Search Results (38)

Lunar orbiter image matching is a critical process for achieving high-precision lunar mapping, positioning, and navigation. However, with the Moon’s weak-texture surface and rugged terrain, lunar orbiter images generally suffer from inconsistent lighting conditions and exhibit varying degrees of non-linear intensity distortion, which pose significant challenges to image traditional matching. This paper presents a robust feature matching method based on crater neighborhood structure, which is particularly robust to changes in illumination. The method integrates deep-learning based crater detection, Crater Neighborhood Structure features (CNSFs) construction, CNSF similarity-based matching, and outlier removal. To evaluate the effectiveness of the proposed method, we created an evaluation dataset, comprising Multi-illumination Lunar Orbiter Images (MiLOIs) from different latitudes (a total of 321 image pairs). And comparative experiments have been conducted using the proposed method and state-of-the-art image matching methods. The experimental results indicate that the proposed approach exhibits greater robustness and accuracy against variations in illumination. Full article

Aiming to address the fundamental limitation of fixed activation functions that constrain network expressiveness in existing deep deblurring models, in this pioneering study, we introduced Kolmogorov–Arnold Networks (KANs) into the field of full-color/RGB image deblurring, proposing the Kolmogorov–Arnold and Transformer Network (KT-Deblur) framework based on dynamically learnable activation functions. This framework overcomes the constraints of traditional networks’ fixed nonlinear transformations by employing adaptive activation regulation for different blur types through KANs’ differentiable basis functions. Integrated with a U-Net architecture within a generative adversarial network framework, it significantly enhances detail restoration capabilities in complex scenarios. The innovatively designed Unified Attention Feature Extraction (UAFE) module combines neighborhood self-attention with linear self-attention mechanisms, achieving synergistic optimization of noise suppression and detail enhancement through adaptive feature space weighting. Supported by the Fast Spatial Feature Module (FSFM), it effectively improves the model’s ability to handle complex blur patterns. Our experimental results demonstrate that the proposed method outperforms existing algorithms in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics across multiple standard datasets, achieving an average PSNR of 41.25 dB on the RealBlur-R dataset, surpassing the latest state-of-the-art (SOTA) algorithms. This model exhibits strong robustness, providing a new paradigm for image-deblurring network design. Full article

Three-dimensional mesh pose transfer transforms the pose of a source model into the pose of a reference model while preserving the source model’s identity (body detail). It has tremendous potential in computer graphics tasks. Current neural network-based methods primarily focus on extracting pose and body features, not entirely using the articulated body structure of humans and animals. We propose an end-to-end pose transfer network based on skinning deformation to address these issues. This network first extracts skinning weights and model joint features. Then, they are decoded to transfer the source model to a pose similar to the reference model while preserving the features of the source model. During feature extraction, we utilize the features of the k-nearest neighborhoods and one-ring neighborhoods to enable the network to learn the body details of the model better. Additionally, we apply skinning weights and joint features to capture the variation in the source model pose compared to the reference model pose and then use a decoding network to obtain the target model, replacing linear blend skinning. We conducted experiments on datasets such as SMPL, SMAL, FAUST, DYNA, and the MG dataset to provide empirical evidence and demonstrate that our method is the best in quantitative experiments. Our method efficiently transfers poses while better preserving the identity of the source model. Full article

Our aim is to contribute to understanding the role of subtropical trees on carbon storage and CO₂ removal in the city of Sao Paulo/Brazil, besides highlighting the surrounding environment implications to sibipiruna trees (Cenostigma pluviosum)’s performance. The case study was conducted with three trees, one planted on a sidewalk in Pinheiros neighborhood, a highly sealed area, and two in a green area, the Ibirapuera Park. To define the stem basal area growth and its pattern, local measurements were taken over a year and a segmented linear regression model was adjusted. The stem growth dependency on microclimate was tested by a Spearman Correlation. The trees’ active stem growth presented a similar pattern. The soil volumetric water content and soil temperatures were the variables with more impact. The total mean radial stem growth for the IBIRA1 and IBIRA2 trees was 1.2 mm year⁻¹ and 3 mm year⁻¹, while at PIN1 it was 1.3 mm year⁻¹. The total biomass increment in IBIRA1 and IBIRA2 was 4.2 kg C year⁻¹ and 12.8 kg C year⁻¹, while in PIN it was 4.9 kg C year⁻¹ and the removal was 15.3 C year⁻¹, 47.1 kg CO₂ year⁻¹ and 17.9 kg CO₂ year⁻¹, respectively. The results indicated that the land cover difference implies a significant interference with the promotion of carbon fixation and CO₂ removal, demonstrating that planting urban trees in soils with better water storage conditions is more efficient. Full article

The work proves that under conditions of instability of the second derivatives of the function in the minimization region, the estimate of the convergence rate of Newton’s method is determined by the parameters of the irreducible part of the conditionality degree of the problem. These parameters represent the degree of difference between eigenvalues of the matrices of the second derivatives in the coordinate system, where this difference is minimal, and the resulting estimate of the convergence rate subsequently acts as a standard. The paper studies the convergence rate of the relaxation subgradient method (RSM) with optimization of the parameters of two-rank correction of metric matrices on smooth strongly convex functions with a Lipschitz gradient without assumptions about the existence of second derivatives of the function. The considered RSM is similar in structure to quasi-Newton minimization methods. Unlike the latter, its metric matrix is not an approximation of the inverse matrix of second derivatives but is adjusted in such a way that it enables one to find the descent direction that takes the method beyond a certain neighborhood of the current minimum as a result of one-dimensional minimization along it. This means that the metric matrix enables one to turn the current gradient into a direction that is gradient-consistent with the set of gradients of some neighborhood of the current minimum. Under broad assumptions on the parameters of transformations of metric matrices, an estimate of the convergence rate of the studied RSM and an estimate of its ability to exclude removable linear background are obtained. The obtained estimates turn out to be qualitatively similar to estimates for Newton’s method. In this case, the assumption of the existence of second derivatives of the function is not required. A computational experiment was carried out in which the quasi-Newton BFGS method and the subgradient method under study were compared on various types of smooth functions. The testing results indicate the effectiveness of the subgradient method in minimizing smooth functions with a high degree of conditionality of the problem and its ability to eliminate the linear background that worsens the convergence. Full article

The built environment has been linked to physical activity (PA) behaviors, yet there is limited knowledge of this association among lower-income midlife and older adults who are insufficiently active. The present cross-sectional study utilized baseline data collected between October 2017 and November 2019 from a clustered randomized controlled trial to determine how built environment attributes were associated with PA behaviors among midlife and older adults (n = 255) residing in or near affordable housing sites (n = 10). At each site, perceptions of the built environment were collected and scored at the participant level via the abbreviated Neighborhood Environment Walkability Survey (NEWS-A), while objective built environment attributes were measured and scored by trained research staff using the Physical Activity Resource Assessment (PARA). Multiple PA behaviors—walking, total PA, and moderate-to-vigorous PA (MVPA) (min/wk)—were measured using the validated Community Healthy Activities Model Program for Seniors (CHAMPS) questionnaire. Adjusted linear regression models examined associations between NEWS-A measures and PA behaviors, and site-level correlations between PARA measures and PA behaviors were examined using Spearman’s rank correlations. At the participant level, adjusted models revealed that a one point increase in the NEWS-A aesthetics score was associated with a 57.37 min/wk increase in walking (β = 57.37 [95% CI: 20.84, 93.91], p = 0.002), with a similar association observed for street connectivity and MVPA (β = 24.31 min/wk [95% CI: 3.22, 45.41], p = 0.02). At the site level, MVPA was positively correlated with the quality of the features of local, PA-supportive environmental resources (ρ = 0.82, p = 0.004). Findings indicate that participant- and site-level measures of the built environment may play a role in promoting PA behavior among this demographic and similar populations. Results also suggest that improvements in aesthetic attributes and street connectivity, along with enhancing the quality of local, PA-supportive environmental resources, may be effective strategies for promoting physical activity among lower-income midlife and older adults. Full article

This study explores the impact of accessibility on property pricing and land economies by advanced spatial analysis techniques, focusing on Shanghai as a representative metropolis. Despite the impact of metro systems on residential property values, which has been frequently assessed, a research gap exists in understanding this phenomenon in Asian, particularly Chinese, urban contexts. Addressing this gap is crucial for shaping effective urban land use policy and improving the land economy rationally in China and similar settings facing urban challenges. To assess the impact of metro station accessibility on property prices in Shanghai, with extensive rail transit, and to deeply explore the overall impact of land value varieties driven by metro on urban development, we conducted a comprehensive analysis, with discussion about future aspirations for land planning and management along with landscape and facility design, and measures to improve land economy. The procedures involved creating neighborhood centroids to represent accessibility and using the Euclidean distance analysis to determine the shortest paths to metro stations. Our evaluation incorporated a hedonic pricing model, considering variables like neighborhood characteristics, housing attributes, and socio-economic factors. Advanced spatial analysis encompassing Ordinary Least Squares (OLS) regression and XGBoost analysis were employed to explore spatial effects, and Geographically Weighted Regression (GWR) helped examine spatial patterns and address autocorrelation challenges. Results revealed a negative association between distance to metro station and property prices, indicating a non-linear and spatially clustered relationship and heterogeneous spatial pattern. We dissected the non-linear results in detail, which complemented the conclusion in existing research. This study provides valuable insights into the dynamic interplay between metro accessibility and housing market behaviors in a significant Asian urban context, offering targeted suggestions for urban planners and governors to decide on more reasonable land use planning and management strategies, along with landscape and infrastructure design, to promote not only the healthy growth of the real estate market but also the sustainable urban development in China and similar regions. Full article

Inverting land cover reflectance or derived indices from low-spatial-resolution images to refine the spatial resolution of this data is cost-effective for land surface monitoring applications that face technical or budget limitations. Based on the linear spectral mixing model, many approaches have successfully unmixed coarse mixed pixels using high-spatial-resolution land cover maps in the past decades. However, in some cases, the solutions of linear systems composed of several mixed pixels may not be acquired due to the underdetermined problem. This study presents the causes of this problem and proposes an iterative approximation strategy to address it. An elastic-window-based algorithm was developed, where the initial size of the window was calculated based on the land cover of the mixed pixel. Mixed pixels of neighborhoods with similar land covers were then selected to form the unmixing linear system, which was examined through a simulation test to ensure it was not underdetermined. Otherwise, the window would expand to include more adjacent pixels. This process was repeated until a successful solution was obtained. A statistical analysis of sixty land cover maps from around the globe shows that the underdetermined problem exists at a low level but becomes more serious with an increase in mixed scale. The results demonstrate that the proposed algorithm effectively prevents the underdetermined problem for mixed pixels of different scales and can be integrated into the coarse NDVI downscaling procedure to refine spatial resolution. This study provides a reference for estimating underdetermined mixed pixels and benefits applications that require dealing with the inversion of land cover values directly. Full article

This paper proposes a spectral clustering method using k-means and weighted Mahalanobis distance (Referred to as MDLSC) to enhance the degree of correlation between data points and improve the clustering accuracy of Laplacian matrix eigenvectors. First, we used the correlation coefficient as the weight of the Mahalanobis distance to calculate the weighted Mahalanobis distance between any two data points and constructed the weighted Mahalanobis distance matrix of the data set; then, based on the weighted Mahalanobis distance matrix, we used the K-nearest neighborhood (KNN) algorithm construct similarity matrix. Secondly, the regularized Laplacian matrix was calculated according to the similarity matrix, normalized and decomposed, and the feature space for clustering was obtained. This method fully considered the degree of linear correlation between data and special spatial structure and achieved accurate clustering. Finally, various spectral clustering algorithms were used to conduct multi-angle comparative experiments on artificial and UCI data sets. The experimental results show that MDLSC has certain advantages in each clustering index and the clustering quality is better. The distribution results of the eigenvectors also show that the similarity matrix calculated by MDLSC is more reasonable, and the calculation of the eigenvectors of the Laplacian matrix maximizes the retention of the distribution characteristics of the original data, thereby improving the accuracy of the clustering algorithm. Full article

Long-non-coding RNA (lncRNA) is a transcription product that exerts its biological functions through a variety of mechanisms. The occurrence and development of a series of human diseases are closely related to abnormal expression levels of lncRNAs. Scientists have developed many computational models to identify the lncRNA-disease associations (LDAs). However, many potential LDAs are still unknown. In this paper, a novel method, namely MSF-UBRW (multiple similarities fusion based on unbalanced bi-random walk), is designed to explore new LDAs. First, two similarities (functional similarity and Gaussian Interaction Profile kernel similarity) of lncRNAs are calculated and fused linearly, also for disease data. Then, the known association matrix is preprocessed. Next, the linear neighbor similarities of lncRNAs and diseases are calculated, respectively. After that, the potential associations are predicted based on unbalanced bi-random walk. The fusion of multiple similarities improves the prediction performance of MSF-UBRW to a large extent. Finally, the prediction ability of the MSF-UBRW algorithm is measured by two statistical methods, leave-one-out cross-validation (LOOCV) and 5-fold cross-validation (5-fold CV). The AUCs of $0.9391$ in LOOCV and 0.9183 $(\pm 0.0054)$ in 5-fold CV confirmed the reliable prediction ability of the MSF-UBRW method. Case studies of three common diseases also show that the MSF-UBRW method can infer new LDAs effectively. Full article

Large volumes of crude oil accidentally released into the sea may cause irreversible adverse impacts on marine and coastal environments. Large swath optical imagery, acquired using platforms such as the moderate-resolution imaging spectroradiometer (MODIS), is frequently used for massive oil spill detection, attributing to its large coverage and short global revisit, providing rich data for oil spill monitoring. The aim of this study was to develop a suitable approach for massive oil spill detection in sun glint optical imagery. Specifically, preprocessing procedures were conducted to mitigate the inhomogeneous light field over the spilled area caused by sun glint, enhance the target boundary contrast, and maintain the internal homogeneity within the target. The image was then segmented into super-pixels based on a simple linear clustering method with similar characteristics of color, brightness, and texture. The neighborhood super-pixels were merged into target objects through the region adjacency graph method based on the Euclidean distance of their colors with an adaptive termination threshold. Oil slicks from the generated bright/dark objects were discriminated through a decision tree with parameters based on spectral and spatial characteristics. The proposed approach was applied to oil spill detection in MODIS images acquired during the Montara oil spill in 2009, with an overall extraction precision of 0.8, recall of 0.838, and F1-score of 0.818. Such an approach is expected to provide timely and accurate oil spill detection for disaster emergency response and ecological impact assessment. Full article

Chaotic and pathological phenomena in topological modules are studied in this manuscript. In particular, constructions of noncontinuous linear functionals are provided for a wide variety of topological modules. In addition, constructions of balanced and absorbing sets which are not neighborhoods of zero are also given in an extensive class of topological modules. Finally, we construct a linearly open set with empty interior in a large amount of topological modules. All these constructions are related to each other. Prior to developing all these results, we provide an axiomatization of the topological concept of limit by introducing the limit operators in a similar context as hull operators or closure operators are defined. Full article

Fuzzy gray-level aura matrices have been developed from fuzzy set theory and the aura concept to characterize texture images. They have proven to be powerful descriptors for color texture classification. However, using them for color texture segmentation is difficult because of their high memory and computation requirements. To overcome this problem, we propose to extend fuzzy gray-level aura matrices to fuzzy color aura matrices, which would allow us to apply them to color texture image segmentation. Unlike the marginal approach that requires one fuzzy gray-level aura matrix for each color channel, a single fuzzy color aura matrix is required to locally characterize the interactions between colors of neighboring pixels. Furthermore, all works about fuzzy gray-level aura matrices consider the same neighborhood function for each site. Another contribution of this paper is to define an adaptive neighborhood function based on information about neighboring sites provided by a pre-segmentation method. For this purpose, we propose a modified simple linear iterative clustering algorithm that incorporates a regional feature in order to partition the image into superpixels. All in all, the proposed color texture image segmentation boils down to a superpixel classification using a simple supervised classifier, each superpixel being characterized by a fuzzy color aura matrix. Experimental results on the Prague texture segmentation benchmark show that our method outperforms the classical state-of-the-art supervised segmentation methods and is similar to recent methods based on deep learning. Full article

Hyperspectral image (HSI) classification is one of the hot research topics in the field of remote sensing. The performance of HSI classification greatly depends on the effectiveness of feature learning or feature design. Traditional vector-based spectral–spatial features have shown good performance in HSI classification. However, when the number of labeled samples is limited, the performance of these vector-based features is degraded. To fully mine the discriminative features in small-sample case, a novel local matrix feature (LMF) was designed to reflect both the correlation between spectral pixels and the spectral bands in a local spatial neighborhood. In particular, the LMF is a linear combination of a local covariance matrix feature and a local correntropy matrix feature, where the former describes the correlation between spectral pixels and the latter measures the similarity between spectral bands. Based on the constructed LMFs, a simple Log-Euclidean distance-based linear kernel is introduced to measure the similarity between them, and an LMF-based kernel joint sparse representation (LMFKJSR) model is proposed for HSI classification. Due to the superior performance of region covariance and correntropy descriptors, the proposed LMFKJSR shows better results than existing vector-feature-based and matrix-feature-based support vector machine (SVM) and JSR methods on three well-known HSI data sets in the case of limited labeled samples. Full article

Lead exposure and neighborhoods can affect children’s behavior, but it is unclear if neighborhood characteristics modify the effects of lead on behavior. Understanding these modifications has important intervention implications. Blood lead levels (BLLs) in children (~7 years) from Montevideo, Uruguay, were categorized at 2 µg/dL. Teachers completed two behavior rating scales (n = 455). At one-year follow-up (n = 380), caregivers reported child tantrums and parenting conflicts. Multilevel generalized linear models tested associations between BLLs and behavior, with neighborhood disadvantage, normalized difference vegetation index (NDVI), and distance to nearest greenspace as effect modifiers. No effect modification was noted for neighborhood disadvantage or NDVI. Children living nearest to greenspace with BLLs < 2 µg/dL were lower on behavior problem scales compared to children with BLLs ≥ 2 µg/dL. When furthest from greenspace, children were similar on behavior problems regardless of BLL. The probability of daily tantrums and conflicts was ~20% among children with BLLs < 2 µg/dL compared to ~45% among children with BLLs ≥ 2 µg/dL when closest to greenspace. Furthest from greenspace, BLLs were not associated with tantrums and conflicts. Effect modification of BLL on child behavior by distance to greenspace suggests that interventions should consider both greenspace access and lead exposure prevention. Full article