Search Results (8,719)

Accurateweed mapping in cereal fields requires pixel-level segmentation from unmanned aerial vehicle (UAV) imagery that remains reliable across fields, seasons, and illumination. Existing multispectral pipelines often depend on thresholded vegetation indices, which are brittle under radiometric drift and mixed crop–weed pixels, or on single-stream convolutional neural network (CNN) and Transformer backbones that ingest stacked bands and indices, where radiance cues and normalized index cues interfere and reduce sensitivity to small weed clusters embedded in crop canopy. We propose VISA (Vegetation Index and Spectral Attention), a two-stream segmentation network that decouples these cues and fuses them at native resolution. The radiance stream learns from calibrated five-band reflectance using local residual convolutions, channel recalibration, spatial gating, and skip-connected decoding, which preserve fine textures, row boundaries, and small weed structures that are often weakened after ratio-based index compression. The index stream operates on vegetation-index maps with windowed self-attention to model local structure efficiently, state-space layers to propagate field-scale context without quadratic attention cost, and Slot Attention to form stable region descriptors that improve discrimination of sparse weeds under canopy mixing. To support supervised training and deployment-oriented evaluation, we introduce BAWSeg, a four-year UAV multispectral dataset collected over commercial barley paddocks in Western Australia, providing radiometrically calibrated blue, green, red, red edge, and near-infrared orthomosaics, derived vegetation indices, and dense crop, weed, and other labels with leakage-free block splits. On BAWSeg, VISA achieves 75.6% mean Intersection over Union (mIoU) and 63.5% weed Intersection over Union (IoU) with 22.8 M parameters, outperforming a multispectral SegFormer-B1 baseline by 1.2 mIoU and 1.9 weed IoU. Under cross-plot and cross-year protocols, VISA maintains 71.2% and 69.2% mIoU, respectively. The full BAWSeg benchmark dataset, VISA code, trained model weights, and protocol files will be released upon publication. Full article

This paper reviews circuit topologies in the literature that aim to suppress submodule (SM) capacitor-voltage ripple of modular multilevel converters (MMCs), since this low-frequency ripple largely determines the required SM capacitance and thus the overall converter volume, cost, and reliability. The circuit topologies covered in this review include high-frequency (HF) magnetic or switched power channels, transformerless active channel or bridging cells with mid-cell connections, hybrid-MMC and DC-bus management options, SM-level active power decoupling (APD) and active power filters (APF), and structural modifications. Physical power-channel topologies (HF magnetic or switched auxiliary paths) suppress the $2\omega$ capacitor-voltage ripple by transferring the associated low-frequency ripple power to an auxiliary high-frequency path. Hybrid-MMC and direct-current (DC) bus management reduce the required capacitance with only a modest increase in hardware requirements. SM-level APD and APF cells transfer the ripple power into auxiliary storage. Structural and topological arrangements modify the converter architecture itself, leading to architectural simplification, passive attenuation, and a reduced need for measurement or balancing. The reviewed topologies are then compared in terms of ripple reduction, hardware complexity, additional components, cost, and control complexity, and the resulting evidence is synthesised into application-driven design trade-offs and selection guidelines. In addition, DC–DC MMC topologies are discussed separately in a contextual overview. Full article

Road extraction from high-resolution remote sensing images (HRSIs) is a fundamental task for many geospatial applications, yet it remains challenging due to complex backgrounds, frequent occlusions, and the requirement to preserve the topological connectivity of elongated road networks. To address these issues, this paper proposes SAM2-RoadNet, a topology-aware multi-scale road extraction framework that adapts the powerful representation capability of the Segment Anything Model 2 (SAM2) to HRSI road segmentation. Unlike prompt-driven segmentation paradigms, SAM2-RoadNet employs the SAM2 image encoder solely as a feature extractor and introduces an adapter-based domain adaptation strategy to efficiently transfer pretrained knowledge to the remote sensing domain. Receptive field blocks are further integrated to enhance contextual perception and align channel dimensions, followed by a weighted bidirectional feature pyramid network (W-BiFPN) to fuse hierarchical features across multiple scales. Moreover, a topology-aware training strategy based on the soft-clDice loss is incorporated to explicitly enforce structural continuity and reduce road fragmentation. Extensive experiments conducted on two challenging benchmarks, including DeepGlobe, Massachusetts, demonstrate that SAM2-RoadNet achieves superior overall performance across multiple evaluation metrics compared with state-of-the-art methods in both quantitative accuracy and qualitative visual quality, while demonstrating promising cross-dataset transferability without additional fine-tuning. Full article

Green finance has emerged as a crucial instrument for driving the macroeconomic transition toward a low-carbon economy, yet its specific transmission mechanisms warrant deeper empirical scrutiny. Leveraging China’s Green Finance Reform and Innovation Pilot Zones as a quasi-natural experiment, this scientific study employs a staggered difference-in-differences (DID) framework using provincial panel data from 2009 to 2023. To overcome the limitations of unidimensional metrics, we developed a comprehensive Industrial Structure Upgrading Index (ISUI) that integrates structural rationalization, advancement, and greening. The empirical findings reveal that the green finance pilot policy exerts a significant and positive impact on the ISUI. This core result remains robust under a series of rigorous checks, including the Callaway and Sant’Anna (CS-DID) estimator. Mechanism analyses demonstrate a dual “push–pull” dynamic: Green Credit Intensity (GCI) acts as the primary mediating channel by directing targeted financial resources (financial pull), while stringent environmental regulation positively moderates this effect (administrative push). Furthermore, the moderating role of digital finance is statistically non-significant, underscoring the policy’s broad inclusiveness and its independence from regional digital infrastructure. Heterogeneity estimations identify a clear structural catch-up effect, with more pronounced benefits observed in resource-dependent regions and areas with historically lower innovation capacities. Ultimately, these findings indicate that coordinating targeted financial incentives with environmental oversight can effectively drive multidimensional industrial upgrading, providing valuable evidence for sustainable transition strategies. Full article

Monocular 3D human–object interaction (HOI) reconstruction requires jointly recovering articulated human geometry, object pose, and physically plausible contact from a single RGB image. While recent token-based methods commonly employ dense self-attention to capture global dependencies, isotropic all-to-all mixing tends to entangle spatial-geometric cues (e.g., contact locality) with channel-wise semantic cues (e.g., action/affordance), and provides limited control for representing directional and asymmetric physical influence between humans and objects. This paper presents HOIMamba, a state-space sequence modeling framework that reformulates HOI reconstruction as bidirectional, multi-scale interaction state inference. Instead of relying on symmetric correlation aggregation, HOIMamba uses structured state evolution to propagate interaction evidence. We introduce a multi-scale state-space module (MSSM) to capture interaction dependencies spanning local contact details and global body–object coordination. Building on MSSM, we propose a spatial-channel grouped SSM (SCSSM) block that factorizes interaction modeling into a spatial pathway for geometric/contact dependencies and a channel pathway for semantic/functional correlations, followed by gated fusion. HOIMamba further performs explicit bidirectional propagation between human and object states to better reflect asymmetric reciprocity in physical interactions. We evaluate HOIMamba on two public benchmarks, BEHAVE and InterCap, using Chamfer distance for human/object meshes and contact precision/recall induced by reconstructed geometry. HOIMamba achieves consistent improvements over representative prior methods. On the BEHAVE dataset, it reduces human Chamfer distance by 8.6% and improves contact recall by 13.5% compared to the strongest Transformer-based baseline, with similar gains observed on the InterCap dataset. Ablation studies on BEHAVE verify the contributions of state-space modeling, multi-scale inference, spatial-channel factorization, and bidirectional interaction reasoning. Full article

Dust pollution has emerged as a critical issue in a wide range of industrial applications, creating an urgent demand for effective strategies to mitigate particle deposition. Recent experimental studies have demonstrated that superhydrophobic coatings represent a promising class of self-cleaning materials, primarily attributed to their hierarchical rough structures and intrinsically low surface energy. Nevertheless, the underlying self-cleaning mechanisms of superhydrophobic surfaces have not yet been fully elucidated. This work examines particle deposition on superhydrophobic surfaces featuring stochastic roughness distributions through computational modeling. Surface topographies were generated using Fast Fourier Transform techniques. An integrated lattice Boltzmann–discrete element method (LBM–DEM) framework simulated particle transport in superhydrophobic-coated channels. Particle–fluid coupling was achieved via the immersed moving boundary approach, while particle–surface interactions employed a modified Johnson–Kendall–Roberts (JKR) adhesion model. Parametric studies quantified effects of particle size, interfacial energy, flow Reynolds number, and topographical statistics on deposition dynamics. Experimental validation demonstrates good agreement between numerical predictions and measurements. Smaller particles exhibit a lower tendency to deposit on superhydrophobic surfaces, whereas increasing surface energy significantly enhances particle deposition due to stronger adhesion forces and the suppression of particle resuspension. In addition, higher Reynolds numbers effectively reduce particle deposition. The revealed self-cleaning mechanisms provide theoretical guidance for the design of high-performance self-cleaning coatings, and the identified effects of particle and surface parameters offer practical insights for anti-pollution engineering applications. Full article

Under China’s rural revitalization and agricultural modernization strategies, digital village construction overcomes resource limits to drive transformation. Using 2013–2022 provincial panel data and a case study of Lin’an, Hangzhou, this study reveals how digital villages boost high-quality agriculture. The empirical results show they significantly enhance agricultural total factor productivity via three paths: IoT-driven precision production, blockchain-enabled green value addition, and e-commerce direct sales demonstrate more pronounced effectiveness in major grain-producing regions and those characterized by balanced production and sales. Simultaneously, this study employs the instrumental variable (TI) approach to address endogeneity from reverse causality and omitted variables. Mechanism testing reveals agricultural technological innovation exerts a significant 77.5% mediating effect. Finally, digital rural construction exhibits a non-linear threshold (0.3082); surpassing it triggers a structural leap with increasing marginal returns. The Lin’an case validates the empirical results while revealing structural barriers, including industrial chain penetration gaps, data silos, and factor supply constraints, leading to the formulation of targeted optimization strategies. The practical contribution of this study is the proposal of a “data-value-technology” closed loop: public brands like “Tianmu Mountain Treasures” channel premiums into R&D funds, creating a self-sustaining mechanism. The findings indicate that digital villages drive high-quality agriculture primarily through direct effects, powered by full-chain tech coordination, institutional reform, and inclusive factor supply. Finally, this study proposes a coordinated governance framework encompassing “technical synergy, institutional innovation, and factor optimization,” providing theoretical support and strategic references for optimizing the pathways of regional agricultural digital transformation. Full article

Image restoration has wide applications in the field of computer vision, yet existing methods suffer from limitations. CNNs struggle to capture long-range dependencies, while transformers exhibit insufficient performance in handling local details and high computational complexity. Additionally, existing dual-branch networks fail to define a clear dominant–auxiliary role between branches, leading to redundancy and high computational costs. This paper proposes a Global Modulated Unbalanced Dual-Branch Network (GMUD-Net), which innovatively adopts an unbalanced structure with a CNN as the main branch and a transformer as the auxiliary branch. Specifically, the CNN branch achieves strong restoration capability by integrating the global–local hybrid backbone block (GLBB) and the frequency-based global attention module (FGAM). As the key building block in the CNN branch, GLBB integrates a local backbone branch, a global Fourier branch, and a residual branch to fuse local details with global context. Meanwhile, FGAM leverages the fast Fourier transform at the bottleneck to enhance cross-channel interaction and improve global restoration performance. In addition, the lightweight transformer branch employs efficient cross-channel attention to provide complementary global cues, which are filtered and injected into the CNN branch via the global attention guidance block (GAG). These designs integrate the advantages of both CNNs and transformers while significantly reducing computational burden, offering a new paradigm to address the limitations of traditional dual-branch architectures. Experimental results demonstrate that compared with existing algorithms, the proposed method achieves state-of-the-art or highly competitive performance in both quantitative evaluations and qualitative results across nine datasets. Full article

This study reconstructs the geography of meaning of the German perception verb schmecken on the basis of 30 major dialect dictionaries, treating them as a distributed semantic corpus and coding attestations as binary variables reflecting the presence or absence of semantic options. Combining a construal-based framework with spatial modeling, the analysis shows that the polysemy of schmecken is structured by three mutually reinforcing forces: embodied sensory organization, construal-based perspectivization, and regionally patterned areal dynamics. The gustatory–olfactory axis forms the semantic core of the verb, from which tactile, visual, affective, and epistemic extensions emerge. These extensions align with systematic pathways constrained by agentive, experiential, emissive, and evaluative construals, demonstrating that semantic extension is channeled through specific construal modes—notably emissive and agentive—rather than determined by sensory modality alone. A detailed areal analysis reveals a pronounced north–south divide. While Low German dialects conform to the cross-linguistically more common tendency to avoid colexifying taste and smekk—itself the outcome of historical change rather than uninterrupted differentiation—Upper German varieties preserve a typologically rare gustatory–olfactory cluster and exhibit the richest range of cross-modal and abstract extensions. The resulting semantic graph formalizes how regional varieties activate different subsets of a lexeme’s semantic potential and demonstrates that semantic networks themselves display spatial organization. The study thus provides an empirically grounded reconstruction of a German geography of meaning and illustrates how dialect data illuminate the interplay between embodied cognition, construal-based lexical architecture, and areal dynamics. Full article

To address the critical challenge of drilling fluid invasion in deep coalbed methane (CBM) reservoirs, this study provides novel insight into the micro-scale sealing mechanism and pore structure evolution by leveraging Low-Field Nuclear Magnetic Resonance (LF-NMR) as a quantitative probe. Unlike traditional macroscopic evaluations, we utilized dynamic NMR T₂ spectral analysis to decipher the synergistic behavior of a proposed “Bridging–Filling–Densifying” ternary sealing system, which integrates a nano-plugging agent, micro-fillers, and size-matched skeletal agents. The results demonstrate a significant improvement in sealing efficiency. The optimized hierarchical architecture reduced the NMR signal intensity of the invaded cores by over 99.8% under a differential pressure of 10 MPa, effectively eliminating fluid invasion channels. Crucially, the study reveals that while multi-scale particle size matching is the precondition for sealing, the mechanical rigidity of the skeletal particles is the determinant for maintaining filter cake integrity against high-pressure deformation. These findings elucidate the transition from a “macropore-dominated” structure to a “zero-detectable” sealed state, establishing a robust theoretical framework for designing non-damaging drilling fluids tailored to the complex geomechanics of deep CBM exploration. Full article

Background: The generation of synthetic CT images from MRI scans represents a crucial step toward enabling MRI-only clinical workflows and supporting multi-modal integration in medical imaging, particularly in radiotherapy planning. Despite significant advancements in deep learning models, many current methods still struggle to reconstruct high-density structures, especially bone, and exhibit limited accuracy in density values. This shortcoming is largely attributed to the passage of excessive or noisy features through skip connections in the traditional U-Net architecture, which degrade the quality of information transmitted to the decoder, negatively impacting the clarity of anatomical boundaries and the pixel-wise accuracy of the resulting synthetic image. Methods: In this work, we propose an enhanced 3D U-Net architecture in which the Convolutional Block Attention Module (CBAM) is systematically integrated within each skip connection. The CBAM sequentially applies channel and spatial attention to adaptively reweight encoder feature maps before fusion with the decoder, thereby emphasizing anatomically relevant structures while suppressing irrelevant feature propagation. The model was trained and evaluated on the SynthRAD2023 (Task 1—Brain) MRI–CT dataset. To rigorously assess the contribution of the attention mechanism, a dedicated ablation study was conducted comparing three variants: 3D U-Net with Squeeze-and-Excitation (SE), Coordinate Attention (CA), and the proposed CBAM module. Performance was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Normalized Cross-Correlation (NCC). Results: The ablation study demonstrated that the CBAM-enhanced model consistently outperformed both SE- and CA-based variants across all quantitative metrics. Specifically, the proposed method achieved an MAE of $38.2\pm 5.4$ HU and an RMSE of $51.0\pm 12.0$ HU, representing the lowest reconstruction errors among the evaluated models. In addition, it obtained a PSNR of $29.45\pm 2.10$ dB, SSIM of $0.940\pm 0.031$, and NCC of $0.967\pm 0.015$, indicating superior structural preservation and strong voxel-wise correspondence between synthesized and reference CT volumes. These results confirm that the sequential integration of channel and spatial attention provides a statistically and practically meaningful improvement for high-fidelity MRI-to-CT synthesis. Discussion and Conclusions: Generating high-resolution brain CT images from brain MRI scans using a 3D U-Net network enhanced with a CBAM module can contribute to supporting the clinical workflow by providing additional diagnostic data without the need for extra radiological examinations, thereby enhancing diagnostic efficiency and reducing radiation exposure. This technique helps reduce patient exposure to radiation and improves accessibility in resource-limited settings. Furthermore, this method is valuable for retrospective studies, surgical planning, and image-guided therapy, where complete multi-modal data may not always be available. Full article

Bacteria-based self-healing concrete is extensively shown to improve strength and durability; yet, the mechanistic relationship among microbial activity, damage progression, and transport resistance is still ambiguous. This study examines the interrelated mechanical and transport properties of concrete that incorporates Bacillus subtilis by directly substituting mixing water. Concrete mixtures with 0%, 5%, and 10% bacterial solution were assessed for compressive strength, complete stress–strain response, split tensile strength, flexural toughness, fast chloride ion penetration, and capillary sorptivity. X-ray diffraction was employed for microstructural validation. Results indicate a dose-dependent shift from brittle to quasi-ductile behavior, marked by augmented strain capacity, postponed crack localization, and improved post-cracking energy absorption. The mechanical alterations resulted in substantial decreases in chloride ion penetrability (up to 57%) and capillary sorptivity (up to 60%), signifying a drop in crack-assisted transport. X-ray diffraction verified the production of calcite resulting from microbial-induced calcium carbonate precipitation. The results indicate that the improvement in durability of bacterial concrete is attributable not only to pore filling but also to altered damage mechanisms that diminish the connectedness of transport channels, underscoring the potential of Bacillus subtilis as a bio-admixture for resilient structural concrete. Full article

Coastal wind turbines operate under severe salt spray, high humidity, and wind-driven erosion, which accelerate coating degradation and corrosion-induced cracking. In such environments, corrosion defects exhibit blurred boundaries, weak textures, and significant scale variations, challenging object detectors in small-target localization and precise boundary regression. To address these limitations, this study proposes CoastCor-Net, an enhanced YOLOv11-based framework that improves spatial–semantic alignment, boundary representation, and channel–spatial dependency modeling. The architecture integrates three complementary modules to enhance boundary sensitivity, spatial–semantic consistency, and cross-channel interaction: a Decoding-Driven Enhancement Block, a Complementary Feature Alignment Module, and a Channel-Transposed Coordinate Attention module. Extensive experiments on the Wind Turbine Blade Damage Dataset show that CoastCor-Net achieves 84.7% mAP@0.5 and 54.1% mAP@0.5:0.95, surpassing YOLOv13n by 3.2 percentage points in mAP@0.5 and improving AP_damage by 5.2 percentage points. The framework also demonstrates strong robustness under composite coastal perturbations. These findings highlight the practical effectiveness of structured multi-level feature enhancement for reliable and high-precision blade inspection in complex coastal environments. Full article

The human mitochondrial Lon protease (LonP1) is a central regulator of mitochondrial DNA copy number and metabolic reprogramming. However, the structural basis for how LonP1 recognizes native physiological substrates remains elusive. Here, we present the high-resolution cryo-EM structure of the human LonP1 hexamer actively engaging its native substrate, TFAM. The reconstruction reveals a distinct bipartite search-and-shred mechanism. Unlike its bacterial homologs, the human N-terminal domain (NTD) adopts a compact architecture acting as a selective vestibule to recruit and initially unfold the substrate tertiary structure. Subsequently, the polypeptide is threaded through the central channel via a hand-over-hand mechanism driven by a spiral array of aromatic pore-loops. This structural framework provides a mechanistic rationale for the spatial segregation of LonP1 and offers a template for targeting mitochondrial proteostasis in human diseases. Full article

In structured orchard environments, harvesting robots operate where rigid bodies (e.g., trunks, poles, and wires) coexist with flexible foliage. Strict avoidance of all obstacles significantly compromises operational efficiency. To address this, this study proposes an end-to-end autonomous harvesting framework characterized by an “avoid-rigid, push-through-soft” strategy. This framework explicitly propagates uncertainties from sensor data and reconstruction processes into the planning and policy phases. First, a multi-task perception network acquires 2D semantic masks of fruits and branches. Class probabilities and instance IDs are back-projected onto a 3D Gaussian Splatting (3DGS) representation to construct a decision-oriented, semantically enhanced 3D scene model. The policy network accepts multi-channel 3DGS rendered observations and proprioceptive states as inputs, outputting a continuous preference vector over eight predefined motion primitives. This approach unifies path planning and action decision-making within a single closed loop. Additionally, a dynamic action shielding module was designed to perform look-ahead collision risk assessments on candidate discrete actions. By employing an action mask to block actions potentially colliding with rigid obstacles, high-risk behaviors are effectively suppressed during both training and execution, thereby enhancing the robustness and reliability of robotic manipulation. The proposed method was validated in both simulation and real-world scenarios. In complex orchard scenarios, the proposed AE-TD3 algorithm achieves a harvesting success rate of 77.1%, outperforming existing RRT (53.3%), DQN (60.9%), and TD3 (63.8%) methods. Furthermore, the method demonstrates superior safety and real-time performance, with a collision rate reduced to 16.2% and an average operation time of only 12.4 s. Results indicate that the framework effectively supports efficient harvesting operations while ensuring safety. Full article