Search Results (10,214)

Visual Internet-of-Things (IoT) cameras and institution-controlled edge gateways increasingly collect artwork images in museums, galleries, and heritage sites. Centralizing these images can expose collection contents, exhibition layouts, and contextual information. This paper proposes FedArtSense, a privacy-preserving federated learning framework for artistic style and medium classification. FedArtSense combines discrepancy-adaptive dual-space prototype alignment, client-level differential privacy for model and prototype releases, and importance-aware shared sparsification compatible with secure aggregation. Experiments on WikiArt, ArtBench-10, and a seven-class Behance Artistic Media subset use emulated non-IID client partitions, persistent acquisition shifts, constrained uplinks, and client dropout. Under the default client-level target $(ϵ,\delta )=(6,{10}^{-5})$, FedArtSense obtains accuracies of $64.2\%$, $81.2\%$, and $75.3\%$, respectively, while reducing cumulative WikiArt uplink traffic to $11.5$ GiB. The results support FedArtSense as a privacy–utility–communication trade-off for gateway-assisted artistic image classification; retrieval, detection, aesthetic prediction, and direct battery-powered camera training are outside the evaluated scope. Full article

Protected horticultural crops are commonly produced at high planting densities and have short production cycles; imbalances in water and fertilizer supply can rapidly affect plant vigor, yield, and quality. Non-destructive diagnostic methods are therefore needed to characterize plant nutritional status under greenhouse conditions. Spectral imaging can simultaneously capture spatial and spectral information associated with pigments, water status, tissue structure, and canopy phenotype. It does not directly detect nutrient ions; rather, it captures physiological and structural responses that may be associated with nutrient status and may also be influenced by water deficit, disease, temperature, salinity, phenology, and genotype. This review focuses on crops grown in soil, substrate, and hydroponic systems under greenhouse conditions. Studies conducted in vertical farms, growth chambers, and open fields are included only as supplementary references for sensor selection, model calibration, and inspection methods. This article synthesizes diagnostic indicators for nitrogen, phosphorus, and potassium, together with their associated physiological responses and spectral characteristics; compares the performance of hyperspectral, multispectral, and machine learning methods at the leaf, plant, and canopy scales; and examines fixed measurement, stop-and-go mobile inspection, continuous motion imaging, and autonomous plant revisitation. Existing studies have established a solid foundation for nutrient content retrieval, deficiency identification, and mobile monitoring. However, several challenges remain inadequately addressed under continuous inspection conditions, including radiometric–geometric joint calibration, plant identity preservation, acquisition of multi-element chemical truth values, model generalization across growth stages and greenhouse types, and long-term performance evaluation. Future work should refine standardized protocols for dynamic data collection and water–fertilizer environmental control, integrate mechanistic constraints with data driven approaches, and incorporate plant re-identification, spatiotemporal registration, uncertainty quantification, and online calibration. These efforts will contribute to constructing a long-term stable and comparable nutritional diagnostic system, thereby advancing the transition of facility vegetable nutritional monitoring from single-time static measurements toward continuous, traceable, and autonomously patrolled systems that may ultimately support precision irrigation and fertilization management after appropriate independent validation. Full article

Multispectral pan-sharpening aims to fuse high-resolution panchromatic and low-resolution multispectral imagery. However, this process introduces spatial artifacts and spectral distortions. Assessing the quality of fused images remains a fundamental challenge due to the absence of full-resolution ground-truth data. This paper provides a comprehensive review of Image Quality Assessment (IQA) frameworks tailored for pan-sharpened imagery. After overviewing major fusion approaches, including Component Substitution (CS), Multi-Resolution Analysis (MRA), Variational Optimization (VO), and Deep Learning (DL), the review analyzes the evaluation techniques used to benchmark them. It then systematically examines the evolution of evaluation protocols, from classical reference-based metrics relying on Wald’s protocol to full-resolution consistency models and recent no-reference (NR) algorithms. The analysis highlights critical methodological bottlenecks within the field, including unrealistic scale-invariance assumptions in consistency-based metrics, dependence on arbitrary parameters, and severe cross-sensor overfitting in deep learning approaches. Furthermore, the review addresses the mismatch between mathematical fidelity, human visual perception, and practical applicability. Finally, it outlines future research directions, focusing on spatial quality mapping and task-driven assessment protocols that validate fusion efficacy based on its impact on automated remote sensing applications. Full article

Nanomaterials are increasingly expected to do more than transport a payload, yet added complexity is useful only when it resolves a rate-limiting diagnostic, transport, release, or monitoring problem. This review develops a function-first framework for precision diagnostics and drug delivery in which formation and processing are linked to nanoscale structure, material properties, demonstrated function, route-specific evidence, and translational value. The scope includes AI-assisted plasmonic and terahertz biosensing; biopolymer nanoparticles and hydrogel depots; barrier-directed nose-to-brain and systemic delivery; graphene and carbon nanotube interfaces; lipid nanoparticles for nucleic acid packaging and endosomal escape; nanoporous, magnetic, and plasmonic carriers; and closed-loop theranostic systems. A platform is treated as genuinely multifunctional only when at least two deliberately engineered functions are experimentally supported and either act on distinct rate-limiting steps or close a sensing–intervention–monitoring loop. This review therefore distinguishes total loading from bioavailable payload, cellular uptake from productive delivery, imaging labels from intact carrier fate, and nominal stimulus responsiveness from controlled release in response to a physiologically realistic trigger. Recent independent studies are used to broaden comparisons across material classes and to separate proof-of-concept performance from translational evidence. Artificial intelligence is considered in three distinct roles—sensor interpretation, formulation/material optimization, and prediction of in vivo behavior—with external validation and, where a model is intended to guide decisions, prospective testing treated as essential. The resulting framework emphasizes biological identity, route-specific safety, carrier-versus-payload tracking, critical quality attributes, manufacturing reproducibility, and a minimum-evidence roadmap from concept to product. Full article

This study addresses the issue of insufficient spatial resolution in remote sensing images for farmland boundary identification in precision agriculture. It proposes a framework that combines Real-ESRGAN, a GAN-based blind super-resolution algorithm, with YOLO, a real-time instance segmentation framework, to improve farmland boundary extraction accuracy from medium-resolution satellite imagery. Using GF-2 imagery of the agricultural area of Nanxiong City, Guangdong Province, a manually annotated farmland boundary dataset was constructed. The experiments were conducted in this single study area (Nanxiong City); the generalization of the proposed framework to other regions, crops, and sensor platforms requires further validation. The super-resolution preprocessing restored a 1 m resolution from 4 m input while enhancing boundary-related high-frequency details and mitigating aliasing-induced field merging. In farmland boundary recognition, the super-resolved 1 m images achieved mAP@0.5 of 0.755 and mAP@0.5:0.95 of 0.628, approaching the resampled 1 m reference (0.823 and 0.733) and clearly outperforming the resampled 4 m baseline (zero accuracy). The reported mAP values are validation-set best-checkpoint figures and therefore represent an optimistic upper bound under the current spatially autocorrelated split. The framework provides a cost-effective solution for large-scale farmland boundary extraction and precision agricultural management. Full article

With the increase in global fishing activities, the transparency of fishery data has drawn increasing attention. Data transparency enables stakeholders to play a greater role in ensuring that fisheries are legal, ethical, and sustainable. Improving the transparency of fishing vessel data can effectively support vessel monitoring and enhance fishery safety. This paper presents a systematic review of satellite remote sensing modalities and datasets currently available for fishing vessel identification and monitoring. Conducted in accordance with the PRISMA 2020 guidelines, this study employs a dual-track search strategy to retrieve, screen, and synthesize academic literature and public datasets from mainstream databases, including the Web of Science Core Collection, IEEE Xplore, and CNKI. First, the existing remote sensing modalities were classified into three major categories based on their imaging principles: synthetic aperture radar (SAR), optical remote sensing, and nighttime light (NTL) remote sensing. In addition, the mainstream satellite data sources and their corresponding parameters were summarized for each category. Second, an in-depth comparative analysis of these remote sensing modalities is conducted from core dimensions such as target detection sensitivity, robustness under complex environments and meteorological conditions, and spatiotemporal resolution. This reveals the performance limitations and significant complementarity of different sensor data in fishing vessel detection. Finally, mainstream remote sensing datasets for fishing vessels (such as xView3-SAR, xView, and VBD) are summarized and evaluated, pointing out the gaps in certain types of datasets. In conclusion, this paper suggests that building a “full spatiotemporal and multi-scale” observation framework based on multi-source heterogeneous data fusion is an important trend for the future development of fishing vessel detection using remote sensing, aiming to provide a reference for relevant researchers. Full article

Real-time LiDAR semantic segmentation for industrial AGVs must distinguish repeated structures and weak glass returns while remaining robust to sensor-dependent intensity and tight edge computing budgets. We introduce DS-RangeNet, a lightweight range image network that processes geometry and material-sensitive intensity in separate streams. The geometry stream uses voxel-PCA descriptors, while the intensity stream uses normalized range, local intensity statistics, boundary strength, and intensity curvature. A lightweight convolutional attention block handles shallow fusion, whereas intensity–geometry cross-attention (IGCA) links deep features by estimating affinity within the guiding stream and routing values from the other stream. Centered kernel alignment (CKA) and normalized cross-covariance reveal weak similarity after separate encoding and progressively stronger alignment during fusion. On the site disjoint UBPC-9 test split, DS-RangeNet reaches 73.2% mIoU with 5.69 M parameters and 37 ms end-to-end latency on Jetson AGX Orin. A nine-fold leave-one-environment-out evaluation obtains 71.0% mIoU. The evaluation further spans SemanticPOSS and SemanticKITTI, five random seeds, 21 corruption conditions across seven families, standard cross-attention and convolution controls, a 60 min Jetson run, and cross-sensor transfer. Full article

Multi-source cross-domain hyperspectral image (HSI) classification is challenged by heterogeneous sensor configurations, scene-dependent distribution shifts, and limited labeled target data, which hinder effective knowledge transfer across multiple scenes. Motivated by progressive feature correction, we propose a three-stage Residual Feature Discrepancy Refinement (RFD) framework for collaborative representation learning across heterogeneous HSI domains. RFD formulates this correction as a deterministic, discrepancy-conditioned residual refinement process. First, domain-specific encoders project four source domains and the target domain, which may have unequal spectral dimensions and label spaces, into a common-dimensional feature space. Adaptive severity and domain weighting uses first- and second-order feature discrepancies to estimate source-specific conditioning coordinates and collaborative contribution weights. A shared discrepancy-conditioned residual refiner then performs multi-step feature refinement to reduce domain-dependent statistical deviations. Finally, an exponential-moving-average historical prototype memory stabilizes target adaptation, followed by cosine 1-nearest-neighbor classification. Across ten randomized runs, RFD achieves mean overall accuracies of 94.65%, 94.87%, and 96.95% on NC12, Salinas, and WHU-Hi-LongKou, respectively, and obtains the highest mean overall accuracy, average accuracy, and $\kappa$ among the evaluated unified-protocol methods. Full article

Image segmentation is a fundamental step in computer vision and a cornerstone of robotic perception, serving as the foundation for interpreting data acquired from vision sensors, enabling robots to analyze complex visual environments, identify and localize objects, and support intelligent decision-making and autonomous control. It plays a critical role in applications such as autonomous navigation, robotic manipulation, medical robotics, agricultural robotics, autonomous vehicles, and human–robot interaction. Image segmentation has evolved from classical methods, which relied on handcrafted rules and mathematical models, to deep learning approaches that learn complex visual patterns directly from data. This evolution reflects advances in algorithms, computational power, and the theoretical foundations of mathematics and data science. Modern deep learning methods rely heavily on large, well-annotated datasets to train sophisticated neural networks. Yet, classical techniques remain valuable in certain scenarios, offering faster, reliable results without extensive computational requirements. Understanding the strengths and limitations of both approaches is key to selecting the right method. This paper surveys image segmentation techniques, comparing them in terms of accuracy, computational cost, and processing speed to guide informed method selection. Full article

Distributed acoustic sensing (DAS) converts fiber cables into dense strain-rate sensor arrays, capturing direct, reflected and guided seismic phases with ultra-fine spatial sampling. However, DAS interrogators suffer far stronger random noise than traditional geophones, limiting its microseismic imaging capacity. This work adopts curvelet-transform denoising to suppress noise. Curvelets partition the frequency–wavenumber plane into multiscale directional sectors; coherent wave energy concentrates in limited angular wedges, while stochastic noise disperses evenly across all transform coefficients, enabling noise-signal separation via wedge-wise thresholding. We test four default threshold schemes on synthetic downhole DAS microseismic data. Parameter tuning proves all methods deliver comparable performance, so we compare their out-of-box reliability for shale reservoir monitoring. Three noise-statistic-based strategies perform stably: median-absolute-deviation (MAD), quiet-window and empirical-cumulative-distribution-Function (ECDF percentile) thresholding. By contrast, the default knee-point algorithm from mainstream DAS toolboxes fails, as its preset threshold falls within noise components and barely removes interference. We propose MAD as a robust default for the tested downhole DAS microseismic setting for it estimates thresholds directly from noisy traces without blank reference windows and offers superior operational stability. Applied to field DAS records from a southwest China shale-gas horizontal monitor well, the MAD curvelet workflow greatly enhances microseismic arrivals with negligible spurious events. Benchmarks against standard 2D Daubechies-4 wavelet and adaptive Goldstein FK filtering verify curvelet denoising as a physically interpretable, efficient tool for DAS wavefields. Full article

Automated concrete-surface classification increasingly employs multimodal sensing, although a wide range of systems assume that all sensors remain continuously available, reliable, and suitable for fusion. This study presents Reliability-Aware Selective Multimodal Fusion (RASMF), an image-first framework in which supplementary acoustic evidence is requested conditionally, assessed for signal-quality anomalies, fused when appropriate, and rejected when necessary. RASMF was evaluated on 4094 class-associated image-acoustic observations using 5 duplicate-aware outer folds and three random seeds under clean, simulated-degradation, and missing-modality conditions. At the nominal 10% acquisition budget, realised acoustic acquisition was 25.67%. Relative to the predefined missing-aware image-first baseline, mean error decreased from 1.9777% to 1.4499%, an absolute reduction of 0.5279 percentage points and a relative reduction of 26.69%, with a two-way bootstrap 95% confidence interval of −1.6220 to −0.0661 percentage points. The mean Brier score decreased from 0.03033 to 0.01688. RASMF produced lower mean error in 12 of 16 simulated-degradation and modality-loss conditions, with 6 condition-specific confidence intervals excluding zero in its favour. Increasing acoustic acquisition progressively reduced mean error and calibration error but increased processing demand; estimated pipeline time was 24.77 ms at the nominal 10% setting compared with 20.60 ms at the nominal 0% setting. A simpler logit stacker achieved a slightly lower mean error of 1.4295%, and the difference from RASMF was not statistically supported. The results therefore support RASMF as an explicit reliability-aware selective decision architecture relative to the designated baseline, without establishing universal predictive superiority over simpler fusion strategies. Full article

Conventional image acquisition requires an electrically powered image sensor to be placed directly behind the camera lens, constraining camera placement. To overcome this issue, we introduce M3-RGB as an incoherent-light fiber imaging system in which a multicore, multimode optical fiber passively relays lens images to a remotely located image sensor. Unlike conventional approaches, M3-RGB is designed to operate directly on incoherent light and requires no electrical power or active components at the sensing interface. Because propagation through the fiber yields spatially scrambled patterns, a neural network is used to reconstruct the original scene by exploiting the spatial locality preserved by the multicore structure. In a controlled optical bench setup, where a liquid crystal display monitor displays road-scene images, we construct a paired dataset of scrambled and ground-truth images and quantitatively evaluate reconstruction performance across different fiber core counts, fiber lengths, and calibration settings, utilizing the peak signal-to-noise ratio and structural similarity index measure as performance metrics. By decoupling imaging electronics from the sensing point, this passive remote image relay approach may expand sensor placement options for potential applications such as all-around perception for mobile robots and autonomous vehicles, surveillance, and inspection in confined spaces. Evaluations in real outdoor environments constitute future work. Full article

Training semantic segmentation models is especially costly in remote sensing, since most problems require a new dataset as targets vary with resolution, sensors, and region. Approaches to reduce this cost are increasingly common, but most add machinery that expands few labeled pixels into a denser training signal using the model’s own predictions, where a confident prediction looks the same whether it is correct or incorrect. The hypothesis here is that these confident errors are the most valuable pixels to label, and that a human examining the image can identify them directly. We propose iSAGE (Iterative Sparse Annotation Guided by Expert), an open-source framework in which the annotator clicks confident errors in the prediction overlay, the clicks train the model under an error-weighted loss, and the updated model surfaces the next errors, with no automatic label expansion at any step. With at most one labeled pixel per class per frame per iteration, iSAGE recovers 96.9% of dense performance on BsB Aerial (74.79% mIoU from 0.040% of the pixels) and matches the dense baseline on ISPRS Vaihingen (76.65% vs. 76.93% from 0.011% of the pixels), surpassing published weakly supervised methods by nearly 4 mIoU points. Four automatic selection strategies run through the same loop plateau 7.3 to 14.4 points below iSAGE, and raising their budgets far higher does not close the gap; in a 35-method comparison, iSAGE is the only iterative human-in-the-loop framework without automatic label generation. Full article

Infrared and visible image fusion combines the thermal cues captured by infrared sensors with the rich structural and texture information provided by visible images. This technique is particularly valuable for security surveillance, nighttime scene perception, and target recognition under challenging environmental conditions. Existing methods generally adopt fixed fusion strategies and neglect dynamic dual-modality changes under low illumination, overexposure and strong light interference, failing to preserve both thermal target saliency and visible structural details in fused images. To address this problem, this paper proposes a Lighting-Aware Spatial–Frequency Fusion Network (LASFNet) for security surveillance. It first estimates modality reliability across low-light, overexposed and infrared-salient regions, incorporating it into the fusion of frequency-domain amplitude and phase. Spatial infrared, visible and frequency-domain compensation features are then jointly fused to generate the output. Experiments on M3FD, MSRS and RoadScene datasets show that LASFNet achieves competitive fusion performance with strong cross-dataset generalization. On M3FD, YOLOv8s with LASFNet-fused inputs achieves 84.825% mAP@0.5 and 57.319% mAP@0.5:0.95, outperforming visible, infrared and YDTR-fused inputs. The proposed method balances target saliency and scene structure, providing more effective visual input for object detection under complex illumination. Full article

Reliable state identification is essential for intelligent flotation control because recovery, concentrate grade, entrainment, and mineral losses are only partially observable online. This systematic review examines field instrumentation, online analyzers, froth imaging, temporal synchronization, machine-vision methods, multimodal soft sensing, and the engineering requirements that determine whether a predictive model can operate as an industrial sensor. Scopus and Web of Science publications from 2021 to June 2026 were screened using a PRISMA-based protocol. The systematic evidence base includes 98 peer-reviewed technical studies published between 2021 and June 2026, and two PRISMA methodological publications are used to ensure the methodology for presenting the review. Additional methodological and contextual sources cited outside the systematic body of evidence are not included in the number of studies reflected in PRISMA. The evidence shows that machine vision is the most mature non-contact sensing approach, supporting bubble-size measurement, froth-velocity estimation, operating-state recognition, grade prediction, and visual monitoring. Current research is shifting from handcrafted descriptors toward convolutional, transformer, self-supervised, graph-based, temporal, and multimodal models. However, predictive accuracy alone does not demonstrate industrial readiness when camera geometry, illumination, contamination, delay compensation, temporal leakage, domain shift, uncertainty, inference latency, and SCADA/PLC integration are not evaluated. A five-dimensional Sensor Readiness Index is proposed to assess metrological validity, temporal integrity, validation rigor, operational robustness, and automation integration. The review defines the principal requirements for reliable industrial deployment of flotation sensing systems. Full article