Search Results (2,083)

Biomass burning processes affect many semi-rural areas in the Mediterranean, but there is a lack of long-term datasets focusing on their classification, obtained by monitoring carbonaceous particle concentrations and optical properties variations. To address this issue, a campaign to measure equivalent black carbon (eBC) and particle number size distributions (0.3–10 μm) was carried out from August 2019 to November 2020 at a coastal semi-rural site in the Basilicata region of Southern Italy. Long-term datasets were useful for aerosol characterization, helping to clearly identify traffic as a constant eBC source. For a shorter period, PM_2.5 mass concentrations were also measured, allowing the estimation of elemental and organic carbon (EC and OC), and chemical and SEM (scanning electron microscope) analysis of aerosols collected on filters. This multi-instrumental approach enabled the discrimination among different biomass burning (BB) processes, and the analysis of three case studies related to domestic heating, regional smoke plume transport, and a local smoldering process. The AAE (Ångström absorption exponent) daily pattern was characterized as having a peak late in the morning and mean hourly values that were always higher than 1.3. Full article

Forests provide habitat for diverse species and play a key role in mitigating climate change. Remote sensing enables efficient monitoring of many forest attributes across vast areas, thus supporting effective and efficient management strategies. This study aimed to identify an effective combination of remote sensing sensors for estimating biophysical variables in Mediterranean and temperate forests that can be easily translated into an operational context. Aboveground biomass (AGB), canopy height (CH), and forest canopy cover (FCC) were estimated using a combination of optical (Sentinel-2, Landsat) and radar sensors (Sentinel-1 and TerraSAR-X/TanDEM-X), along with records of past forest disturbances and topography-related variables. As a reference, lidar-derived AGB, CH, and FCC were used. Model performance was assessed not only with standard approaches such as out-of-bag sampling but also with completely independent lidar-derived reference datasets, thus enabling evaluation of the model’s temporal inference capacity. In Mediterranean forests, models based on optical imagery outperformed the radar-enhanced models when estimating FCC and CH, with elevation and spectral indices being key predictors of forest structure. In contrast, in denser temperate forests, radar data (especially X-band relative heights) were crucial for estimating CH and AGB. Incorporating past disturbance data further improved model accuracy in these denser ecosystems. Overall, this study underscores the value of integrating multi-source remote sensing data while highlighting the limitations of temporal extrapolation. The presented methodology can be adapted to enhance forest variable estimation across many forest ecosystems. Full article

Understanding remote sensing imagery is vital for object observation and planning. However, the acquisition of optical images is inevitably affected by shadows and occlusions, resulting in local discrepancies in object representation. To address these challenges, this paper proposes AFNE-Net, a general network architecture for remote sensing image segmentation. First, the model introduces an attention-based feature fusion module. Through the use of weighted fusion of multi-resolution features, this effectively expands the receptive field and enhances semantic associations between categories. Subsequently, a feature enhancement module based on the consistency of neighborhood semantic representation is introduced. This aims to improve the feature representation and reduce segmentation errors caused by local perturbations. Finally, evaluations are conducted on the ISPRS Potsdam, UAVid, and LoveDA datasets to verify the effectiveness of the proposed model. Full article

The updated MODIS Collection 6.1 (C6.1) Dark Target (DT) aerosol optical depth (AOD) is extensively utilized in aerosol-climate studies in China. Nevertheless, the long-term accuracy of this data remains under-evaluated, especially for the forested areas. This study was undertaken to substantiate the accuracy of MODIS Terra (MOD04) and Aqua (MYD04) at 3 km resolution AOD retrievals at six forested sites in China from 2004 to 2022. The results revealed that MODIS C6.1 DT MOD04 and MYD04 datasets display good correlation (R = 0.75), low RMSE (0.20, 0.18), but significant underestimation, with only 53.57% (Terra) and 52.20% (Aqua) of retrievals within expected error (EE). Both the Terra and Aqua struggled in complex terrain (Gongga Mt.) and high aerosol loads (AOD > 1). In northern sites, MOD04 outperformed MYD04 with better correlation and a relatively high number of retrievals percentage within EE. In contrast, MYD04 outperformed MOD04 in central region with better R (0.69 vs. 0.62), and high percentage within EE (68.70% vs. 63.62%). Since both products perform well in the central region, MODIS C6.1 DT products are recommended for this region. In southern sites, MOD04 product performs relatively better than MYD04 with a marginally higher percentage within EE. However, MYD04 shows better correlation, although a higher number of retrievals fall below EE compared to MOD04. Seasonal biases, driven by snow and dust, were pronounced at northern sites during winter and spring. Southern sites faced issues during biomass burning seasons and complex terrain further degraded accuracy. MOD04 demonstrated a marginally superior performance compared to MYD04, yet both failed to achieve the global validation benchmark (66% within). The proposed results highlight critical limitations of current aerosol retrieval algorithms in forest and mountainous landscapes, necessitating methodological refinements to improve satellite-based derived AOD accuracy in ecological sensitive areas. Full article

Atmospheric optical turbulence intensity, quantified by the Fried parameter ($r_0$), serves as a critical metric for astronomical site testing and selection. The Solar Differential Image Motion Monitor (SDIMM), adapted from the methodology of the Differential Image Motion Monitor (DIMM), is a dedicated instrument for daytime $r_0$ measurements. Conventional SDIMM systems typically employ telescopes with apertures ≥30 cm and reconstruct wavefront segmentation at the exit pupil, resulting in bulky configurations that impede portability. To address the demands of multi-site surveys, we developed a low-cost, portable SDIMM system that directly adopts the DIMM optical path without backend wavefront reconstruction, instead deriving $r_0$ through image processing algorithms. Integrated with a 20 cm aperture telescope, the system achieves a total weight of <20 kg, significantly enhancing field portability. This paper details the instrument’s architecture, measurement principles, and comparative tests with a traditional SDIMM, demonstrating strong consistency between the two systems. Field measurements conducted at the Ali Observatory (elevation: 5050 m) from 16 August to 10 December 2024 yielded the site’s first continuous daytime $r_0$ dataset, with values ranging from 1.5 cm to 12 cm and a mean of 4.09 cm. The compact SDIMM provides a cost-effective and easily deployable solution for comparative daytime $r_0$ assessments across multiple candidate astronomical sites. Full article

Glaucoma is a leading cause of irreversible blindness worldwide, yet early detection can prevent vision loss. This paper proposes a novel deep learning approach that combines two ophthalmic imaging modalities, fundus photographs and optical coherence tomography scans, as paired images from the same eye of each patient for automated glaucoma detection. We develop separate convolutional neural network models for fundus and optical coherence tomography images and a fusion model that integrates features from both modalities for each eye. The models are trained and evaluated on a private clinical dataset (Bangladesh Eye Hospital and Institute Ltd.) consisting of 216 healthy eye images (108 fundus, 108 optical coherence tomography) from 108 patients and 200 glaucomatous eye images (100 fundus, 100 optical coherence tomography) from 100 patients. Our methodology includes image preprocessing pipelines for each modality, custom convolutional neural network/ResNet-based architectures for single-modality analysis, and a two-branch fusion network combining fundus and optical coherence tomography feature representations. We report the performance (accuracy, sensitivity, specificity, and area under curve) of the fundus-only, optical coherence tomography-only, and fusion models. In addition to a fixed test set evaluation, we perform five-fold cross-validation, confirming the robustness and consistency of the fusion model across multiple data partitions. On our fixed test set, the fundus-only model achieves 86% accuracy (AUC 0.89) and the optical coherence tomography-only model, 84% accuracy (AUC 0.87). Our fused model reaches 92% accuracy (AUC 0.95), an absolute improvement of 6 percentage points and 8 percentage points over the fundus and OCT baselines, respectively. McNemar’s test on pooled five-fold validation predictions (b = 3, c = 18) yields ${\chi }^2=10.7$ (p = 0.001), and on optical coherence tomography-only vs. fused (b_o = 5, c_o = 20) ${\chi }_o^2=9.0$ (p = 0.003), confirming that the fusion gains are significant. Five-fold cross-validation further confirms these improvements (mean AUC $0.952\pm 0.011$. We also compare our results with the existing literature and discuss the clinical significance, limitations, and future work. To the best of our knowledge, this is the first time a novel deep learning model has been used on a fusion of paired fundus and optical coherence tomography images of the same patient for the detection of glaucoma. Full article

Glaucoma is an irreversible neurodegenerative disease that affects the optic nerve, leading to partial or complete vision loss. Early and accurate detection is crucial to prevent vision impairment, which necessitates the development of highly precise diagnostic tools. Deep learning (DL) has emerged as a promising approach for glaucoma diagnosis, where the model is trained on datasets of fundus images. To improve the detection accuracy, we propose a hybrid model for glaucoma detection that combines multiple DL models with two fine-tuning strategies and uses a majority voting scheme to determine the final prediction. In experiments, the hybrid model achieved a detection accuracy of 96.55%, a sensitivity of 98.84%, and a specificity of 94.32%. Integrating datasets was found to improve the performance compared to using them separately even with transfer learning. When compared to individual DL models, the hybrid model achieved a 20.69% improvement in accuracy compared to the best model when applied to a single dataset, a 13.22% improvement when applied with transfer learning across all datasets, and a 1.72% improvement when applied to all datasets. These results demonstrate the potential of hybrid DL models to detect glaucoma more accurately than individual models. Full article

Wide-angle images often suffer from severe radial distortion, compromising geometric accuracy and challenging image correction and real-time stitching, especially in resource-constrained embedded environments. To address this, this study proposes a wide-angle image correction and stitching framework based on a Swin Transformer, optimized for lightweight deployment on edge devices. The model integrates multi-scale feature extraction, Thin Plate Spline (TPS) control point prediction, and optical flow-guided constraints, balancing correction accuracy and computational efficiency. Experiments on synthetic and real-world datasets show that the method outperforms mainstream algorithms, with PSNR gains of 3.28 dB and 2.18 dB on wide-angle and fisheye images, respectively, while maintaining real-time performance. To validate practical applicability, the model is deployed on a Jetson TX2 NX device, and a real-time dual-camera stitching system is built using C++ and DeepStream. The system achieves 15 FPS at 1400 × 1400 resolution, with a correction latency of 56 ms and stitching latency of 15 ms, demonstrating efficient hardware utilization and stable performance. This study presents a deployable, scalable, and edge-compatible solution for wide-angle image correction and real-time stitching, offering practical value for applications such as smart surveillance, autonomous driving, and industrial inspection. Full article

Milk powder is a key nutritional alternative to breastfeeding, but its thermal properties, which vary with temperature, can affect its quality and shelf life. However, there is little information about the physical and chemical properties of powdered milk in several countries. This dataset contains the result of an analysis of the aflatoxins, macroelement and microelement concentrations, oxidative stability, and fatty acid profile of infant formula milk powder. The concentrations of Al, As, Ba, Cd, Co, Cr, Cu, Fe, Mg, Mn, Mo, Ni, Pb, Se, V, and Zn in digested powdered milk samples were quantified through inductively coupled plasma optical emission spectrometry (ICP OES). Thermogravimetry (TG) and differential scanning calorimetry (DSC) were used to estimate the oxidative stability of infant formula milk powder, while the methyl esters of the fatty acids were analyzed by gas chromatography. Most milk samples showed significant concentrations of As (0.5583–1.3101 mg/kg) and Pb (0.2588–0.0847 mg/kg). The concentrations of aflatoxins G2 and B2 are below the limits established by Brazilian regulatory agencies. The thermal degradation behavior of the samples is not the same due to their fatty acid compositions. The data presented may be useful in identifying compounds present in infant milk powder used as a substitute for breast milk and understanding the mechanism of thermal stability and degradation, ensuring food safety for those who consume them. Full article

Accurate identification of non-food crops underpins food security by clarifying land-use dynamics, promoting sustainable farming, and guiding efficient resource allocation. Proper identification and management maintain the balance between food and non-food cropping, a prerequisite for ecological sustainability and a healthy agricultural economy. Distinguishing large-scale non-food crops—such as oilseed rape, tea, and cotton—remains challenging because their canopy reflectance spectra are similar. This study proposes a novel phenology-aware Vision Transformer Model (PVM) for accurate, large-scale non-food crop classification. PVM incorporates a Phenology-Aware Module (PAM) that fuses multi-source remote-sensing time series with crop-growth calendars. The study area is Hunan Province, China. We collected Sentinel-1 SAR and Sentinel-2 optical imagery (2021–2022) and corresponding ground-truth samples of non-food crops. The model uses a Vision Transformer (ViT) backbone integrated with PAM. PAM dynamically adjusts temporal attention using encoded phenological cues, enabling the network to focus on key growth stages. A parallel Multi-Task Attention Fusion (MTAF) mechanism adaptively combines Sentinel-1 and Sentinel-2 time-series data. The fusion exploits sensor complementarity and mitigates cloud-induced data gaps. The fused spatiotemporal features feed a Transformer-based decoder that performs multi-class semantic segmentation. On the Hunan dataset, PVM achieved an F1-score of 74.84% and an IoU of 61.38%, outperforming MTAF-TST and 2D-U-Net + CLSTM baselines. Cross-regional validation on the Canadian Cropland Dataset confirmed the model’s generalizability, with an F1-score of 71.93% and an IoU of 55.94%. Ablation experiments verified the contribution of each module. Adding PAM raised IoU by 8.3%, whereas including MTAF improved recall by 8.91%. Overall, PVM effectively integrates phenological knowledge with multi-source imagery, delivering accurate and scalable non-food crop classification. Full article

Advanced Synthetic Aperture Radar (SAR) has become an essential modality in remote sensing, offering all-weather capabilities and sensitivity to vegetation biophysical parameters and surface conditions, while effectively complementing optical sensor data. This study evaluates the impact of precipitation on the Normalized Polarimetric Radar Vegetation Index (NPRVI) using dual-polarization Sentinel-1 C-band SAR data from agricultural fields at the Beltsville Agricultural Research Center (BARC). Field-measured precipitation and Global Precipitation Measurement (GPM) precipitation datasets were temporally aligned with Sentinel-1 acquisition times to assess the sensitivity of radar signals to precipitation events. NPRVI exhibited a strong sensitivity to precipitation, particularly within the 1 to 7 h prior to the satellite overpass, even for small amounts of precipitation. A quality assessment (QA) framework was developed to flag and correct precipitation-affected radar observations through interpolation. The adjusted NPRVI values, based on the QA framework using precipitation within a 6 h window, showed strong agreement between field- and GPM-derived data, with an RMSE of 0.09 and a relative RMSE of 19.8%, demonstrating that GPM data can serve as a viable alternative for quality adjustment despite its coarse spatial resolution. The adjusted NPRVI for both soybean and corn fields significantly improved the temporal consistency of the time series and closely followed NDVI trends, while also capturing crop-specific seasonal variations, especially during periods of NDVI saturation or limited variability. These findings underscore the value of the proposed radar-based QA framework in enhancing the interpretability of vegetation dynamics. NPRVI, when adjusted for precipitation effects, can serve as a reliable and complementary tool to optical vegetation indices in agricultural and environmental monitoring. Full article

Defect detection in mass production lines often involves small and imbalanced datasets, necessitating the use of few-shot learning methods. Traditional deep learning-based approaches typically rely on large datasets, limiting their applicability in real-world scenarios. This study explores few-shot learning models for detecting product defects using limited data, enhancing model generalization and stability. Unlike previous deep learning models that require extensive datasets, our approach effectively performs defect detection with minimal data. We propose a Siamese network that integrates Residual blocks, Squeeze and Excitation blocks, and Convolution Block Attention Modules (ResNet-SE-CBAM Siamese network) for feature extraction, optimized through triplet loss for embedding learning. The ResNet-SE-CBAM Siamese network incorporates two primary features: attention mechanisms and metric learning. The recently developed attention mechanisms enhance the convolutional neural network operations and significantly improve feature extraction performance. Meanwhile, metric learning allows for the addition or removal of feature classes without the need to retrain the model, improving its applicability in industrial production lines with limited defect samples. To further improve training efficiency with imbalanced datasets, we introduce a sample selection method based on the Structural Similarity Index Measure (SSIM). Additionally, a high defect rate training strategy is utilized to reduce the False Negative Rate (FNR) and ensure no missed defect detections. At the classification stage, a K-Nearest Neighbor (KNN) classifier is employed to mitigate overfitting risks and enhance stability in few-shot conditions. The experimental results demonstrate that with a good-to-defect ratio of 20:40, the proposed system achieves a classification accuracy of 94% and an FNR of 2%. Furthermore, when the number of defective samples increases to 80, the system achieves zero false negatives (FNR = 0%). The proposed metric learning approach outperforms traditional deep learning models, such as parametric-based YOLO series models in defect detection, achieving higher accuracy and lower miss rates, highlighting its potential for high-reliability industrial deployment. Full article

Traditionally, Helicobacter pylori (HP) gastritis has been diagnosed by pathologists through the examination of gastric biopsies using optical microscopy with standard hematoxylin and eosin (H&E) staining. However, with the adoption of digital pathology, the identification of HP faces certain limitations, particularly due to insufficient resolution in some scanned images. Moreover, interobserver variability has been well documented in the traditional diagnostic approach, which may further complicate consistent interpretation. In this context, deep convolutional neural network (DCNN) models are showing promising results in the automated detection of this infection in whole-slide images (WSIs). The aim of the present article is to detect the presence of HP infection from our own institutional dataset of histopathological gastric biopsy samples using different pretrained and recognized DCNN and AutoML approaches. The dataset comprises 100 H&E-stained WSIs of gastric biopsies. HP infection was confirmed previously using immunohistochemical confirmation. A total of 45,795 patches were selected for model development. InceptionV3, Resnet50, and VGG16 achieved AUC (area under the curve) values of 1. However, InceptionV3 showed superior metrics such as accuracy (97%), recall (100%), F1 score (97%), and MCC (93%). BoostedNet and AutoKeras achieved accuracy, precision, recall, specificity, and F1 scores less than 85%. The InceptionV3 model was used for external validation, and the predictions across all patches yielded a global accuracy of 78%. In conclusion, DCNN models showed stronger potential for diagnosing HP in gastric biopsies compared with the auto ML approach. However, due to variability across pathology applications, no single model is universally optimal. A problem-specific approach is essential. With growing WSI adoption, DL can improve diagnostic accuracy, reduce variability, and streamline pathology workflows using automation. Full article

This paper presents FWStab, a specialized video stabilization dataset tailored for flapping-wing platforms. The dataset encompasses five typical flight scenarios, featuring 48 video clips with intense dynamic jitter. The corresponding Inertial Measurement Unit (IMU) sensor data are synchronously collected, which jointly provide reliable support for multimodal modeling. Based on this, to address the issue of poor image acquisition quality due to severe vibrations in aerial vehicles, this paper proposes a multi-modal signal fusion video stabilization framework. This framework effectively integrates image features and inertial sensor features to predict smooth and stable camera poses. During the video stabilization process, the true camera motion originally estimated based on sensors is warped to the smooth trajectory predicted by the network, thereby optimizing the inter-frame stability. This approach maintains the global rigidity of scene motion, avoids visual artifacts caused by traditional dense optical flow-based spatiotemporal warping, and rectifies rolling shutter-induced distortions. Furthermore, the network is trained in an unsupervised manner by leveraging a joint loss function that integrates camera pose smoothness and optical flow residuals. When coupled with a multi-stage training strategy, this framework demonstrates remarkable stabilization adaptability across a wide range of scenarios. The entire framework employs Long Short-Term Memory (LSTM) to model the temporal characteristics of camera trajectories, enabling high-precision prediction of smooth trajectories. Full article

Deep learning (DL) has shown great capability in remote sensing and automatic target recognition (ATR). However, huge computational costs and power consumption are challenging the development of current DL methods. Optical neural networks have recently been proposed to provide a new mode to replace artificial neural networks. Here, we develop a residual optronic convolutional neural network (res-OPCNN) for synthetic aperture radar (SAR) recognition tasks. We implement almost all computational operations in optics and significantly decrease the network computational costs. Compared with digital DL methods, res-OPCNN offers ultra-fast speed, low computation complexity, and low power consumption. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset demonstrate the lightweight nature of the optronic method and its feasibility for SAR target recognition. Full article