Search Results (1,221)

Monocular depth estimation is one of the key tasks in autonomous driving, which derives depth information of the scene from a single image. And it is a fundamental component for vehicle decision-making and perception. However, approaches currently face challenges such as visual artifacts, scale ambiguity and occlusion handling. These limitations lead to suboptimal performance in complex environments, reducing model efficiency and generalization and hindering their broader use in autonomous driving and other applications. To solve these challenges, this paper introduces a Neural Radiance Field (NeRF)-based monocular depth estimation method for autonomous driving. It introduces a Gaussian probability-based ray sampling strategy to effectively solve the problem of massive sampling points in large complex scenes and reduce computational costs. To improve generalization, a lightweight spherical network incorporating a fine-grained adaptive channel attention mechanism is designed to capture detailed pixel-level features. These features are subsequently mapped to 3D spatial sampling locations, resulting in diverse and expressive point representations for improving the generalizability of the NeRF model. Our approach exhibits remarkable performance on the KITTI benchmark, surpassing traditional methods in depth estimation tasks. This work contributes significant technical advancements for practical monocular depth estimation in autonomous driving applications. Full article

Precise identification of weeds at the maize seedling stage is pivotal for implementing Site-Specific Weed Management and minimizing herbicide environmental pollution. However, the performance of existing lightweight detectors is severely bottlenecked by unstructured field environments, characterized by the “green-on-green” spectral similarity between crops and weeds, diminutive seedling targets, and complex mutual occlusion of leaves. To address these challenges, this study proposes SLD-YOLO11, a topology-reconstructed lightweight detection model tailored for complex field environments. First, to mitigate the feature loss of tiny targets, a Lossless Downsampling Topology based on Space-to-Depth Convolution (SPD-Conv) is constructed, transforming spatial information into depth channels to preserve fine-grained features. Second, a Decomposed Large Kernel Attention (D-LKA) mechanism is designed to mimic the wide receptive field of human vision. By modeling long-range spatial dependencies with decomposed large-kernel attention, it enhances discrimination under severe occlusion by leveraging global structural context. Third, the DySample operator is introduced to replace static interpolation, enabling content-aware feature flow reconstruction. Experimental results demonstrate that SLD-YOLO11 achieves an mAP@0.5 of 97.4% on a self-collected maize field dataset, significantly outperforming YOLOv8n, YOLOv10n, YOLOv11n, and mainstream lightweight variants. Notably, the model achieves Zero Inter-class Misclassification between maize and weeds, establishing high safety standards for weeding operations. To further bridge the gap between visual perception and precision operations, a Visual Weed-Crop Competition Index (VWCI) is innovatively proposed. By integrating detection bounding boxes with species-specific morphological correction coefficients, the VWCI quantifies field weed pressure with low cost and high throughput. Regression analysis reveals a high consistency (R² = 0.70) between the automated VWCI and manual ground-truth coverage. This study not only provides a robust detector but also offers a reliable decision-making basis for real-time variable-rate spraying by intelligent weeding robots. Full article

Improving sensitivity in short-wave infrared (SWIR) detection is crucial for low-signal applications, such as astronomy and hyperspectral imaging, which demand readout integrated circuits (ROICs) with minimal noise and high density. However, conventional differential pixels with correlated double sampling (CDS) are difficult to integrate due to spatial limitations. In order to tackle this issue, we propose a compact, pixel-level, single-ended charge-domain architecture. It integrates single-ended CDS within each pixel, guaranteeing compatibility with the integrate-while-read (IWR) mode while suppressing reset and 1/f noise. A capacitor reuse technique is also proposed to enable the integration capacitor to function as an auxiliary load, which optimizes the noise–area trade-off. Fabricated in 180 nm CMOS, our 1296 × 256 ROIC attains a noise floor of 0.50 mV (achieving a reduction of approximately 70% compared to conventional architectures under identical conditions), consumes under 200 mW, and operates at frequencies exceeding 200 Hz. It also exhibits great linearity (0.9999) and supports both integrate-then-read (ITR) mode and integrate-while-read (IWR) mode, while also providing a row-level gain selecting function. Validated at 15 μm pitch, this design provides an effective option for high-density SWIR systems. Full article

Existing 3D point cloud enhancement methods typically rely on artificially designed geometric transformations or local blending strategies, which are prone to introducing illogical deformations, struggle to preserve global structure, and exhibit insufficient adaptability to diverse degradation patterns. To address these limitations, this paper proposes SFD-ADNet—an adaptive deformation framework based on a dual spatial–frequency domain. It achieves 3D point cloud augmentation by explicitly learning deformation parameters rather than applying predefined perturbations. By jointly modeling spatial structural dependencies and spectral features, SFD-ADNet generates augmented samples that are both structurally aware and task-relevant. In the spatial domain, a hierarchical sequence encoder coupled with a bidirectional Mamba-based deformation predictor captures long-range geometric dependencies and local structural variations, enabling adaptive position-aware deformation control. In the frequency domain, a multi-scale dual-channel mechanism based on adaptive Chebyshev polynomials separates low-frequency structural components from high-frequency details, allowing the model to suppress noise-sensitive distortions while preserving the global geometric skeleton. The two deformation predictions dynamically fuse to balance structural fidelity and sample diversity. Extensive experiments conducted on ModelNet40-C and ScanObjectNN-C involved synthetic CAD models and real-world scanned point clouds under diverse perturbation conditions. SFD-ADNet, as a universal augmentation module, reduces the mCE metrics of PointNet++ and different backbone networks by over 20%. Experiments demonstrate that SFD-ADNet achieves state-of-the-art robustness while preserving critical geometric structures. Furthermore, models enhanced by SFD-ADNet demonstrate consistently improved robustness against diverse point cloud attacks, validating the efficacy of adaptive space-frequency deformation in robust point cloud learning. Full article

In the last decade, the interdisciplinary field of neuroarchitecture has grown significantly, revealing measurable links between architectural features and human neural processing. This review synthesizes current research at the nexus of neuroscience and architecture, with a focus on how emerging virtual reality (VR) and artificial intelligence (AI) technologies are being utilized to understand and enhance human spatial experience. We systematically reviewed literature from 2015 to 2025, identifying key empirical studies and categorizing advances into three themes: core components of neuroarchitectural research; the use of physiological sensors (e.g., EEG, heart rate variability) and virtual reality to gather data on occupant responses; and the integration of neuroscience with AI-driven analysis. Findings indicate that built environment elements (e.g., geometry, curvature, lighting) influence brain activity in regions governing emotion, stress, and cognition. VR-based experiments combined with neuroimaging and physiological measures enable ecologically valid, fine-grained analysis of these effects, while AI techniques facilitate real-time emotion recognition and large-scale pattern discovery, bridging design features with occupant emotional responses. However, the current evidence base remains nascent, limited by small, homogeneous samples and fragmented data. We propose a four-domain framework (somatic, psychological, emotional, cognitive-“SPEC”) to guide future research. By consolidating methodological advances in VR experimentation, physiological sensing, and AI-based analytics, this review provides an integrative roadmap for replicable and scalable neuroarchitectural studies. Intensified interdisciplinary efforts leveraging AI and VR are needed to build robust, diverse datasets and develop neuro-informed design tools. Such progress will pave the way for evidence-based design practices that promote human well-being and cognitive health in built environments. Full article

Candida albicans is a major fungal pathogen associated with vulvovaginal candidiasis, and rapid, sensitive detection remains challenging, particularly in amplification-free formats. Here, we report NaPddCas, a microfluidic-free, droplet-based CRISPR/Cas12a detection strategy for qualitative identification of Candida albicans DNA. Unlike conventional bulk CRISPR assays, NaPddCas partitions the reaction mixture into vortex-generated polydisperse droplets, enabling spatial confinement of Cas12a activation events and effective suppression of background fluorescence. This compartmentalization substantially enhances detection sensitivity without nucleic acid amplification or microfluidic devices. Using plasmid and genomic DNA templates, NaPddCas achieved reliable detection at concentrations several orders of magnitude lower than bulk CRISPR/Cas12a reactions. The assay further demonstrated high specificity against non-target bacterial and fungal species and was successfully applied to clinical vaginal secretion samples. Importantly, NaPddCas is designed as a qualitative or semi-qualitative droplet-dependent digital detection method rather than a quantitative digital assay. Owing to its simplicity, sensitivity, and amplification-free workflow, NaPddCas represents a practical approach for laboratory-based screening of Candida albicans infections. Full article

The current intrusion detection methods suffer from deficiencies in terms of cross-domain adaptability, privacy preservation, and limited effectiveness in detecting minority-class attacks. To address these issues, a novel intrusion detection model framework, TrMulS, is proposed that integrates federated learning, generative adversarial networks with multispace feature enhancement ability, and transformers with multi-source transfer ability. First, at each institution (source domain), local spatial features are extracted through a CNN, multiple subsets are constructed (to solve the feature singularity problem), and the multihead self-attention mechanism of the transformer is utilized to capture the correlation of features. Second, the synthetic samples of the target domain are generated on the basis of the improved Exchange-GAN, and the cross-domain transfer module is designed by combining the Maximum Mean Discrepancy (MMD) to minimize the feature distribution difference between the source domain and the target domain. Finally, the federated transfer learning strategy is adopted. The model parameters of each local institution are encrypted and uploaded to the target server and then aggregated to generate the global model. These steps iterate until convergence, yielding the globally optimal model. Experiments on the ISCX2012, KDD99 and NSL-KDD intrusion detection standard datasets show that the detection accuracy of this method is significantly improved in cross-domain scenarios. This paper presents a novel paradigm for cross-domain security intelligence analysis that considers efficiency, privacy and balance. Full article

The automated localization of the flange interface in LNG tanker loading and unloading imposes stringent requirements for accuracy and illumination robustness. Traditional monocular vision methods are prone to localization failure under extreme illumination conditions, such as intense glare or low light, while LiDAR, despite being unaffected by illumination, suffers from limitations like a lack of texture information. This paper proposes an illumination-robust localization method for LNG tanker flange interfaces by fusing monocular vision and LiDAR, with three scenario-specific innovations beyond generic multi-sensor fusion frameworks. First, an illumination-adaptive fusion framework is designed to dynamically adjust detection parameters via grayscale mean evaluation, addressing extreme illumination (e.g., glare, low light with water film). Second, a multi-constraint flange detection strategy is developed by integrating physical dimension constraints, K-means clustering, and weighted fitting to eliminate background interference and distinguish dual flanges. Third, a customized fusion pipeline (ROI extraction-plane fitting-3D circle center solving) is established to compensate for monocular depth errors and sparse LiDAR point cloud limitations using flange radius prior. High-precision localization is achieved via four key steps: multi-modal data preprocessing, LiDAR-camera spatial projection, fusion-based flange circle detection, and 3D circle center fitting. While basic techniques such as LiDAR-camera spatiotemporal synchronization and K-means clustering are adapted from prior works, their integration with flange-specific constraints and illumination-adaptive design forms the core novelty of this study. Comparative experiments between the proposed fusion method and the monocular vision-only localization method are conducted under four typical illumination scenarios: uniform illumination, local strong illumination, uniform low illumination, and low illumination with water film. The experimental results based on 20 samples per illumination scenario (80 valid data sets in total) show that, compared with the monocular vision method, the proposed fusion method reduces the Mean Absolute Error (MAE) of localization accuracy by 33.08%, 30.57%, and 75.91% in the X, Y, and Z dimensions, respectively, with the overall 3D MAE reduced by 61.69%. Meanwhile, the Root Mean Square Error (RMSE) in the X, Y, and Z dimensions is decreased by 33.65%, 32.71%, and 79.88%, respectively, and the overall 3D RMSE is reduced by 64.79%. The expanded sample size verifies the statistical reliability of the proposed method, which exhibits significantly superior robustness to extreme illumination conditions. Full article

Pedestrian safety in developing countries faces critical challenges from rapid urbanization and infrastructure deficiencies. This study investigates how visual context influences pedestrian crossing preferences through a controlled stated preference experiment in multiple Ecuadorian cities. A sample of 875 participants was randomly assigned to view either non-compliant (mid-block crossing) or compliant (signalized crosswalk) imagery before evaluating six hypothetical scenarios involving three crossing alternatives. Multinomial logit models reveal that waiting time, traveling with a minor, and walking distance are primary determinants of choice. Visual context showed systematic associations with choice patterns: compliant imagery was associated with increased preference for safer alternatives (50.5% versus 43.8% prediction accuracy) and larger safety-related parameter magnitudes. Principal Component Analysis identified two latent perception constructs, safety/security and bridge-specific convenience, providing behavioral interpretation of choice patterns. Substantial spatial heterogeneity emerged across cities (χ² = 124.10 and 84.74, p < 0.001), with larger urban centers showing stronger responsiveness to formal infrastructure cues. The findings demonstrate that visual stimuli systematically alter choice distributions and attribute sensitivities through normative activation and perceptual recalibration. This research contributes methodologically by establishing visual framing effects in stated preference frameworks and provides actionable insights for pedestrian infrastructure design, emphasizing alignment of objective safety improvements with perceived risk and contextual behavioral cues. Full article

Accurate characterization of ore grindability is essential for optimizing mill throughput, reducing energy consumption, and predicting mill performance under varying ore conditions. However, the standard Bond work index (BWI) test remains time-consuming, costly, and requires a large amount of sample. This study evaluates the effectiveness of several rapid, low-cost alternatives, Leeb rebound hardness (LRH), Cerchar abrasivity Index (CAI), portable X-ray fluorescence (pXRF), and hyperspectral imaging (HSI), as proxies for grindability in gold-bearing ores. Sixty-two hand-size rock samples collected from two adjacent Canadian open-pit mines were analyzed using these techniques and subsequently grouped into ten ore groups for BWI testing. LRH and CAI effectively differentiated moderate (<15 kWh/t) from hard (>15 kWh/t) grindability classes, while geochemical features and HSI-based mineralogical attributes also showed strong predictive capability. HSI, in particular, provided non-destructive, spatially continuous data that are advantageous for complex geology and large-scale operational deployment. A conceptual workflow integrating HSI with complementary field measurements is proposed to support comminution planning and optimization, enabling more responsive and timely decision-making. While BWI testing remains necessary for circuit design, the results highlight the value of combining rapid proxy measurements with advanced analytics to enhance geometallurgical modelling, reduce operational risk, and improve overall mine-to-mill performance. Full article

Background/Objectives: Swimming requires precise motor control, sustained attention, and optimal cognitive–motor integration, making it an ideal model for investigating neural efficiency—the phenomenon whereby expert performers achieve optimal outcomes with reduced neural resource expenditure, operationalized as lower activation, sparser connectivity, and enhanced functional integration. This systematic review examined cognitive performance and neural adaptations in swimming athletes, investigating neuroimaging and behavioral outcomes distinguishing swimmers from non-athletes across performance levels. Methods: Following PRISMA 2020 guidelines, seven databases were searched (1999–2024) for studies examining cognitive/neural outcomes in swimmers using neuroimaging or validated assessments. A total of 24 studies (neuroimaging: n = 9; behavioral: n = 15) met the inclusion criteria. Risk of bias assessment used adapted Cochrane RoB2 and Newcastle–Ottawa Scale criteria. Results: Neuroimaging modalities included EEG (n = 4), fMRI (n = 2), TMS (n = 1), and ERP (n = 2). Key associations identified included the following: (1) Neural Efficiency: elite swimmers showed sparser upper beta connectivity (35% fewer connections, d = 0.76, p = 0.040) and enhanced alpha rhythm intensity (p ≤ 0.01); (2) Cognitive Performance: superior attention, working memory, and executive control correlated with expertise (d = 0.69–1.31), with thalamo-sensorimotor functional connectivity explaining 41% of world ranking variance (r² = 0.41, p < 0.001); (3) Attention: external focus strategies improved performance in intermediate swimmers but showed inconsistent effects in experts; (4) Mental Fatigue: impaired performance in young adult swimmers (1.2% decrement, d = 0.13) but not master swimmers (p = 0.49); (5) Genetics: COMT Val158Met polymorphism associated with performance differences (p = 0.026). Effect sizes ranged from small to large, with Cohen’s d = 0.13–1.31. Conclusions: Swimming expertise is associated with specific neural and cognitive characteristics, including efficient brain connectivity and enhanced cognitive control. However, cross-sectional designs (88% of studies) and small samples (median n = 36; all studies underpowered) preclude causal inference. The lack of spatially quantitative synthesis and visualization of neuroimaging findings represents a methodological limitation of this review and the field. The findings suggest potential applications for talent identification, training optimization, and mental health promotion through swimming but require longitudinal validation and development of standardized swimmer brain atlases before definitive recommendations. Full article

To address the challenges of insufficient efficiency and accuracy in traditional detection models caused by minute target sizes, low signal-to-noise ratios (SNRs), and feature volatility in Satellite Laser Ranging (SLR) images, this paper proposes an efficient, lightweight, and high-precision detection model. The core motivation of this study is to fundamentally enhance the model’s capabilities in feature extraction, fusion, and localization for minute and blurred targets through a specifically designed network architecture and loss function, without significantly increasing the computational burden. To achieve this goal, we first design a DMS-Conv module. By employing dense sampling and channel function separation strategies, this module effectively expands the receptive field while avoiding the high computational overhead and sampling artifacts associated with traditional multi-scale methods, thereby significantly improving feature representation for faint targets. Secondly, to optimize information flow within the feature pyramid, we propose a Lightweight Upsampling Module (LUM). Integrating depthwise separable convolutions with a channel reshuffling mechanism, this module replaces traditional transposed convolutions at a minimal computational cost, facilitating more efficient multi-scale feature fusion. Finally, addressing the stringent requirements for small target localization accuracy, we introduce the MPD-IoU Loss. By incorporating the diagonal distance of bounding boxes as a geometric penalty term, this loss function provides finer and more direct spatial alignment constraints for model training, effectively boosting localization precision. Experimental results on a self-constructed real-world SLR observation dataset demonstrate that the proposed model achieves an ${\mathrm{mAP}}_{50:95}$ of 47.13% and an F1-score of 88.24%, with only 2.57 M parameters and 6.7 GFLOPs. Outperforming various mainstream lightweight detectors in the comprehensive performance of precision and recall, these results validate that our method effectively resolves the small target detection challenges in SLR scenarios while maintaining a lightweight design, exhibiting superior performance and practical value. Full article

The 3D reconstruction of vessel hulls is crucial for enhancing safety, efficiency, and knowledge in the maritime industry. Neural Radiance Fields (NeRFs) are an alternative to 3D reconstruction and rendering from multi-view images; particularly, tensor-based methods have proven effective in improving efficiency. However, existing tensor-based methods typically suffer from a lack of spatial coherence, resulting in gaps in the reconstruction of fine-grained geometric structures. This paper proposes a spatial multi-scale weighted NeRF (MDW-NeRF) for accurate and efficient surface reconstruction of vessel hulls. The proposed method develops a novel multi-scale feature decomposition mechanism that models 3D space by leveraging multi-resolution features, facilitating the integration of high-resolution details with low-resolution regional information. We designed separate color and density weighting, using a coarse-to-fine strategy, for density and a weighted matrix for color to decouple feature vectors from appearance attributes. To boost the efficiency of 3D reconstruction and rendering, we implement a hybrid sampling point strategy for volume rendering, selecting sample points based on volumetric density. Extensive experiments on the SVH dataset confirm MDW-NeRF’s superiority: quantitatively, it outperforms TensoRF by 1.5 dB in PSNR and 6.1% in CD, and shrinks the model size by 9%, with comparable training times; qualitatively, it resolves tensor-based methods’ inherent spatial incoherence and fine-grained gaps, enabling accurate restoration of hull cavities and realistic surface texture rendering. These results validate our method’s effectiveness in achieving excellent rendering quality, high reconstruction accuracy, and timeliness. Full article

In the context of industrial heritage conservation and adaptive reuse, the transformation of industrial buildings into patriotic education bases has emerged as a significant approach, where enhancing emotional education efficacy becomes crucial. This study adopts an evidence-based design (EBD) methodology, focusing on the Siwangzhang patriotic education base in Guangdong Province, to address the scientific evaluation and optimization of emotional arousal efficacy. The research rigorously follows the standardized EBD workflow: (1) during problem definition, the literature review establishes the dual objectives of quantitative assessment and spatial optimization; (2) evidence collection employs questionnaire surveys to capture emotional data from both static environmental nodes and dynamic activity nodes; (3) evidence analysis integrates descriptive analysis, factor analysis, emotional mapping visualization, and paired-sample t-tests. Key findings reveal the following: (1) spatial emotional distribution exhibits three distinct patterns—high-arousal clusters, single-node prominence areas, and emotional depressions; (2) dynamic training activities significantly enhance 66.7% of observed emotional variables. A seven-stage progressive training protocol was developed to achieve phased emotional cultivation. This study validates the applicability of EBD methodology in educational space optimization through a complete workflow, establishing an operational evaluation framework integrating spatial-behavioral-emotional metrics. It provides empirical evidence for targeted optimization of patriotic education bases while pioneering a data-driven transition from conventional experiential design. The results hold theoretical and practical significance for revitalizing industrial heritage through socially valuable functional transformations. Full article

Soil degradation and limited root-exploitable depth restrict maize productivity in Plinthosols of tropical regions. However, the combined effects of subsoiling and amendments derived from termite mound materials on soil functionality and yield remain insufficiently quantified. This study examines how variations in a functionally exploitable rooting depth, within a management system combining subsoiling and termite mound amendments, are associated with soil physicochemical properties and spatial variability of maize (Zea mays L.) grain yield in the Lubumbashi region of the Democratic Republic of the Congo. Spatial soil sampling and correlation analyses were used to identify the dominant pedological factors controlling yield variability. The results indicate a reduced vertical stratification of most nutrients within the explored depth, reflecting a more homogeneous distribution of soil properties within the managed profile, although direct causal attribution to specific practices cannot be established in the absence of untreated control plots. Improved rooting conditions were reflected by high and spatially variable productivity (2.3 to 11.1 t ha⁻¹ across blocks), accompanied by a moderate average gain between seasons (<1 t ha⁻¹), while extractable manganese emerged as a consistent negative predictor of yield. These patterns are consistent with a larger functionally exploitable rooting depth and an improved soil environment, although causal contributions of subsoiling and termite mound amendments cannot be isolated in the absence of control plots. Overall, the results highlight the importance of jointly considering structural and chemical soil properties when interpreting productivity gradients in Plinthosols and designing sustainable management strategies for degraded tropical soils. Full article