. However, the existing methods are sensitive to factors, such as the uneven lighting and terrain relief. To address these issues, a novel method combining multiscale phase feature type maps (PFTMs) and phase congruency moment maps (PCMMs) is proposed. First, rock seeds are detected through phase congruency and gradient analysis. Second, a strategy called the local scale saliency score (LSSS) is proposed to adaptively estimate the optimal scale layer for candidate rock detection. Within this layer, the specifically designed local-contextual and global-contextual (LGC) features are employed to identify the regions of interests (ROIs) for rocks. Subsequently, the process of filtering false positives (FPs) involves the utilization of geometric metrics and scale feature analysis. Finally, a specially designed edge detector named the bilateral local maximum PCMM-PFTM path is proposed to describe the edges of the rocks. Tests on Chang’E-3 and Chang’E-5 Landing Camera (LCAM) images show the proposed method’s robustness in detecting lunar rocks of varying sizes and reflectance, achieving F1-scores ranging from 0.919 to 0.947.

The mineral composition of lunar regolith influences brightness temperature (TB) as observed by the microwave radiometer (MRM); however, the large-scale spatial relationship between TB and mineral abundance has yet to be sufficiently revealed. This study aims to quantify the impact of specific mineral abundances (plagioclase and ilmenite) on TB distribution, using MRM 37-GHz data from Chang’E-2 and mineral abundance products from Kaguya. We applied hour angle correction and latitude normalization to produce high-accuracy TB maps and developed a self-adaptive moving-window method to remove strip noise to produce higher precision mineral abundance maps. Using these two types of maps, we performed comprehensive large-scale spatial analysis of TB and mineral abundance using a bivariate spatial autocorrelation model and a geographically weighted regression (GWR) approach considering spatial similarity and heterogeneity, respectively. The bivariate analysis indicates a negative spatial correlation between TB and plagioclase abundance, while a positive spatial correlation between TB and ilmenite abundance. In addition, bivariate anomalies, including both hot and cold spots of diurnal TB amplitude (i.e., noon minus nighttime), were identified through the simultaneous consideration of TB and mineral abundance. The GWR analysis reveals regional variations in the impact of mineral abundances on diurnal TB amplitudes. These correlations can be attributed to the spatial distributions and variations in TB, which arise from the unique dielectric and thermal properties of minerals across distinct regions on the Moon. These findings contribute to a better understanding of subsurface thermal behavior and regimes, enhancing our comprehension of lunar evolution.

Accurate simulation of subsurface physical temperatures in lunar south polar craters is essential for thermal environment analysis in landing site selection. In this study, we developed an improved method for simulating large-scale subsurface temperature by integrating multi-source datasets, including Lunar Reconnaissance Orbiter (LRO) DEM, LRO Diviner infrared brightness temperature (TB), and Chang’E-2 microwave TB. The proposed method accounts for differences in heat sources between non-permanently shaded regions (non-PSR) and permanently shaded regions (PSR) craters, applying effective solar irradiance with terrain effect for non-PSR craters, and calibrated infrared TB with emissivity effect for PSR craters. Additionally, we incorporated key model parameters, including an annual model period and updated thermal conductivity, into a one-dimensional (1-D) heat transfer model. This method was applied to simulate subsurface temperatures (0–2 m depth) in lunar south polar craters, validated by the microwave radiative transfer model and observed microwave TB data. The simulation results indicate that temperatures near the lunar south polar are generally lower than those in the 80°-85°S latitude range. These temperature profiles can be applied to quantitatively estimate the detection depths of heat flow and buried water ice. Furthermore, the model period considering seasonality shows a stronger impact on temperature simulations than other model parameters — altering temperatures by 20–40 K in non-PSR and by 20–30 K in PSR. Our method and findings provide valuable insights for future scientific exploration of the lunar south pole region and contribute to a better understanding of subsurface thermal evolution.

The positioning accuracy of synthetic aperture radar (SAR) images is affected by factors, such as satellite platform instability, aging of on-board instruments, and environmental changes. Geometric calibration is a commonly employed and cost-effective method to enhance the positioning accuracy of SAR images. The classical point-based geometric calibration (PB-GC) model, however, only utilizes the location of ground control points (GCPs) and does not fully exploit the spatial relationships among the GCPs. This study introduces a high-precision geometric calibration method that builds upon the classical model for calibrating SAR imaging systems. This method incorporates the Co-Line-GC and Co-Circle-GC models, where the former uses GCPs distributed on a line while the latter uses GCPs distributed on a circle. The results reveal that, compared to the classical model, our approach enhances the positioning accuracy of Gaofen-3 and Sentinel-1A SAR images by approximately 2 m in eastern China, achieving a mean positioning accuracy of 3.02 m. In terms of calibration performance, a comparison between postcalibrated and precalibrated images indicates that the images are shifted, not distorted, and a better match of the same features between different scenes in the image mosaic is observed after calibration. The improved positioning accuracy of SAR images significantly contributes to global remote sensing mapping, land use change monitoring, and ground target detection applications.

The investigation of small lunar craters holds scientific and engineering significance. This paper presents a novel method for detecting small lunar craters. It consists of three stages: seed detection, candidate crater detection, and crater evaluation. Firstly, crater seeds are identified through morphological operations as pixels with the highest local gradient and specific gradient direction. Secondly, the optimal scale for each seed is estimated based on the maximum response of the established phase congruency maximum moment (PCMM) scale space. For detecting very small craters, a crater detector called statistical morphological constraint path-sets (SMPS), which leverages image spatial domain features, is proposed. It configures the image as a weighted directed graph, using path-sets centered on seeds to flexibly detect highlights and shadow regions of craters. For detecting craters with larger optimal scale, another crater detector named structural consistency constrained multi-paths (SCMP) is proposed, utilizing the frequency phase features. The core idea of SCMP is to configure the phase feature type (PFT) map with the optimal scale as a directed graph. Centered on the seed, the multi-path operator is designed to detect craters. Unsupervised discriminative correlation filters (UDCFs) are trained with HOG features from images or PFT maps to validate candidate craters. The results indicate that for images with a resolution of 0.5-2m/pixel, the proposed method demonstrates good detection performance for small craters with diameters of less than 5 m, 5-10 m, and greater than 10 m, with an average detection rate of 0.89, 0.91, and 0.92, respectively.

Accurate detection of the multiple classes in aerial images has become possible with the use of anchor-based object detectors. However, anchor-based object detectors place a large number of preset anchors on images and regress the target bounding box while anchor-free object detections predict the location of objects directly and avoid the carefully predefined anchor box parameters. Object detection in aerial images is faced with two main challenges: 1) the scale diversity of the geospatial objects; and 2) the cluttered background in complex scenes. In this letter, to address these challenges, we present a novel Anchor-Free Network with a Density map and attention mechanism (DA2FNet). Considering the extreme density variations of the detection instances among the different categories in aerial images, the proposed DA2FNet model conducts density map estimation with image-level supervision for the geospatial object counting, to acquire global knowledge about the scale information. A simple and effective image-level global counting loss function is also introduced. In addition, a compositional attention network is further introduced to enhance the saliency of the foreground objects. The proposed DA2FNet method was compared with the state-of-the-art object detection models, achieving excellent performance on the NWPU VHR-10, RSOD, and DOTA datasets.

Conventional subpixel mapping (SPM) is performed based on the abundance maps obtained by spectral unmixing (SU), to interpret the mixed pixels and improve the mapping resolution for hyperspectral remote-sensing imagery. However, the SU and SPM tasks are separately conducted, so that the unmixing error is propagated to SPM, and the mapping result is strongly reliant on the quality of the abundance maps. In this article, a novel joint SPM and SU framework (MO_SUSM) based on multiobjective optimization is proposed to simultaneously perform unmixing and mapping. Specifically, the multiobjective joint optimization model with a data fidelity term and a Laplacian prior term is constructed for SU and SPM. For the data fidelity term, since the unmixing result can be recovered by downsampling the mapping result, the unmixing model is joined with the mapping model by the downsampling matrix, so that the reconstruction errors of the unmixing and mapping results can be minimized together. Meanwhile, the Laplacian prior term is used to maximize the spatial dependence of the mapping result and provide the spatial constraint for SU. In addition, the multiobjective optimization algorithm with local search is designed to search for the optimal unmixing and mapping results that can balance the objective terms. Since the two objective terms are dynamically integrated during optimization, there is no need to set sensitive weights for the objectives combination. Four experiments were conducted on hyperspectral images of various data sources, including ground, airborne, and satellite images. The unmixing results show that MO_SUSM can reduce the unmixing error and can improve the quality of the abundance maps. The mapping results show that MO_SUSM can alleviate the dependence of SPM on the abundance maps and can improve the mapping accuracy.

Crater detection from planetary images is a challenging issue due to the complicated variations in geometry shape, illumination, and scale. An automatic crater detection algorithm (CDA) that is robust to these factors is, therefore, necessary. In this article, a novel automatic CDA that is robust to these factors is proposed to detect the multiscale craters of the Moon. The proposed method consists of two main steps: 1) in the hypothesis generation (HG) step, a novel feature operator called the path-profile, which is constructed based on the self-defined adjacency graph and a path descriptor, is presented to derive the highlight-shadow feature of craters for detecting candidate craters. 2) In the hypothesis verification (HV) step, based on the idea of anomaly detection, the isolation forest algorithm which is an unsupervised learning anomaly detection method is applied to eliminate falsely detected craters. Lunar Reconnaissance Orbiter Camera Wide Angle Camera and Narrow Angle Camera images and Chang’E-4 landing camera images were used to test the accuracy and robustness of the proposed method. The experimental results indicate that: on average, the accuracy of the detection result of the HG step is about 90%, and the HV step can further improve this by 3%–4%. The proposed method is a reliable way to detect multiscale lunar craters for various resolutions images with diameters ranging from five pixels to hundreds of pixels, and it is robust to the different terrains and illumination conditions on the Moon.

Subpixel mapping (SPM) is a useful technique that can interpret the spatial distribution inside mixed pixels and produce a finer-resolution classification map for hyperspectral remote-sensing imagery. However, SPM is essentially an ill-posed problem that requires additional information to produce the unique solution. The limited information of a single image is insufficient to make the mapping problem well posed, whereas the complementary spatial information of multiple shifted images is able to reduce the uncertainty and generate an accurate map. The maximum a posteriori model is a feasible way to incorporate auxiliary information for SPM with multiple shifted images, but it introduces a sensitive regularization parameter, which is difficult to preset. Furthermore, the fixed parameter in the iterations influences the incorporation of the multiple images and the spatial prior. In this article, to address these issues, a multiobjective SPM framework for use with multiple shifted hyperspectral images (MOMSM) is proposed. In the proposed algorithm, a multiobjective model consisting of two objective functions, i.e., data fidelity and spatial prior terms, is constructed to transform the SPM into a multiobjective optimization problem, to get rid of the sensitive regularization parameter. To simultaneously optimize the two objective functions, a multiobjective memetic algorithm with a local search operator and an adaptive global replacement strategy is proposed. The multiple images and spatial information can be dynamically fused and the optimal mapping solution with a good balance between the two objectives can be finally obtained. Experiments conducted on both synthetic and real data sets confirm that the proposed method outperforms the other tested SPM algorithms.

Crop classification and mapping are important to socioeconomic, food safety, and policy-making. Accurate and timely spatial distribution of crop types based on remote sensing is important for both scientific and practical purposes. However, the existing studies mostly focused on main crops, such as winter wheat, paddy rice and some others. For the garlic crop, there is few relevant research available. So in this paper, in order to explore the feasibility of garlic extraction, a preliminary experiment of garlic mapping based on random forest (GMRF) is carried out with multi-temporal 10-m resolution Sentinel-2 images, by taking Jinxiang County, Shandong Province, China as the experimental area. The experimental results suggest that the proposed GMRF method can achieve a good performance, with an overall accuracy (OA) of 98.56% and a kappa coefficient of 0.967.

The spatio-temporal pattern of cultivated land and its changes are of great significance in the study of ecology, geography and agronomy. In this study, long time series remote sensing information is used to monitor the spatio-temporal pattern and phenological characteristics of cultivated land on Chongming Eco-island, Shanghai, China. Based on MODIS-NDVI products (2012-2018), NDVI expectations curves of Chongming Eco-Island are established. It is demonstrated that the negative peaks of NDVI expectation curve in June become less noticeable after 2016. After that, NDVI image difference is performed between the time points at the positive peaks and negative peaks. The results indicate that the reason for the NDVI pattern changes these years may be related to the policy that wheat reduction and green manure enhancement implemented in Chongming Eco-island. Therefore, crops are diversified, and the phenological period of crops on the island is no longer sheer two cropping per year. This study is helpful to the ecological structure adjustment of Chongming Eco-island and the scientific management of cultivated land.

The Fourier-based image correlation technique has been widely concerned due to its accuracy, efficiency, and robustness to image contrast and brightness. Accordingly, a variety of subpixel methods have been proposed. However, the detailed subpixel-level influence of the complicated radiometric variations has yet to be investigated, and few corresponding improvements have been made. This paper presents a novel illumination-robust subpixel Fourier-based image correlation method based on phase congruency. Both the magnitude and orientation information of the phase congruency features are adopted to construct a structural image representation. The image representation is then embedded into the correlation scheme of the subpixel methods, either by linear phase estimation in the frequency domain or by kernel fitting in the spatial domain, achieving two improved subpixel methods. The proposed methods integrate the advantages of the structural image representation and the original correlation scheme, and make full use of both global and local phase information to achieve illumination-robust correlation. Experiments undertaken with both simulated and real radiometric differences were carried out with ground-truth subpixel shifts. The performances of the proposed methods and the other state-of-the-art subpixel Fourier-based correlation methods were evaluated and compared. The experimental results indicate that the proposed methods outperform the other methods in the presence of diverse radiometric variations, in both accuracy and robustness.

During recent years, many regularization techniques have been proposed to deal with ill-posed problems related to hyperspectral image classification, in which the limited number of training samples contrasts with the very high spectral dimensionality. However, the intrinsic structure of a hyperspectral image often depends on the specific scene and spectrometer, although regularizers like Ridge, LASSO, etc, have been widely used in practical applications. Instead of imposing these regularizers to the probabilistic output of a classifier, this work evaluates the use of extreme learning machines (ELM) with output weights of a single-hidden layer feed-forward neural network (SLFN) regularized with Ridge and LASSO priors, respectively. Experimental results with several real hyperspectral images are conducted to compare the performance and adaptation of these two regularizers with the the original ELM in classification scenarios.

Hyperspectral remote sensing image (HSI) clustering can be defined as the process of segmenting pixels into different sets that satisfy the requirement that the differences between sets are much greater than the differences within sets. According to the fast density peak-based clustering algorithm, we propose an unsupervised HSI clustering method based on the density of pixels in the spectral space and the distance between pixels. For the metric of the density, we present an adaptive-bandwidth probability density function using pixel numbers as the input and the calculated pixel local density as the output, which determines the bandwidth on the basis of the Gaussian assumption. For the metric of the distance, in order to obtain a pixel-level spectral distance, we calculate the Euclidean distance between pixel vectors from the multiple bands. In the proposed approach: 1) use the least-squares method for the curve fitting of the two results; 2) eliminate outliers based on the Pauta criterion; 3) adopt regression calculation; and 4) obtain the cluster centers according to the classification criteria of the local density and the distance between pixel vectors. The other noncluster center points are clustered based on their similarities with the cluster centers by iteration. Finally, we compare the results with those of other unsupervised clustering methods and the reference data sets.

In this paper, a new joint spectral-spatial subpixel mapping model is proposed for hyperspectral remotely sensed imagery. Conventional approaches generally use an intermediate step based on the derivation of fractional abundance maps obtained after a spectral unmixing process, and thus the rich spectral information contained in the original hyperspectral data set may not be utilized fully. In this paper, a concept of subpixel abundance map, which calculates the abundance fraction of each subpixel to belong to a given class, was introduced. This allows us to directly connect the original (coarser) hyperspectral image with the final subpixel result. Furthermore, the proposed approach incorporates the spectral information contained in the original hyperspectral imagery and the concept of spatial dependence to generate a final subpixel mapping result. The proposed approach has been experimentally evaluated using both synthetic and real hyperspectral images, and the obtained results demonstrate that the method achieves better results when compared to other seven subpixel mapping methods. The numerical comparisons are based on different indexes such as the overall accuracy and the CPU time. Moreover, the obtained results are statistically significant at 95% confidence.

A hierarchical method for subpixel surface water mapping accounting for the high spectral heterogeneity of urban materials is proposed in this paper. Specifically, we first applied water index (WI) for remote sensing image classification at pixel level, afterwards, the land, water, and land-water mixture can be extracted automatically. Then the spectral mixture analysis (SMA) is applied to land-water mixed pixels for water fraction estimation at subpixel level. To obtaining the most representative endmembers in SMA, we designed an adaptive iterative endmember selection method based on the spatial similarity of adjacent pixels. The proposed hierarchical processing method based on WI and SMA (WISMA) is applied to urban areas for reliability evaluation using the Landsat-8 Operational Land Imager (OLI) images. For comparison, four methods at pixel level and subpixel level were chosen respectively. Results indicate that the water maps generated by WISMA correspond as closely with the truth water maps with subpixel precision. And the results showed that the WISMA achieved the best performance in water mapping with comprehensive analysis of different accuracy evaluation indexes (RMSE and SE).

Hyperspectral image super resolution (SR) reconstruction has been studied widely and many algorithms have been proposed. In this paper, a novel super resolution reconstruction method was designed by employing a joint spectral-spatial sub-pixel mapping model which aims to obtain the probabilities of sub-pixels to belong to different land cover classes by dividing mixed pixels into several sub-pixels. Given these sub-pixel probabilities, the resolution enhanced image can be further generated. The proposed approach has been evaluated using both synthetic and real hyperspectral images and compared with other well-known methods. The visual and quantitative comparisons confirm the effectiveness of the proposed method.

Subpixel mapping, which is a promising technique based on the assumption of spatial dependence, enhances the spatial resolution of images by dividing a mixed pixel into several subpixels and assigning each subpixel to a single land-cover class. The traditional subpixel mapping methods usually utilize the fractional abundance images obtained by a spectral unmixing technique as input and consider the spatial correlation information among pixels and subpixels. However, most of these algorithms treat subpixels separately and locally while ignoring the rationality of global patterns. In this paper, a novel subpixel mapping model based on sparse representation theory, namely, adaptive sparse subpixel mapping with a total variation model (ASSM-TV), is proposed to explore the possible spatial distribution patterns of subpixels by considering these subpixels as an integral patch. In this way, the proposed method can obtain the optimal subpixel mapping result by determining the most appropriate subpixel spatial pattern. However, the number of possible spatial configurations of subpixels can increase sharply with large-scale factors, and therefore, in ASSM-TV, the subpixel mapping is considered as a sparse representation problem. A preconstructed discrete cosine transform dictionary, which consists of piecewise smooth subpixel patches and textured patches, is utilized to express the original subpixel mapping observation in a sparse representation pattern. The total variation prior model is designed as a spatial regularization constraint to characterize the relationship between a subpixel and its neighboring subpixels. In addition, a joint maximum a posteriori model is proposed to adaptively select the regularization parameters. Compared with the other traditional and state-of-the-art subpixel mapping approaches, the experimental results using a simulated image, three synthetic hyperspectral remote sensing images, and two real remote sensing images demonstrate that the proposed algorithm can obtain better results, in both visual and quantitative evaluations.

The subpixel mapping technique can specify the spatial distribution of different categories at the subpixel scale by converting the abundance map into a higher resolution image, based on the assumption of spatial dependence. Traditional subpixel mapping algorithms only utilize the low-resolution image obtained by the classification image downsampling and do not consider the spectral unmixing error, which is difficult to account for in real applications. In this paper, to improve the accuracy of the subpixel mapping, an adaptive subpixel mapping method based on a maximum a posteriori (MAP) model and a winner-take-all class determination strategy, namely, AMCDSM, is proposed for hyperspectral remote sensing imagery. In AMCDSM, to better simulate a real remote sensing scene, the low-resolution abundance images are obtained by the spectral unmixing method from the downsampled original image or real low-resolution images. The MAP model is extended by considering the spatial prior models (Laplacian, total variation (TV), and bilateral TV) to obtain the high-resolution subpixel distribution map. To avoid the setting of the regularization parameter, an adaptive parameter selection method is designed to acquire the optimal subpixel mapping results. In addition, in AMCDSM, to take into account the spectral unmixing error in real applications, a winner-take-all strategy is proposed to achieve a better subpixel mapping result. The proposed method was tested on simulated, synthetic, and real hyperspectral images, and the experimental results demonstrate that the AMCDSM algorithm outperforms the traditional subpixel mapping methods and provides a simple and efficient algorithm to regularize the ill-posed subpixel mapping problem.

The existence of mixed pixels is a major problem in remote-sensing image classification. Although the soft classification and spectral unmixing techniques can obtain an abundance of different classes in a pixel to solve the mixed pixel problem, the subpixel spatial attribution of the pixel will still be unknown. The subpixel mapping technique can effectively solve this problem by providing a fine-resolution map of class labels from coarser spectrally unmixed fraction images. However, most traditional subpixel mapping algorithms treat all mixed pixels as an identical type, either boundary-mixed pixel or linear subpixel, leading to incomplete and inaccurate results. To improve the subpixel mapping accuracy, this paper proposes an adaptive subpixel mapping framework based on a multiagent system for remote-sensing imagery. In the proposed multiagent subpixel mapping framework, three kinds of agents, namely, feature detection agents, subpixel mapping agents and decision agents, are designed to solve the subpixel mapping problem. Experiments with artificial images and synthetic remote-sensing images were performed to evaluate the performance of the proposed subpixel mapping algorithm in comparison with the hard classification method and other subpixel mapping algorithms: subpixel mapping based on a back-propagation neural network and the spatial attraction model. The experimental results indicate that the proposed algorithm outperforms the other two subpixel mapping algorithms in reconstructing the different structures in mixed pixels.

The sub-pixel mapping technique, which can provide a fine-resolution map of class labels, has attracted more and more attention in recent years. Generally speaking, there are two kinds of methods used to realize the sub-pixel labeling. The first kind are image reconstruction based methods, which first improve the spatial resolution of an image by the super-resolution technique, and then perform a hard classification on the super-resolved image. The second kind are pixel unmixing based methods, where the sub-pixel mapping is implemented based on the results of image unmixing. In this paper, we present a sparse representation method and a back-propagation (BP) neural network method for image reconstruction based and pixel unmixing based mapping, respectively. The advantages and disadvantages of both kinds of methods are analyzed and discussed.