Search Results (1,603)

The acquisition of nighttime remote-sensing visible-light images is often accompanied by low-illumination effects and haze interference, resulting in significant image quality degradation and greatly affecting subsequent applications. Existing low-light enhancement and dehazing algorithms can handle each problem individually, but their simple cascade cannot effectively address unknown real-world degradations. Therefore, we design a joint processing framework, WFDiff, which fully exploits the advantages of Fourier–wavelet dual-domain features and innovatively integrates the inverse diffusion process through differentiable operators to construct a multi-scale degradation collaborative correction system. Specifically, in the reverse diffusion process, a dual-domain feature interaction module is designed, and the joint probability distribution of the generated image and real data is constrained through differentiable operators: on the one hand, a global frequency-domain prior is established by jointly constraining Fourier amplitude and phase, effectively maintaining the radiometric consistency of the image; on the other hand, wavelets are used to capture high-frequency details and edge structures in the spatial domain to improve the prediction process. On this basis, a cross-overlapping-block adaptive smoothing estimation algorithm is proposed, which achieves dynamic fusion of multi-scale features through a differentiable weighting strategy, effectively solving the problem of restoring images of different sizes and avoiding local inconsistencies. In view of the current lack of remote-sensing data for low-light haze scenarios, we constructed the Hazy-Dark dataset. Physical experiments and ablation experiments show that the proposed method outperforms existing single-task or simple cascade methods in terms of image fidelity, detail recovery capability, and visual naturalness, providing a new paradigm for remote-sensing image processing under coupled degradations. Full article

Crop leaves naturally exhibit a curved morphology and primarily display bending deformation and vibrational responses under wind load. The curved surface structure of leaves plays a critical role in the deposition and retention of pesticide droplets. In this study, wind tunnel experiments combined with high-speed photography and digital image analysis were conducted to systematically investigate the curvature and flexibility distributions of three typical crop leaves: walnut, peach, and pepper, across a range of wind speeds. The results indicate that with increasing wind speed, all three types of leaves gradually transition from smooth, uniform bending to a multi-peak pattern of pronounced local curvature, with increasingly prominent nonlinear deformation characteristics. Moreover, once the wind speed exceeds the critical threshold of 6 m/s, the primary deformation region generally shifts from the leaf base to the tip. For example, the maximum curvature of walnut leaves increased from 0.018 mm⁻¹ to 0.047 mm⁻¹, and that of pepper leaves from 0.031 mm⁻¹ to 0.101 mm⁻¹, both more than double their original values. In addition, all three types of leaves demonstrated a distinct structural gradient characterized by strong basal rigidity and high apical flexibility. The tip flexibility values exceeded 1.5 × 10⁻⁵, 4 × 10⁻⁴, and 5.6 × 10⁻⁴ mm⁻²·mN⁻¹ for walnut, peach, and pepper leaves, respectively. These findings elucidate the mechanical response mechanisms of non-uniform flexible crop leaves under wind-induced bending and provide a theoretical basis and data support for the optimization of air-assisted spraying parameters. Full article

Road extraction from remote sensing imagery plays a critical role in applications such as autonomous driving, urban planning, and infrastructure development. Although deep learning methods have achieved notable progress, current approaches still struggle with complex backgrounds, varying road widths, and strong texture interference, often leading to fragmented road predictions or the misclassification of background regions. Given that roads typically exhibit smooth low-frequency characteristics while background clutter tends to manifest in mid- and high-frequency ranges, incorporating frequency-domain information can enhance the model’s structural perception and discrimination capabilities. To address these challenges, we propose a novel frequency-aware road extraction network, termed PWFNet, which combines frequency-domain modeling with multi-scale feature enhancement. PWFNet comprises two key modules. First, the Pyramidal Wavelet Convolution (PWC) module employs multi-scale wavelet decomposition fused with localized convolution to accurately capture road structures across various spatial resolutions. Second, the Frequency-aware Adjustment Module (FAM) partitions the Fourier spectrum into multiple frequency bands and incorporates a spatial attention mechanism to strengthen low-frequency road responses while suppressing mid- and high-frequency background noise. By integrating complementary modeling from both spatial and frequency domains, PWFNet significantly improves road continuity, edge clarity, and robustness under complex conditions. Experiments on the DeepGlobe and CHN6-CUG road datasets demonstrate that PWFNet achieves IoU improvements of 3.8% and 1.25% over the best-performing baseline methods, respectively. In addition, we conducted cross-region transfer experiments by directly applying the trained model to remote sensing images from different geographic regions and at varying resolutions to assess its generalization capability. The results demonstrate that PWFNet maintains the continuity of main and branch roads and preserves edge details in these transfer scenarios, effectively reducing false positives and missed detections. This further validates its practicality and robustness in diverse real-world environments. Full article

Waterline extraction is a key step in applying the Waterline Detection Method (WDM) to Digital Elevation Model (DEM) generation. Cloud interference remains a major challenge for achieving high-quality extraction of waterlines. This study developed an image filtering method termed “Cloud Coverage in Region of Interest” (CCROI). By integrating the CCROI method with the Otsu algorithm and noise smoothing techniques, this study enabled high-quality batch and automated extraction of waterlines within the Google Earth Engine (GEE) platform. Using the WDM, DEMs were established to evaluate recent geomorphological changes in the estuarine tidal flats of the abandoned Diaokou Course (ETFADC). The results confirm that the erosional trend of the ETFADC has persisted throughout nearly 50 years of natural adjustment. In areas distant from oil extraction zones, erosion dominates the high-tide zone, while accretion prevails in the low-tide zone, indicating a slope-flattening process. However, in areas near the oil extraction zone, tree-shaped embankments have acted to inhibit erosion rather than exacerbate it, with strong accretion even occurring in wave-sheltered areas. By enhancing the quality of the selected images and reducing the waterline false detection rate, the CCROI method demonstrates significant potential for time-series studies of small regions. Full article

The shape and position information of towed streamers is crucial for both implementing marine seismic exploration operations and analyzing exploration data. Streamer positioning accuracy directly impacts the quality and reliability of seismic imaging. Existing polynomial curve models exhibit deviations between the calculated and actual shapes during streamer turning. This paper proposes a segmented fitting positioning model based on spline curves. It is mathematically rigorous and applicable to complex scenarios. First, the specific function expression of the spline curve model is constructed. Then, using a cubic spline as an example, the segmented fitting method is explained, incorporating smoothness constraints at the connection points. The error equations for positioning observations and the calculation processes for curve parameters and hydrophone coordinates are derived. Finally, the model is verified through simulations and field tests. The experimental results show that, compared with the polynomial curve model, the spline curve model improves positioning accuracy by 47.1% in simulations involving six streamers and by 20.0% and 35.0% in field tests with six and ten streamers, respectively. In straight scenarios, both models perform similarly. Thus, the spline model can effectively reduce the modeling errors of the polynomial curve model under high-curvature conditions. Full article

This paper investigates the combined application of seismic inversion and migration for processing seismic data in the depth domain. Seismic inversion serves as a widely used practical tool allowing the derivation of detailed subsurface models from seismic data. In this study, we implement a constrained total variation inversion algorithm. The inversion input data comprise true-amplitude depth imaging results along with the depth migration velocity model. Furthermore, we develop and examine an iterative algorithm that jointly performs acoustic seismic inversion and depth migration. This approach aims to refine high-frequency and smooth low-frequency components of the depth velocity model. We validate our methods through numerical experiments using both synthetic data and a realistic Marmousi model. Full article

Background: Postoperative ocular inflammation is a frequent complication of eye surgeries commonly managed using corticosteroids or nonsteroidal anti-inflammatory drug (NSAIDs) eye drops. However, poor ocular bioavailability and patient non-adherence due to frequent dosing limit the therapeutic efficacy of conventional eye drops. This study aimed to develop a sustained-release ocular insert containing bromfenac sodium (BS)-loaded poly(lactic-co-glycolic acid) (PLGA) microparticles (MPs) with an initial 3% (w/w) free BS fraction incorporated into a poly(vinyl alcohol) (PVA) matrix designed to achieve a dual-phase release profile for improved postoperative therapy. Methods: PLGA-based MPs were fabricated using a double emulsion solvent evaporation technique and incorporated into PVA films to produce ocular inserts with varying MP content. Formulations were characterized for morphology, particle size, zeta potential, drug loading, entrapment efficiency, mucoadhesion, drug distribution, and in vitro release. Data were analyzed by an ANOVA and t-tests with p < 0.05 as significance. Results: MPs were smooth, spherical, and well-dispersed in the PVA inserts. Particle sizes ranged from 3.7 to 5.6 µm, with drug loading 7–8% and entrapment efficiencies 47–52%. Multiphoton imaging confirmed uniform drug distribution. In vitro release showed a dual-phase profile with an initial burst followed by sustained release for up to 4 days, with only negligible further release through Day 6 in one formulation (M1-7525). Conclusions: The developed BS-loaded PLGA MP/PVA insert demonstrated a dual-phase release profile relevant to postoperative ocular inflammation. Its biodegradable, single-application design holds promise for enhancing compliance and therapeutic outcomes in ophthalmic care. Full article

The aim of this study was to address the issue of significant performance degradation in existing defogging algorithms under extreme fog conditions. Traditional Taylor series-based deformable convolutions are limited by local approximation errors, while the heavy-tailed characteristics of the Cauchy distribution can more successfully model outliers in fog images. The following improvements are made: (1) A displacement generator based on the inverse cumulative distribution function (ICDF) of the Cauchy distribution is designed to transform uniform noise into sampling points with a long-tailed distribution. A novel double-peak Cauchy ICDF is proposed to dynamically balance the heavy-tailed characteristics of the Cauchy ICDF, enhancing the modeling capability for sudden changes in fog concentration. (2) An innovative Cauchy–Gaussian fusion module is proposed to dynamically learn and generate hybrid coefficients, combining the complementary advantages of the two distributions to dynamically balance the representation of smooth regions and edge details. (3) Tree-based multi-path and cross-resolution feature aggregation is introduced, achieving local–global feature adaptive fusion through adjustable window sizes (3/5/7/11) for parallel paths. Experiments on the RESIDE dataset demonstrate that the proposed method achieves a 2.26 dB improvement in the peak signal-to-noise ratio compared to that obtained with the TaylorV2 expansion attention mechanism, with an improvement of 0.88 dB in heavily hazy regions (fog concentration > 0.8). Ablation studies validate the effectiveness of Cauchy distribution convolution in handling dense fog and conventional lighting conditions. This study provides a new theoretical perspective for modeling in computer vision tasks, introducing a novel attention mechanism and multi-path encoding approach. Full article

This paper addresses the problem of subsurface target localization from single-snapshot multimonostatic and multifrequency radar measurements. In this context, the use of subspace projection methods—known for their super-resolution capabilities—is hindered by the rank deficiency of the data correlation matrix and the lack of a Vandermonde structure, especially in near-field configurations and layered media. To overcome this issue, we propose a novel pre-processing strategy that transforms the measured data into the $\omega -k$ domain, thereby restoring the structural conditions required for subspace-based detection. The resulting algorithm, referred to as $\omega -k$ MUSIC, enables the application of subspace projection techniques in scenarios where traditional smoothing procedures are not viable. Numerical experiments in a 2-D scalar configuration demonstrate the effectiveness of the proposed method in terms of resolution and robustness under various noise conditions. A Monte Carlo simulation study is also included to provide a quantitative assessment of localization accuracy. Comparisons with conventional migration imaging highlight the superior performance of the proposed approach. Full article

Background: Pulmonary benign metastasizing leiomyoma (PBML) is a rare condition characterized by histologically benign smooth muscle tumors occurring at extrauterine sites, often in women with a history of uterine leiomyoma. While PBML generally exhibits indolent behavior, its pathogenesis, management, and malignant potential remain unclear. Methods: This study retrospectively analyzes the clinical characteristics, imaging features, diagnostic approaches, pathological findings, treatment strategies, and outcomes of seven patients with PBML treated at our institution between January 2016 and May 2025. Results: Seven patients were included, with a mean age at diagnosis of 48.9 ± 5.6 years. Two patients presented with respiratory symptoms. Imaging revealed multiple bilateral pulmonary nodules in four patients and solitary nodules in three. Six patients were diagnosed via video-assisted thoracoscopic surgery, and one through computed tomography-guided percutaneous biopsy. Immunohistochemistry revealed positivity for SMA and Desmin in all cases, ER in six, and PR in five, with the Ki-67 labeling index ≤3% in six patients. One patient had a coexisting in situ mucinous adenocarcinoma within the PBML lesion. All had a history of uterine leiomyoma. After diagnosis, one patient received hormonal therapy, and another underwent right adnexectomy. The remaining patients were managed with surveillance without additional treatment. During follow-up, one patient developed distant organ metastasis. Conclusions: PBML is a rare, typically indolent condition with potential for metastasis. Accurate diagnosis relies on imaging, histopathology, and immunohistochemistry. This study reports a unique case of PBML coexisting with intratumoral in situ mucinous adenocarcinoma, a previously unreported finding that may broaden the known histopathological spectrum. Full article

Mechanical and contractile forces in the vascular wall regulate smooth muscle cell migration. We previously demonstrated the presence of C3 complement products in atherosclerotic lesions of human aortas and showed that that C3-derived fragments promote key cellular processes, such as actin cytoskeleton organization and cell migration, in lipid-loaded human vascular smooth muscle cells (hVSMCs). In the present study, we aimed to investigate gene expression profiles related to cytoskeletal remodeling and cell adhesion in migrating hVSMCs with a particular focus on modulatory effect of the C3 complement pathway on these processes. We analyzed gene expression in migrating and non-migrating hVSMCs using real-time PCR and in silico network analysis. Additionally, we investigated cytoskeletal remodeling through Western blotting and confocal microscopy. PCR profiling revealed 30 genes with significantly altered expression in migrating hVSMCs compared to non-migrating control cells. In silico analysis identified six of these genes—PXN, AKT1, RHOA, VCL, CTNNB1, and FN1—as being associated with cytoskeletal remodeling and focal adhesion, with PXN occupying a central position in the interaction network. PXN expression was reduced at both the transcript and protein levels and showed altered subcellular localization in migrating lipid-loaded hVSMCs. Protein–protein interaction analysis using STRING predicted an association between PXN and the integrin complex αMβ2 (comprising ITGAM (CD11b) and ITGB2 (CD18)), which functions as receptors for the iC3b complement fragment. Confocal imaging of cell adhesion structures revealed that lipid-loaded hVSMCs stimulated with iC3b displayed a more diffuse PXN distribution and significantly increased PXN–F-actin colocalization in active cytoplasmic regions compared to lipid-loaded control cells. PXN–F-actin colocalization increased from 1.26% to 19.68%. Subcellular fractionation further confirmed enhanced PXN enrichment in the membrane fraction, with no significant changes observed in the cytosolic or cytoskeletal compartments. In conclusion, iC3b-mediated molecular signaling in lipid-loaded hVSMCs alters PXN distribution and enhances cytoskeletal remodeling, revealing novel molecular interactions in vascular remodeling and the progression of atherosclerotic lesions. Full article

Micro-crack defects on the surfaces of plate heat exchanger sheets often exhibit a linear grayscale pattern when clustered. In defect detection, traditional methods are more suitable than deep learning models in controlled production environments with limited computing resources to meet stringent national standards, which require low miss rates. However, deep learning models commonly suffer feature loss when detecting individual, small-scale defects, leading to higher leak detection rates. Moreover, in grayscale image line detection using traditional methods, the varying direction, width, and asymmetric grayscale profiles of defects can result in filled grayscale valleys due to width-adaptive smoothing coefficients, complicating accurate defect extraction. To address these issues, this study establishes a theoretical foundation for parameter selection in variable-width defect detection. We propose a directional gradient-based algorithm that mathematically constrains the Gaussian template width to cover variable-width defects with a fixed σ, reframing the detection defect from ridge edges to centrally symmetric double-ridge edges in gradient images. Experimental results show that, when tested in the defective boards library and under simulated factory CPU conditions, this algorithm achieves a miss detection rate of 14.55%, a false detection rate of 21.85%, and an 600 × 600 pixel image detection time of 0.1402 s. Compared to traditional line detection and deep learning object detection methods, this algorithm proves advantageous for detecting micro-crack defects on plate heat exchanger sheets in industrial production, particularly in data-scarce and resource-limited scenarios. Full article

Various low-light image enhancement techniques inevitably introduce noise to varying degrees while improving visibility, leading to a decline in image quality that adversely affects downstream vision tasks. Existing post-processing denoising methods often produce overly smooth results lacking in detail, presenting the challenge of balancing noise suppression and detail preservation. To address this, this paper proposes a conditional diffusion denoising framework based on multi-feature fusion. The framework utilizes a diffusion model to learn the conditional distribution between underexposed and normally exposed images. Complementary features are extracted in parallel through four dedicated branches. These multi-source features are then concatenated and fused to enrich semantic information. Subsequently, redundant information is compressed via 1 × 1 convolutional layers, mitigating the issue of information degradation commonly encountered with U-Net skip connections during multi-scale feature fusion. Experimental results demonstrate the method’s applicability across diverse scenarios and illumination conditions. It outperforms both traditional methods and mainstream deep learning models in qualitative and quantitative evaluations, particularly in terms of perceptual quality. This research provides significant technical support for subsequent image restoration and denoising within low-light enhancement pipelines. Full article

Monocular depth estimation is a crucial technique in computer vision that determines the depth or distance of objects in a scene using a single 2D image captured by a camera. UNet-based models are a fundamental architecture for monocular depth estimation, due to their effective encoder–decoder structure. This study presents an effective depth estimation model based on a hybrid UNet architecture that incorporates ensemble features. The new model integrates Transformer-based attention blocks to capture global context and an encoder built on ResNet18 to extract spatial features. Additionally, a novel Boundary-Aware Depth Consistency Loss (BADCL) function has been introduced to enhance accuracy. This function features dynamic scaling, smoothness regularization, and boundary-aware weighting, which provides sharper edges, smoother depth transitions, and scale-consistent predictions. The proposed model has been evaluated on the NYU Depth V2 dataset, achieving a Structural Similarity Index Measure (SSIM) of 99.8%. The performance of the proposed model indicates increased depth accuracy compared to state-of-the-art methods. Full article

In this paper, we propose a navigation synthesis method for indoor mobile robots based on the Improved Jumping Point Search (JPS) framework. Although traditional JPS has high search efficiency, it often leads to excessive node expansion and sharp turns in complex environments, which limits its practical application. In order to overcome these problems, we introduced three key strategies. First, we used a density-sensing heuristic function calculated by integrating the image to improve the adaptability of complex areas. Secondly, we extracted structural key points from the path and used third-order B-splines to fit them to enhance smoothness and continuity. Third, a curvature-driven Regulated Pure Pursuit (RPP) controller adjusts the look-ahead distance and speed based on path curvature, improving tracking stability. Simulation results show that the proposed method reduces planning time and node redundancy while generating smoother and more executable paths than the conventional JPS framework. Full article