Search Results (275)

Pedestrian gender recognition plays an important role in pedestrian analysis and intelligent video applications, for example, in demographic statistics, soft biometric analysis, and context-aware person retrieval. However, it remains a challenging task owing to viewpoint variations, illumination changes, occlusions, and low image quality in real-world imagery. To address these issues, an effective adaptive decision fusion framework, termed the Decision Fusion Learning Network (DFLN), is proposed in this paper. The key novel aspect of DFLN is that it effectively explores both an appearance-centered view that emphasizes detailed texture and clothing information and a structure-centered view that captures rich contour and structural information for pedestrian gender recognition. To realize DFLN, a Parallel CNN Prediction Probability Learning Module (PCNNM) is first constructed to independently learn modality-specific probabilities from color image and edge maps. Subsequently, a learnable Decision Fusion Module (DFM) is designed to fuse the modality-specific probabilities and explore their complementary merits for realizing accurate pedestrian gender recognition. The DFM can be easily coupled with the PCNNM, forming an end-to-end decision fusion learning framework that simultaneously learns the feature representations and carries out adaptive decision fusion. Experiments on two pedestrian benchmark datasets, named PETA and PA-100K, show that DFLN achieves competitive or superior performance compared with several state-of-the-art pedestrian gender recognition methods. Extensive experimental analysis further confirms the effectiveness of the proposed decision fusion strategy and its favorable generalization ability under domain shift. Full article

Visual perception in Unmanned Surface Vehicles (USVs) suffers from drastic lighting changes and missing texture features. These factors lead to depth scale drift and motion estimation bias. Moreover, existing multi-modal fusion models are computationally complex and unfit for resource-limited edge devices. To address these problems, a lightweight Radar–Vision Fusion (Geo-RVF) algorithm is proposed. To supplement spatial information, point clouds are projected to build sparse depth maps. A probability consistency-based depth correction module is designed to suppress water noise. This helps extract accurate geometric anchors to guide visual depth propagation. Subsequently, a Recurrent Autoregressive Network (RAN) fuses radar and image features in the temporal dimension. This resolves dynamic positional deviations caused by texture degradation and distant small targets. After real-time optimization, Geo-RVF achieves 23 FPS on the Jetson Orin NX. On a collected dataset, the method attains a mean average precision (mAP) 50–90 of 44.2% and a mean intersection over union (mIoU) of 99%, outperforming HybridNets and Achelous. Full article

Granites of the Cornubian batholith of SW England and their host rocks are variably cross-cut by quartz–feldspar porphyry (QFP) and microgranite sheet intrusions locally referred to as elvan dykes. These are usually relatively potassic, have a porphyritic texture, and are often spatially and temporally associated with mineralisation. The processes by which they became so K-rich, their interaction with wall rocks, and their role in mineralisation remain poorly understood. Based on studies of a mineralised QFP dyke in the Tregonning Hill area of SW England, we present micro-textural and whole-rock geochemical evidence for potassic and then sericitic metasomatism of the dyke and its slate wall rocks, the latter to a rock strongly resembling granite, which could confound the identification of xenoliths and mapping of granite contacts. The metasomatism was caused by the through-flow of magmatic–hydrothermal fluids via inter-crystal pathways within a fluid–crystal mush, as evidenced by the presence of a network of vermiform micro-quartz veinlets that feed polymetallic quartz veins. QFP dykes acting as fluid–mush conduits, probably tapping larger underlying fluid-enriched mush reservoirs, is consistent with their association with metasomatism and mineralisation. Full article

The newly identified greisen-hosted Nb-Ta mineralization in the Qidashan iron deposit, Liaoning Province, China, offers a unique opportunity to explore how hydrothermal processes contribute to the enrichment of critical metals. In this study, an integrated analytical approach of petrographic observation and scanning electron microscopy–energy-dispersive spectrometer (SEM-EDS), electron probe microanalyzer (EPMA), and laser ablation inductively coupled plasma mass spectrometer (LA-ICP-MS) U-Pb dating of columbite-group minerals (CGMs) were employed to systematically decipher the paragenetic sequence, micro-structure, elemental composition and mineralization age of CGMs, aiming at the genesis of greisen-hosted Nb-Ta mineralization. The mineralization is characterized by the abundant occurrence of CGMs. Three generations of CGMs and two mineralization stages are distinguished: stage I contains CGM Is and CGM IIs, with Nb₂O₅ ranging from 25.7 to 69.56 wt.% and Ta₂O₅ from 5.8 to 52.5 wt.%; stage II contains CGM IIIs, with Nb₂O₅ between 59.5 and 71.5 wt.% and Ta₂O₅ between 3.5 and 16.2 wt.%. CGM Is consist of euhedral, homogeneous crystals of more than 100 μm, exhibit low Ta/(Nb + Ta) ratios (0.05–0.06) and high Mn/(Fe + Mn) ratios (0.19–0.26), and belong to columbite-Fe. CGM IIs generally overgrow on CGM Is with hydrothermal overprinting textures, and show significant compositional gaps compared to CGM Is, exhibiting higher Ta/(Nb + Ta) ratios (0.13–0.55) and restricted Mn/(Fe + Mn) ratios (0.15–0.18), with some belonging to columbite-Fe and others to tantalite-Fe, which reveals a transition from magma to “hydrosilicate fluid”. CGM IIIs are mainly anhedral and homogeneous, with a grain size of less than 50 μm. However, some CGM IIIs overgrow on CGM IIs and/or CGM Is with patchy textures indicative of subsequent hydrothermal overprinting of hydrosilicate fluid, forming a coarse-grain size over 100 μm. CGM IIIs are characterized by lower Ta/(Nb + Ta) ratios (0.03–0.14) and variable Mn/(Fe + Mn) ratios (0.08–0.26), and they belong to columbite-Fe. LA-ICP-MS U-Pb dating yields weighted mean ²⁰⁶Pb/²³⁸U ages of 2646 ± 15 Ma for stage I and 2500 ± 28 Ma for stage II, indicating two-stage Nb-Ta mineralization. The early mineralization may correlate with the partial melting of volcanic–sedimentary rocks due to the geothermal anomalies associated with ~2.7 Ga submarine volcanism, and the late mineralization formed by the magmatic hydrothermal activities related to emplacement of the Qidashan granite in 2.5 Ga. We therefore propose that the two-stage greisen-hosted Nb-Ta mineralization probably widely occurred in these sedimentary–metamorphic iron deposits in the Anshan–Benxi area and even in the northern edge of the North China Craton, and it may provide new insights for evaluating the Nb-Ta resource potential in similar Algoma-type iron deposits globally. Full article

Soiling of solar panels has a considerable impact on the performance of photo voltaic (PV) systems, emphasizing the importance of developing reliable decision support tools for solar panel cleaning. Although recent convolutional neural network (CNN)-based models, including lightweight architectures such as SolPowNet, have demonstrated high classification accuracy, their performance can be sensitive to dataset variability and domain shifts encountered in real-world PV environments. Motivated by the lightweight design philosophy of SolPowNet, this paper proposes a hybrid and ensemble-based intelligent cleaning decision framework that integrates classical image processing, machine learning, and deep learning techniques. The proposed approach combines physically interpretable handcrafted texture and sharpness features classified using a Random Forest model with a pretrained MobileNetV3-Small CNN through a conservative OR-based ensemble fusion strategy. In addition, a probability-driven Soiling Index (SI) is introduced to translate classification confidence into actionable cleaning decisions, including no cleaning, light cleaning, and full cleaning. Experimental results on multiple PV image datasets demonstrate that, under domain-shift conditions where individual models may experience performance degradation, the proposed ensemble framework achieves an accuracy of up to 85.93% and attains a dusty-panel detection rate of 0.90 on the unseen dataset. On the in-distribution evaluation, the proposed OR-ensemble achieves an average accuracy of 0.9663 ± 0.0177 with dusty recall of 0.9896 ± 0.0104 over repeated stratified runs. Importantly, the conservative fusion strategy minimizes high-risk false negative cases while avoiding excessive misclassification of clean panels. Overall, the proposed framework offers a robust, scalable, and deployment-ready solution for intelligent PV cleaning decision support, advancing CNN-based soiling detection toward practical and risk-aware operation and maintenance systems. Full article

Epichloë sinensis engages in mutualistic symbiosis with Festuca sinensis on the Qinghai–Tibet Plateau. The influence of variation within the Epichloë genus on morphology in this context is poorly understood, as is the influence of environmental factors (e.g., temperature, precipitation, and altitude). Accordingly, a total of 122 fungal endophyte strains were isolated from 270 F. sinensis seeds collected from different locations on the Qinghai–Tibet Plateau, and their morphological characteristics were observed. The colonies were white on the front, dark brown in the center on the back, and light brown or yellow around the PDA medium, exhibiting typical characteristics of E. sinensis. Morphological diversity was categorized into (1) colony features (six types based on texture, shape, and cracks), (2) growth rates (51 strains that produce spores: 0.23–0.78 mm/d; 71 strains that do not produce spores: 0.11–0.93 mm/d), and (3) hyphal width (51 strains that produce spores: 0.60–2.57 μm; 71 strains that do not produce spores: 0.95–2.10 μm). Correlation analyses revealed that temperature and altitude had significant effects on these traits. Phylogenetic relationships showed that 17 strains probably were E. sinensis, and only 4 strains probably were the endophyte E. poae. One strain was haploid and may have originated from E. festucae. All 22 tested strains lacked genes associated with toxic alkaloid biosynthesis (ergot alkaloid) but harbored regulatory genes for the insect-resistant alkaloid peramine, demonstrating potential for use in developing new germplasm in Festuca species. Full article

Reliable autonomous perception is essential for indoor service machines operating in human-centered environments, where weak textures, repetitive structures, and frequent dynamic interference often degrade localization stability. Conventional RGB-D SLAM systems typically rely on static-scene assumptions or binary semantic masking, which are insufficient for handling persistent and fine-grained environmental dynamics. This paper presents a robust autonomous perception framework based on geometry-aware RGB-D SLAM, with a particular emphasis on probabilistic dynamic modeling at the feature level. The proposed system integrates multi-granularity geometric representations, including point features, parallel-line structures, and planar regions, to enhance geometric observability in low-texture indoor environments. On this basis, a probabilistic dynamic model is introduced to explicitly characterize feature reliability under motion, where dynamic probabilities are initialized by object detection and continuously updated through temporal consistency, spatial propagation, and multi-view geometric verification. Large-scale planar structures further serve as stable anchors to support robust pose estimation. Experimental results on the TUM RGB-D dynamic benchmark demonstrate that the proposed method significantly improves localization robustness, reducing the average ATE RMSE by approximately 66% compared with representative dynamic SLAM baselines. Additional evaluations on a real-world indoor dataset further validate its effectiveness for long-term autonomous perception under dense motion and frequent occlusions. Full article

Industrial visual anomaly detection remains challenging because practical inspection systems must achieve high detection accuracy while operating under highly imbalanced data, diverse defect patterns, limited computational resources, and increasing demands for interpretability. This work aims to develop a lightweight yet effective and explainable anomaly detection framework for industrial images in settings where a limited number of labeled anomalous samples are available. We propose a dual-branch feature-based supervised ensemble method that integrates complementary representations: a PCA branch to capture linear global structure and a scattering branch to model multi-scale textures. A heterogeneous pool of classical learners (SVM, RF, ET, XGBoost, and LightGBM) is trained on each feature branch, and stable probability outputs are obtained via stratified K-fold out-of-fold training, probability calibration, and a quantile-based threshold search. Decision-level fusion is then performed by stacking, where logistic regression, XGBoost, and LightGBM serve as meta-learners over the out-of-fold probabilities of the selected top-K base learners. Experiments on two public benchmarks (MVTec AD and BTAD) show that the proposed method substantially improves the best PCA-based single model, achieving relative F1_score gains of approximately 31% (MVTec AD) and 26% (BTAD), with maximum AUC values of about 0.91 and 0.96, respectively, under comparable inference complexity. Overall, the results demonstrate that combining high-quality handcrafted features with supervised ensemble fusion provides a practical and interpretable alternative/complement to heavier deep models for resource-constrained industrial anomaly detection, and future work will explore more category-adaptive decision strategies to further enhance robustness on challenging classes. Full article

We quantify the transmission and absorption of 75–110 GHz radiation through ex vivo porcine skin. Millimeter waves are currently used in a range of technologies, including communication systems, fog-penetrating radar, and the detection of hidden weapons or drugs. They have also been proposed for use in non-lethal weaponry and, more recently, in targeted cancer therapies. Since pigs are often used as biological models for humans, determining how deeply millimeter waves penetrate a pig’s skin and influence the underlying tissues is essential for understanding their potential effects on humans. This experimental study aims to quantify that penetration and associated energy loss. The results show significant absorption in the skin and fat layer. Attenuation of over three orders of magnitude can be expected in penetration through a layer with a thickness of about 12 mm (−30 dB). The reflectance from the skin is similar at all frequencies. The values range from −10 to −20 dB, which probably depends on the texture of the skin. Therefore, most skin transfer loss is caused by absorption. Full article

Sea fog is a major meteorological hazard that severely disrupts maritime transportation and economic activities in the South China Sea. As China’s next-generation geostationary meteorological satellite, Fengyun-4B (FY-4B) supplies continuous observations that are well suited for sea fog monitoring, yet a satellite-specific recognition method has been lacking. A key obstacle is the radiometric inconsistency between the Advanced Geostationary Radiation Imager (AGRI) sensors on FY-4A and FY-4B, compounded by the cessation of Cloud–Aerosol Lidar with Orthogonal Polarization (CALIOP) observations, which prevents direct transfer of fog labels. To address these challenges and fill this research gap, we propose a machine learning framework that integrates cross-satellite radiometric recalibration and physical mechanism constraints for robust daytime sea fog detection. First, we innovatively apply a radiation recalibration transfer technique based on the radiative transfer model to normalize FY-4A/B radiances and, together with Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) cloud/fog classification products and ERA5 reanalysis, construct a highly consistent joint training set of FY-4A/B for the winter-spring seasons since 2019. Secondly, to enhance the model’s physical performance, we incorporate key physical parameters related to the sea fog formation process (such as temperature inversion, near-surface humidity, and wind field characteristics) as physical constraints, and combine them with multispectral channel sensitivity and the brightness temperature (BT) standard deviation that characterizes texture smoothness, resulting in an optimized 13-dimensional feature matrix. Using this, we optimize the sea fog recognition model parameters of decision tree (DT), random forest (RF), and support vector machine (SVM) with grid search and particle swarm optimization (PSO) algorithms. The validation results show that the RF model outperforms others with the highest overall classification accuracy (0.91) and probability of detection (POD, 0.81) that surpasses prior FY-4A-based work for the South China Sea (POD 0.71–0.76). More importantly, this study demonstrates that the proposed FY-4B framework provides reliable technical support for operational, continuous sea fog monitoring over the South China Sea. Full article

Efficient intra-mode decision for depth maps assumes a pivotal role in augmenting the overall performance of 3D-HEVC. Existing research endeavors predominantly rely on fast mode screening strategies grounded in texture characteristics or machine learning techniques. These strategies, to a certain extent, mitigate the complexity of mode search. Nevertheless, these approaches often fall short of fully leveraging the intrinsic spatio-temporal correlations within depth maps. Moreover, strategies relying on deterministic classifiers exhibit insufficient discrimination reliability in regions featuring edge mutations or intricate structures. To tackle these challenges, this paper presents a two-stage fast intra-mode decision algorithm for depth maps, integrating naive Bayes probability estimation and fuzzy support vector machine (FSVM). Initially, it confines the candidate mode space through spatio-temporal prior modeling. Subsequently, FSVM is employed to enhance the decision accuracy in regions with low confidence. This methodology constructs a joint mode decision framework spanning from probability screening to refined classification. By doing so, it significantly reduces the computational burden while preserving rate-distortion performance, thereby attaining an effective equilibrium between encoding complexity and performance. Experimental findings demonstrate that the proposed algorithm reduces the average encoding time by 52.30% with merely a 0.68% increment in BDBR. Additionally, it showcases stable universality across test sequences of diverse resolutions and scenes. Full article

A reproducible deep learning framework is presented for surface metrology to predict surface texture parameters together with their reported standard uncertainties. Using a multi-instrument dataset spanning tactile and optical systems, we jointly address measurement system type classification and regression of key surface parameters—arithmetic mean roughness (Ra), mean peak-to-valley roughness (Rz), and total roundness deviation (RONt)—alongside their reported standard uncertainties. Uncertainty is modelled via quantile and heteroscedastic regression heads, with post hoc conformal calibration used to obtain calibrated prediction intervals. On a held-out test set, high fidelity was achieved by single-target regressors (coefficients of determination: Ra 0.9824, Rz 0.9847, RONt 0.9918), with two uncertainty targets also well modelled (standard uncertainty of Ra 0.9899, standard uncertainty of Rz 0.9955); the standard uncertainty of RONt remained more difficult to learn (0.4934). The classifier reached 92.85% accuracy, and probability calibration was essentially unchanged after temperature scaling (expected calibration error 0.00504 → 0.00503 on the test split). Negative transfer was observed for naive multi-output trunks, with single-target models performing better. These results provide calibrated predictions suitable for informing instrument selection and acceptance decisions in metrological workflows. Full article

Background: Spatial heterogeneity in tumor tissue has been linked to patient prognosis. To exploit both structural and semantic cues in whole slide images (WSIs), we propose Dual eXplanatory Framework (DuXplore), a dual-branch deep learning framework that integrates tissue architecture and cellular morphology for hepatocellular carcinoma (HCC) prognosis. Method: At the macroscopic level, DuXplore constructs a multi-channel tissue organization probability map (MTOP) to represent the spatial layout of eight tissue categories within the WSIs. At the microscopic level, a feature-guided Fused Structure Tensor (FST) based on tissue composition is employed to extract representative cell morphology patches. Accordingly, MTOP representations are modeled by Macro-Net, while FST-guided patches are modeled by Micro-Net. Each branch produces a 32-dimensional prognostic embedding, which are fused and passed through a multi-layer perceptron with a Cox proportional hazards head to generate patient-level risk predictions. To further elucidate the distinct contributions of the two branches, we conducted model-agnostic interpretability analyses, including occlusion sensitivity mapping (OSM) on MTOP and nuclear morphometrics from CellProfiler on high- versus low-risk tiles. Result: DuXplore achieves promising performance with C-indices of 0.764 on the public Cancer Genome Atlas (TCGA) dataset and 0.713 on the Eastern Hepatobiliary HCC (EHBH) cohort from our clinical center, along with significant patient risk stratification (log-rank p < 0.001). OSM highlighted necrosis and central fibrosis as high-risk and marginal fibrosis as protective; these patterns were corroborated by multivariable Cox using reproducible structural parameters (N-ratio, FIB-center, FIB-edge). Micro-level analysis revealed that higher nuclear staining intensity, increased texture irregularity (GLCM features), and greater morphological heterogeneity characterize high-risk tiles, aligning with pathological understanding. Conclusions: DuXplore advances prognostic modeling by coupling structure-aware micro-sampling with macro architectural encoding, delivering robust, generalizable survival prediction and biologically plausible explanations. While validated on HCC WSIs, broader multi-center, multi-omics studies are warranted to refine sampling scales and enhance clinical translation. Full article

The multi-source fusion localization algorithm demonstrates advantages in achieving continuous localization. However, its reliability and robustness could not be guaranteed and still with some insufficiencies in complex environments, especially for severe occlusions and low-texture scenes in non-cooperative scenarios. In this paper, we propose a GNSS/INS/LiDAR multi-source fusion localization framework. To enhance the algorithm’s performance, availability of different sensors is evaluated quantitatively through GNSS/INS status detection, and LiDAR-data-feature repeatability quality control is implemented at the front end. Both the variability of the standard deviation of differences of features and the standard deviation of real-time features are designed as major considerations and proposed to characterize the repeatability of 3D point clouds of LiDAR. The prior probability of the sensor covariance within the factor graph improves the algorithm’s fusion weight adjustment capability. Finally, a GNSS/INS/LiDAR multi-sensor positioning test platform is developed, and experiments are conducted in sheltered and semi-sheltered environments, such as urban, tunnel, campus, and mountainous environments. The results show that, compared with state-of-the-art methods, the proposed algorithm exhibits superior adaptability, significantly enhancing both reliability and robustness in four different typical real, complex environments, and our algorithm improves the robust running time by 44% in terms of availability in large-scale urban tests. In addition, the algorithm demonstrates superior positioning accuracy compared with those of other methods, achieving a positioning accuracy (RMSE) of 0.18 and 0.21 m in large-scale, long-duration urban and mountainous settings, respectively. Full article

Background: Non-smokers and individuals with minimal smoking history represent a significant proportion of lung cancer cases but are often overlooked in current risk assessment models. Pulmonary nodules are commonly detected incidentally—appearing in approximately 24–31% of all chest CT scans regardless of smoking status. However, most established risk models, such as the Brock model, were developed using cohorts heavily enriched with individuals who have substantial smoking histories. This limits their generalizability to non-smoking and light-smoking populations, highlighting the need for more inclusive and tailored risk prediction strategies. Purpose: We aimed to develop a longitudinal radiomics-based approach for lung cancer risk prediction, integrating time-varying radiomic modeling to enhance early detection in USPSTF-ineligible patients. Methods: Unlike conventional models that rely on a single scan, we conducted a longitudinal analysis of 122 patients who were later diagnosed with lung cancer, with a total of 622 CT scans analyzed. Of these patients, 69% were former smokers, while 30% had never smoked. Quantitative radiomic features were extracted from serial chest CT scans to capture temporal changes in nodule evolution. A time-varying survival model was implemented to dynamically assess lung cancer risk. Additionally, we evaluated the integration of handcrafted radiomic features and the deep learning-based Sybil model to determine the added value of combining local nodule characteristics with global lung assessments. Results: Our radiomic analysis identified specific CT patterns associated with malignant transformation, including increased nodule size, voxel intensity, textural entropy, as indicators of tumor heterogeneity and progression. Integrating radiomics, delta-radiomics, and longitudinal imaging features resulted in the optimal predictive performance during cross-validation (concordance index [C-index]: 0.69), surpassing that of models using demographics alone (C-index: 0.50) and Sybil alone (C-index: 0.54). Compared to the Brock model (67% accuracy, 100% sensitivity, 33% specificity), our composite risk model achieved 78% accuracy, 89% sensitivity, and 67% specificity, demonstrating improved early cancer risk stratification. Kaplan–Meier curves and individualized cancer development probability functions further validated the model’s ability to track dynamic risk progression for individual patients. Visual analysis of longitudinal CT scans confirmed alignment between predicted risk and evolving nodule characteristics. Conclusions: Our study demonstrates that integrating radiomics, sybil, and clinical factors enhances future lung cancer risk prediction in USPSTF-ineligible patients, outperforming existing models and supporting personalized screening and early intervention strategies. Full article