Search Results (372)

Caragana korshinskii, a key species in China’s Grain for Green Project on the Loess Plateau, is effective in enhancing soil C sequestration. However, whether its contribution to SOC (soil organic carbon) stability persists over multi-decadal restoration chronosequences remains unclear. Using the time–space substitution method, we investigated the SOC fractions (POC, particulate organic C, and MAOC, mineral-associated organic C) dynamics across soil depths (0–10, 10–30, and 30–60 cm) in a 40-year chronosequence of C. korshinskii restoration, which is located in a comprehensive managed watershed on the Loess Plateau, China. The results showed that the C. korshinskii restoration chronosequence improved soil C sequestration at different scales compared to abandoned sites. In the middle phase (10–30 years), the concentration of SOC peaked at 35.88 g/kg, exceeding natural grassland (32.33 g/kg). Above- and belowground biomass accumulation drove SOC enhancement. POC as transient C inputs, and MAOC through mineral interactions, reach a peak at 7.98 g/kg which shows the greatest increase (276.81%). In the subsequent phase (after 30 years), MAOC dominated SOC stabilization, yet SOC fractions declined overall. MAOC contribution to SOC stability plateaued at 20–30%, constrained by soil desiccation from prolonged root water uptake. C. korshinskii provides the optimal SOC benefits within 10–30 years of restoration, highlighting a trade-off between vegetation-driven C inputs and hydrological limits in arid ecosystems. Beyond 30 years, C. korshinskii’s high water demand reduced SOC sequestration efficiency, risking the reversal of carbon gains despite initial MAOC advantages. Full article

With the rapid development of global maritime trade, high-precision ship heading estimation has become crucial for maritime traffic safety and intelligent shipping. To address the challenge of heading estimation from horizontal-view optical images, this study proposes a novel framework integrating DeepLabV3+ image segmentation with contrastive-learning-optimized multi-scale similarity matching. First, a cascaded image preprocessing method is developed, incorporating linear transformation, bilateral filtering, and the Multi-Scale Retinex with Color Restoration (MSRCR) algorithm to mitigate noise and haze interference and enhance image quality with improved target edge clarity. Subsequently, the DeepLabV3+ network is employed for the precise segmentation of ship targets, generating binarized contour maps for subsequent heading analysis. Based on actual ship dimensional parameters, 3D models are constructed and multi-angle rendered to establish a heading template library. The framework introduces the Multi-Scale Structural Similarity (MS-SSIM) algorithm enhanced by a triplet contrastive learning mechanism that dynamically optimizes feature weights across scales, thereby improving robustness against image degradation and partial occlusion. Experimental results demonstrate that under noise-free, noise-interfered, and mist-occluded conditions, the proposed method achieves mean heading estimation errors of 0.41°, 0.65°, and 0.88°, respectively, significantly outperforming the single-scale SSIM and fixed-weight MS-SSIM approaches. This verification confirms the method’s effectiveness and robustness, offering a novel technical solution for ship heading estimation in maritime surveillance and intelligent navigation systems. Full article

Numerous existing methods demonstrate impressive performance in brightening low-illumination images but fail in detail enhancement and color correction. To tackle these challenges, this paper proposes a dual-branch network including three main parts: color space transformation, a color correction network (CC-Net), and a light-boosting network (LB-Net). Specifically, we first transfer the input into the CIELAB color space to extract luminosity and color components. Afterward, we employ LB-Net to effectively explore multiscale features via a carefully designed large–small-scale structure, which can adaptively adjust the brightness of the input images. And we use CC-Net, a U-shaped network, to generate noise-free images with vivid color. Additionally, an efficient feature interaction module is introduced for the interaction of the two branches’ information. Extensive experiments on low-light image enhancement public benchmarks demonstrate that our method outperforms state-of-the-art methods in restoring the quality of low-light images. Furthermore, experiments further indicate that our method significantly enhances performance in object detection under low-light conditions. Full article

The Western Sichuan Plateau, an ecologically critical transition zone between the Qinghai–Tibet Plateau and the Sichuan Basin, is also a typical fragile and sensitive area in China’s ecological security. This study established a multi-process evaluation model using the Spatial Distance Index Method, integrating cluster analysis, Sen–Mann–Kendall trend detection, and OWA-based scenario simulations to assess composite ecological sensitivity dynamics. The optimal geodetector was further applied to quantitatively determine the driving mechanisms underlying these sensitivity dynamics. The research showed the following findings: (1) From 2000 to 2020, the ecological environment of the Western Sichuan Plateau exhibited a phased pattern characterized by significant improvement, partial rebound, and overall stabilization. The composite ecological sensitivity grading index showed a declining trend, indicating a gradual reduction in ecological vulnerability. The effectiveness of ecological restoration projects became evident after 2010, with the area of medium- to high-sensitivity zones decreasing by 24.29% at the regional scale compared to the 2010 baseline. (2) The spatial pattern exhibited a gradient-decreasing characteristic from west to east. Scenario simulations under varying decision-making behaviors prioritized Jiuzhaigou, Xiaojin, Jinchuan, Danba, and Yajiang counties as ecologically critical. (3) Driving force analysis revealed a marked increase in the explanatory power of freeze-thaw erosion, with its q-value rising from 0.49 to 0.80. Moreover, its synergistic effect with landslide disasters spans 74.19% of county-level units. Dominant drivers ranked: annual temperature range (q = 0.32) > distance to faults (q = 0.17) > slope gradient (q = 0.16), revealing a geomorphic-climatic-tectonic interactive mechanism. This study provided methodological innovations and decision-making support for sustainable environmental development in plateau transitional zones. Full article

To address the issues of high computational complexity and boundary feature loss encountered when extracting farmland information from high-resolution remote sensing images, this study proposes an innovative CNN–Transformer hybrid network, MAMNet. This framework integrates a lightweight encoder, a global–local Transformer decoder, and a bidirectional attention architecture to achieve efficient and accurate farmland information extraction. First, we reconstruct the ResNet-18 backbone network using deep separable convolutions, reducing computational complexity while preserving feature representation capabilities. Second, the global–local Transformer block (GLTB) decoder uses multi-head self-attention mechanisms to dynamically fuse multi-scale features across layers, effectively restoring the topological structure of fragmented farmland boundaries. Third, we propose a novel bidirectional attention architecture: the Detail Improvement Module (DIM) uses channel attention to transfer semantic features to geometric features. The Context Enhancement Module (CEM) utilizes spatial attention to achieve dynamic geometric–semantic fusion, quantitatively distinguishing farmland textures from mixed ground cover. The positional attention mechanism (PAM) enhances the continuity of linear features by strengthening spatial correlations in jump connections. By cascading front-end feature module (FEM) to expand the receptive field and combining an adaptive feature reconstruction head (FRH), this method improves information integrity in fragmented areas. Evaluation results on the 2022 high-resolution two-channel image dataset from Chenggong District, Kunming City, demonstrate that MAMNet achieves an mIoU of 86.68% (an improvement of 1.66% and 2.44% over UNetFormer and BANet, respectively) and an F1-Score of 92.86% with only 12 million parameters. This method provides new technical insights for plot-level farmland monitoring in precision agriculture. Full article

Habitat degradation poses a critical threat to the Malabar slender loris (Loris lydekkerianus malabaricus), yet little is known about its microhabitat requirements in intact forest. In Aralam Wildlife Sanctuary, we combined nocturnal trail surveys (337 loris sightings) with plotless sampling of 2830 trees (86 species from 35 families) to characterize both vegetation structure and loris presence. Our results show that lorises occur almost exclusively in mildly degraded wet evergreen and secondary moist deciduous subcanopies, where understory trees and climber networks provide continuous pathways. Individuals are most often encountered at heights of 5–15 m—ascending into higher strata as the night progresses—reflecting a balance between foraging access and predator avoidance. Substrate analysis revealed strong preferences for twigs ≤ 1 cm (36.98%) and small branches 2–5 cm in diameter, oriented obliquely to minimize energetic costs and maintain stability during slow, deliberate arboreal locomotion. Day-sleeping sites were overwhelmingly located within dense tangles of lianas on large-girth trees, where intertwined stems and thorny undergrowth offer concealment from both mammalian and avian predators. Vegetation surveys documented a near-equal mix of evergreen (50.6%) and deciduous (49.4%) species—including 26 endemics (18 restricted to the Western Ghats)—with Aporosa cardiosperma emerging as the most abundant riparian pioneer, suggesting both ecological resilience and potential simplification in fragmented patches. Complementing field observations, our recent habitat-suitability modeling in Aralam indicates that broad-scale climatic and anthropogenic factors—precipitation patterns, elevation, and proximity to roads—are the strongest predictors of loris occupancy, underscoring the interplay between landscape-level processes and microhabitat structure. Together, these findings highlight the imperative of multi-strata forest restoration—planting insect-hosting native trees, maintaining continuous canopy and climber networks, and integrating small “mini-forest” modules—to recreate the structural complexity vital for slender loris conservation and the broader resilience of Western Ghats biodiversity. Full article

Low-light image enhancement remains a challenging task in computer vision due to the complex interplay of noise, asymmetrical artifacts, illumination non-uniformity, and detail preservation. Existing methods such as traditional histogram equalization, gamma correction, and Retinex-based approaches often struggle to balance contrast improvement and naturalness preservation. Deep learning methods such as CNNs and transformers have shown promise, but face limitations in modeling multi-scale illumination and long-range dependencies. To address these issues, we propose WIGformer, a novel wavelet-based illumination-guided transformer framework for low-light image enhancement. The proposed method extends the single-stage Retinex theory to explicitly model noise in both reflectance and illumination components. It introduces a wavelet illumination estimator with a Wavelet Feature Enhancement Convolution (WFEConv) module to capture multi-scale illumination features and an illumination feature-guided corruption restorer with an Illumination-Guided Enhanced Multihead Self-Attention (IGEMSA) mechanism. WIGformer leverages the symmetry properties of wavelet transforms to achieve multi-scale illumination estimation, ensuring balanced feature extraction across different frequency bands. The IGEMSA mechanism integrates adaptive feature refinement and illumination guidance to suppress noise and artifacts while preserving fine details. The same mechanism allows us to further exploit symmetrical dependencies between illumination and reflectance components, enabling robust and natural enhancement of low-light images. Extensive experiments on the LOL-V1, LOL-V2-Real, and LOL-V2-Synthetic datasets demonstrate that WIGformer achieves state-of-the-art performance and outperforms existing methods, with PSNR improvements of up to 26.12 dB and an SSIM score of 0.935. The qualitative results demonstrate WIGformer’s superior capability to not only restore natural illumination but also maintain structural symmetry in challenging conditions, preserving balanced luminance distributions and geometric regularities that are characteristic of properly exposed natural scenes. Full article

Image super-resolution (SR) models based on the generative adversarial network (GAN) face challenges such as unnatural facial detail restoration and local blurring. This paper proposes an improved GAN-based model to address these issues. First, a Multi-scale Hybrid Attention Residual Block (MHARB) is designed, which dynamically enhances feature representation in critical face regions through dual-branch convolution and channel-spatial attention. Second, an Edge-guided Enhancement Block (EEB) is introduced, generating adaptive detail residuals by combining edge masks and channel attention to accurately recover high-frequency textures. Furthermore, a multi-scale discriminator with a weighted sub-discriminator loss is developed to balance global structural and local detail generation quality. Additionally, a phase-wise training strategy with dynamic adjustment of learning rate (Lr) and loss function weights is implemented to improve the realism of super-resolved face images. Experiments on the CelebA-HQ dataset demonstrate that the proposed model achieves a PSNR of 23.35 dB, a SSIM of 0.7424, and a LPIPS of 24.86, outperforming classical models and delivering superior visual quality in high-frequency regions. Notably, this model also surpasses the SwinIR model (PSNR: 23.28 dB → 23.35 dB, SSIM: 0.7340 → 0.7424, and LPIPS: 30.48 → 24.86), validating the effectiveness of the improved model and the training strategy in preserving facial details. Full article

Cropland slope structure is a key factor influencing agricultural sustainability and ecological risk, especially in topographically complex regions. This study proposes a novel framework that integrates slope spectrum analysis with H3 hexagonal grid partitioning to examine the spatiotemporal dynamics of cropland slope across China from 1990 to 2023. Using 30 m CLCD land cover data, we derived key indicators, including the T-value, upper slope limit (ULS), peak area proportion (PaP), slope at maximum area (SMA), and cropland slope change index (CSCI). This grid-based, multi-indicator approach enables the fine-scale detection of slope structure transitions. Results show that the average slope of cropland fluctuated at around 4.12°, peaking at 4.18° in 2003, while the ULS remained stable at 17°, with 95% of cropland below this threshold. Regionally, cropland in southwest and northwest China was concentrated on steeper slopes (ULS > 26°, PaP < 10%), whereas flatter areas in north and south China had cropland mainly below 15°. From 1990 to 2023, upslope expansion was evident in south China (CSCI > 10), while downslope shifts aligned with high-slope cropland in the western regions. Geographically weighted regression revealed significant positive correlations between increasing ULS and CSCI and elevated cropland fragmentation and soil erosion in hilly areas. These findings highlight the ecological risks of cropland expansion into steep terrain. The proposed framework offers a spatially explicit perspective of cropland slope evolution and supports targeted strategies for land management and ecological restoration. Full article

Phase wrapping is a common phenomenon in optical full-field imaging or measurement systems. It arises from large phase retardations and results in wrapped-phase maps that contain essential information about surface roughness and topology. However, these maps are often degraded by noise, such as speckle and Gaussian, which reduces the measurement accuracy and complicates phase reconstruction. Denoising such data is a fundamental problem in computer vision and plays a critical role in biomedical imaging modalities like Full-Field Optical Interferometry. In this paper, we propose WPD-Net (Wrapped-Phase Denoising Network), a lightweight deep learning-based neural network specifically designed to restore phase images corrupted by high noise levels. The network architecture integrates a shallow feature extraction module, a series of Residual Dense Attention Blocks (RDABs), and a dense feature fusion module. The RDABs incorporate attention mechanisms that help the network focus on critical features and suppress irrelevant noise, especially in high-frequency or complex regions. Additionally, WPD-Net employs a growth-rate-based feature expansion strategy to enhance multi-scale feature representation and improve phase continuity. We evaluate the model’s performance on both synthetic and experimentally acquired datasets and compare it with other state-of-the-art deep learning-based denoising methods. The results demonstrate that WPD-Net achieves superior noise suppression while preserving fine structural details even with mixed speckle and Gaussian noises. The proposed method is expected to enable fast image processing, allowing unwrapped biomedical images to be retrieved in real time. Full article

In recent years, the use of video content has experienced exponential growth. The rapid growth of video content has led to an increased reliance on various video codecs for efficient compression and transmission. However, several challenges are associated with codecs such as H.265/High Efficiency Video Coding and H.266/Versatile Video Coding (VVC) that can impact video quality and performance. One significant challenge is the trade-off between compression efficiency and visual quality. While advanced codecs can significantly reduce file sizes, they introduce artifacts such as blocking, blurring, and color distortion, particularly in high-motion scenes. Different compression tools in modern video codecs are vital for minimizing artifacts that arise during the encoding and decoding processes. While the advanced algorithms used by these modern codecs can effectively decrease file sizes and enhance compression efficiency, they frequently find it challenging to eliminate artifacts entirely. By utilizing advanced techniques such as post-processing after the initial decoding, this method can significantly improve visual clarity and restore details that may have been compromised during compression. In this paper, we introduce a Deep Residual Enhanced Feature Generative Adversarial Network as a post-processing method aimed at further improving the quality of reconstructed frames from the advanced codec VVC. By utilizing the benefits of Deep Residual Blocks and Enhanced Feature Blocks, the generator network aims to make the reconstructed frame as similar as possible to the original frame. The discriminator network, a crucial element of our proposed method, plays a vital role in guiding the generator by evaluating the authenticity of generated frames. By distinguishing between fake and original frames, the discriminator enables the generator to improve the quality of its output. This feedback mechanism ensures that the generator learns to create more realistic frames, ultimately enhancing the overall performance of the model. The proposed method shows significant gain for Random Access (RA) and All Intra (AI) configurations while improving Video Multimethod Assessment Fusion (VMAF) and Multi-Scale Structural Similarity Index Measure (MS-SSIM). Considering VMAF, our proposed method can obtain 13.05% and 11.09% Bjøntegaard Delta Rate (BD-Rate) gain for RA and AI configuration, respectively. In the case of the luma component MS-SSIM, RA and AI configurations get, respectively, 5.00% and 5.87% BD-Rate gain after employing our suggested proposed network. Full article

Biometric systems such as fingerprint recognition encounter significant challenges under wet conditions or small fingerprints, where noise degrades recognition accuracy. These challenges increase false acceptance rates (FARs) and false rejection rates (FRRs) as conventional denoising models designed for larger fingerprints cannot handle the smaller and noisier samples in portable and embedded devices. In this study, we collected 71,188 wet–dry fingerprints using a capacitive sensor. Fingerprints in sizes of 176 × 36, 88 × 88, and 80 × 100 pixels were preprocessed by padding and cropping them to a uniform size of 48 × 48 pixels. Preprocessing was conducted to standardize and augment the data and enhance the model’s ability to generalize across diverse data types. We developed a wet fingerprint denoising network (WFDN), a multi-stage neural network designed to improve wet fingerprint quality for small and large samples. By integrating scale-invariant feature transform, WFDN effectively restores critical minutiae and significantly enhances feature preservation compared with existing models. The network also incorporates an automatic label classifier and cyclic multi-variate functions to reduce noise. Despite its compact architecture, WFDN demonstrates superior performance, reducing the FRR from 19.6 to 8.4% for small fingerprints. Moreover, assessment results using NIST fingerprint image quality 2.0 (NFIQ2) for larger fingerprints show notable improvements in system reliability. The proposed model improves biometric processing significantly. WFDN represents a significant advancement in fingerprint-based identification, offering improved performance and robustness in challenging conditions. Full article

Due to the diversity and semi-transparency of snowflakes, accurately locating and reconstructing background information during image restoration poses a significant challenge. Snowflakes obscure image details, thereby affecting downstream tasks such as object recognition and image segmentation. Although Convolutional Neural Networks (CNNs) and Transformers have achieved promising results in snow removal through local or global feature processing, residual snowflakes or shadows persist in restored images. Inspired by the recent popularity of State Space Models (SSMs), this paper proposes a Mamba-based multi-scale desnowing network (SnowMamba), which effectively models the long-range dependencies of snowflakes. This enables the precise localization and removal of snow particles, addressing the issue of residual snowflakes and shadows in images. Specifically, we design a four-stage encoder–decoder network that incorporates Snow Caption Mamba (SCM) and SE modules to extract comprehensive snowflake and background information. The extracted multi-scale snow and background features are then fed into the proposed Multi-Scale Residual Interaction Network (MRNet) to learn and reconstruct clear, snow-free background images. Extensive experiments demonstrate that the proposed method outperforms other mainstream desnowing approaches in both qualitative and quantitative evaluations on three standard image desnowing datasets. Full article

With the increasing demand for power supply reliability, efficient load restoration in large-scale distribution networks post-outage scenarios has become a critical challenge. However, traditional methods become computationally prohibitive as network expansion leads to exponential growth of decision variables. This study proposes a multi-agent reinforcement learning (MARL) framework enhanced by distribution network partitioning to address this challenge. Firstly, an improved Girvan–Newman algorithm is employed to achieve balanced partitioning of the network, defining the state space of each agent and action boundaries within the multi-agent system (MAS). Subsequently, a counterfactual reasoning framework solved by the QTRAN-alt algorithm is incorporated to refine action selection during training, thereby accelerating convergence and enhancing decision-making efficiency during execution. Experimental validation using a 27-bus system and a 70-bus system demonstrates that the proposed QTRAN-alt with the Girvan–Newman method achieves fast convergence and high returns compared to typical MARL approaches. Furthermore, the proposed methodology significantly improves the success rate of full system restoration without violating constraints. Full article

Accurate segmentation of soil pore structure is crucial for studying soil water migration, nutrient cycling, and gas exchange. However, the low-contrast and high-noise CT images in complex soil environments cause the traditional segmentation methods to have obvious deficiencies in accuracy and robustness. This paper proposes a hybrid model combining a Multi-Modal Low-Frequency Reconstruction algorithm (MMLFR) and UNet (MMLFR-UNet). MMLFR enhances the key feature expression by extracting the image low-frequency signals and suppressing the noise interference through the multi-scale spectral decomposition, whereas UNet excels in the segmentation detail restoration and complexity boundary processing by virtue of its coding-decoding structure and the hopping connection mechanism. In this paper, an undisturbed soil column was collected in Hainan Province, China, which was classified as Ferralsols (FAO/UNESCO), and CT scans were utilized to acquire high-resolution images and generate high-quality datasets suitable for deep learning through preprocessing operations such as fixed-layer sampling, cropping, and enhancement. The results show that MMLFR-UNet outperforms UNet and traditional methods (e.g., Otsu and Fuzzy C-Means (FCM)) in terms of Intersection over Union (IoU), Dice Similarity Coefficients (DSC), Pixel Accuracy (PA), and boundary similarity. Notably, this model exhibits exceptional robustness and precision in segmentation tasks involving complex pore structures and low-contrast images. Full article