Search Results (158)

The scarcity of labeled hyperspectral video samples has motivated existing methods to leverage RGB-pretrained networks; however, many existing methods of hyperspectral object tracking (HOT) select only three representative spectral bands from hyperspectral images, leading to spectral information loss and weakened target discrimination. To address this issue, we propose the Band and Context Refinement Network (BCR-Net) for HOT. Firstly, we design a band importance learning module to partition hyperspectral images into multiple false-color images for pre-trained backbone network. Specifically, each hyperspectral band is expressed as a non-negative linear combination of other bands to form a correlation matrix. This correlation matrix is used to guide an importance ranking of the bands, enabling the grouping of bands into false-color images that supply informative spectral features for the multi-branch tracking framework. Furthermore, to exploit spectral–spatial relationships and contextual information, we design a Contextual Feature Refinement Module, which integrates multi-scale fusion and context-aware optimization to improve feature discrimination. Finally, to adaptively fuse multi-branch features according to band importance, we employ a correlation matrix-guided fusion strategy. Extensive experiments on two public hyperspectral video datasets show that BCR-Net achieves competitive performance compared with existing classical tracking methods. Full article

Background/Objectives: Diabetic retinopathy (DR) segmentation faces critical challenges from domain shift and false positives caused by heterogeneous retinal backgrounds. Recent transformer-based studies have shown that existing approaches do not comprehensively integrate the anatomical context, particularly training datasets combining blood vessels with DR lesions. Methods: These limitations were addressed by deploying a DeepLabV3+ framework enhanced with more comprehensive anatomical contexts, rather than more complex architectures. The approach produced the first training dataset that systematically integrates DR lesions with complete retinal anatomical structures (optic disc, fovea, blood vessels, retinal boundaries) as contextual background classes. An innovative illumination-based data augmentation simulated diverse camera characteristics using color constancy principles. Two-stage training (cross-entropy and Tversky loss) managed class imbalance effectively. Results: An extensive evaluation of the IDRiD, DDR, and TJDR datasets demonstrated significant improvements. The model achieved competitive performances (AUC-PR: 0.7715, IoU: 0.6651, F1: 0.7930) compared with state-of-the-art methods, including transformer approaches, while showing promising generalization on some unseen datasets, though performance varied across different domains. False-positive returns were reduced through anatomical context awareness. Conclusions: The framework demonstrates that comprehensive anatomical context integration is more critical than architectural complexity for DR segmentation. By combining systematic anatomical annotation with effective data augmentation, conventional network performances can be improved while maintaining computational efficiency and clinical interpretability, establishing a new paradigm for medical image segmentation. Full article

This paper presents a novel hybrid and hierarchical architecture of a Convolutional Neural Network (CNN), based on MobileNetV2 and Support Vector Machines (SVM) for the classification of crop diseases (SVMobileNetV2). The system feeds from multispectral images captured by Unmanned Aerial Vehicles (UAVs) alongside data from IoT nodes. The primary objective is to improve classification performance in terms of both accuracy and precision. This is achieved by integrating contemporary Deep Learning techniques, specifically different CNN models, a prevalent type of artificial neural network composed of multiple interconnected layers, tailored for the analysis of agricultural imagery. The initial layers are responsible for identifying basic visual features such as edges and contours, while deeper layers progressively extract more abstract and complex patterns, enabling the recognition of intricate shapes. In this study, different datasets of tropical crop images, in this case banana crops, were constructed to evaluate the performance and accuracy of CNNs in detecting diseases in the crops, supported by transfer learning. For this, multispectral images are used to create false-color images to discriminate disease through spectra related to the blue, green and red colors in addition to red edge and near-infrared. Moreover, we used IoT nodes to include environmental data related to the temperature and humidity of the environment and the soil. Machine Learning models were evaluated and fine-tuned using standard evaluation metrics. For classification, we used fundamental metrics such as accuracy, precision, and the confusion matrix; in this study was obtained a performance of up to 86.5% using current deep learning models and up to 98.5% accuracy using the proposed hybrid and hierarchical architecture (SVMobileNetV2). This represents a new paradigm to significantly improve classification using the proposed hybrid CNN-SVM architecture and UAV-based multispectral images. Full article

This paper focuses on the study of the famous royal purple dye. It aims to present a holistic approach by researching historical evidence, both for its use and its production, to highlight the importance of the dye within the Greek area. As a substantial part of information concerning the dyeing procedure of purple dye has been lost during the ages, it is crucial to establish points of documentation and identification. The latter can be achieved through chemical analysis, but as this dye is found on precious’s cultural heritage items, which cannot always be sampled, a non-destructive approach should be considered as more appropriate. At first, the history of the dye purple is presented within the Greek area. Then, samples of purple dye are created based on traditional recipes from the Greek area, in order to compose a profile with the characteristics of purple using non-destructive and imaging techniques, thus emphasizing the importance of applying these techniques for the study of dyes on textiles. The results of the experiments show differences in behavior between the pure gland and the dyed samples, as well as the intensity of the color depending on the dyeing procedure. Full article

The Arctic, characterized by extensive ice and snow cover with persistent low solar elevation angles and prolonged polar nights, poses significant challenges for conventional spectral threshold methods in cloud detection and cloud-top thermodynamic phase classification. The study addressed these limitations by combining active and passive remote sensing and developing a machine learning framework for cloud detection and cloud-top thermodynamic phase classification. Utilizing the CALIOP (Cloud-Aerosol Lidar with Orthogonal Polarization) cloud product from 2021 as the truth reference, the model was trained with spatiotemporally collocated datasets from FY3D/MERSI-II (Medium Resolution Spectral Imager-II) and CALIOP. The AdaBoost (Adaptive Boosting) machine learning algorithm was employed to construct the model, with considerations for six distinct Arctic surface types to enhance its performance. The accuracy test results showed that the cloud detection model achieved an accuracy of 0.92, and the cloud recognition model achieved an accuracy of 0.93. The inversion performance of the final model was then rigorously evaluated using a completely independent dataset collected in July 2022. Our findings demonstrated that our model results align well with results from CALIOP, and the detection and identification outcomes across various surface scenarios show high consistency with the actual situations displayed in false-color images. Full article

Modern inspection mobile robots can carry multiple sensors that can provide opportunities to take advantage of the fusion of information obtained from different sensors. In real-world condition monitoring, harsh environmental conditions can significantly affect the sensor’s accuracy. To address this issue in this paper, we introduced a fusion approach around information gaps to handle the portion of false information that can be captured by the employed sensors. To test our idea, we looked at various types of data, such as sounds, color images, and infrared images taken by a mobile robot inspecting a mining site to check the condition of the belt conveyor idlers. The RGB images are used to classify the rotating idlers as stuck ones (late-stage faults); on the other hand, the acoustic signals are employed to identify early-stage faults. In this work, the cyclostationary analysis approach is employed to process the captured acoustic data to visualize the bearing fault signature in the form of Cyclic Spectral Coherence. Since convolutional neural networks (CNNs) and their transfer learning (TL) forms are popular approaches for performing classification tasks, a comparison study of eight CNN-TL models was conducted to find the best models to classify different fault signatures in captured RGB images and acquired Cyclic Spectral Coherence. Finally, to combine the collected information, we suggest a method called dynamic weighted majority voting, where each model’s importance is regularly adjusted for each sample based on the surface temperature of the idler taken from IR images. We demonstrate that our method of combining information from multiple classifiers can work better than using just one sensor for monitoring conditions in real-world situations. Full article

The Koldar Massif in southeastern Kazakhstan is a geologically complex area with potential for porphyry copper and rare-metal mineralization. This study applies a multi-scale remote sensing approach to delineate hydrothermal alteration zones using medium-resolution ASTER imagery and very high-resolution WorldView-3 data. Image processing techniques—including false color composites (FCCs), band ratios (BRs), and the Spectral Angle Mapper (SAM)—were employed across the VNIR and SWIR bands to detect alteration minerals such as kaolinite, illite, montmorillonite, chlorite, epidote, calcite, quartz, and muscovite. These minerals correspond to argillic, propylitic, and phyllic alteration zones. While ASTER supported regional-scale mapping, WorldView-3 enabled detailed analysis at the Aidarly deposit. Validation was performed using copper occurrences, lithogeochemical anomaly contours, and ore body boundaries. The results show a strong spatial correlation between the mapped alteration zones and known mineralization patterns. Importantly, this study reports the identification of a previously undocumented hydrothermal zone north of the Aidarly deposit, detected using WorldView-3 data. This zone exhibits concentric phyllic and argillic alterations, similar to those at Aidarly, and may represent an extension of the mineralized system. Unlike earlier studies on the Aktogay deposit based on ASTER and Landsat-8, this work focuses on the Aidarly deposit and introduces higher-resolution analysis and SAM-based classification, offering improved spatial accuracy and target delineation. The proposed methodology provides a reproducible and scalable workflow for early-stage mineral exploration in underexplored regions, especially where field access is limited. These results highlight the value of high-resolution remote sensing in detecting concealed porphyry copper systems in structurally complex terrains. Full article

Aiming at the problem of harrowing target feature extraction for one-dimensional radar signals in the strong sea clutter background, this paper proposes a weak target detection method based on the combination of multi-modal time-frequency map fusion and deep learning in the sea clutter background. The one-dimensional signal is converted into three gray-scale maps with complementary characteristics by three signal processing methods: normalized continuous wavelet transform, Normalized Smooth Pseudo Wigner-Ville Distribution, and recurrence plot; the resulting two-dimensional grayscale maps are adaptively mapped to the R, G, and B channels through an adaptive weighting matrix for feature fusion, ultimately generating a fused color image. Subsequently, an improved multi-modal EfficientNetV2s classification framework was constructed, wherein the decision threshold of the Softmax layer was optimized to achieve controllable false alarm rates for weak signal detection. Experiments are carried out on the IPIX dataset and the China Yantai dataset, and the proposed method achieves certain improvement in detection performance compared with existing detection methods. Full article

Imaging techniques have revolutionized cultural heritage analysis, particularly for objects that cannot be sampled. This study investigated the utilization of spectral imaging for the identification of pigments in artifacts from the Arxiu Valencià del Disseny, in conjunction with other portable spectroscopy techniques such as XRF, Raman, FT-NIR, and FT-MIR. Four early 1930s watercolors were examined using point-wise elemental and molecular spectroscopic data for pigment classification. Initially, the data cubes obtained with the spectral camera were processed using various methods. The spectral behavior was analyzed pixel-point, and the reflectance curves were qualitatively compared with a set of standards. Subsequently, a computational approach was applied to the data cube to produce RGB, false-color infrared (IRFC), and principal component (PC) images. Algorithms, such as the Vector Angle (VA) mapper, were also employed to map the pigment spectra. Consequently, 19th-century pigments such as Prussian blue, chrome yellow, and alizarin red were distinguished according to their composition, combining the spatial and spectral dimensions of the data. Elemental analysis and infrared spectroscopy supported these findings. In this context, the use of reflectance imaging spectroscopy (RIS), despite its technical limitations, emerged as an essential tool for the documentation and conservation of design heritage. Full article

In recent years, heavy metal contamination in agricultural products has become a growing concern in the field of food safety. Copper (Cu) stress in crops not only leads to significant reductions in both yield and quality but also poses potential health risks to humans. This study proposes an efficient and precise non-destructive detection method for Cu stress in oilseed rape, which is based on hyperspectral false-color image construction using principal component analysis (PCA). By comprehensively capturing the spectral representation of oilseed rape plants, both the one-dimensional (1D) spectral sequence and spatial image data were utilized for multi-class classification. The classification performance of models based on 1D spectral sequences was compared from two perspectives: first, between machine learning and deep learning methods (best accuracy: 93.49% vs. 96.69%); and second, between shallow and deep convolutional neural networks (CNNs) (best accuracy: 95.15% vs. 96.69%). For spatial image data, deep residual networks were employed to evaluate the effectiveness of visible-light and false-color images. The RegNet architecture was chosen for its flexible parameterization and proven effectiveness in extracting multi-scale features from hyperspectral false-color images. This flexibility enabled RegNetX-6.4GF to achieve optimal performance on the dataset constructed from three types of false-color images, with the model reaching a Macro-Precision, Macro-Recall, Macro-F₁, and Accuracy of 98.17%, 98.15%, 98.15%, and 98.15%, respectively. Furthermore, Grad-CAM visualizations revealed that latent physiological changes in plants under heavy metal stress guided feature learning within CNNs, and demonstrated the effectiveness of false-color image construction in extracting discriminative features. Overall, the proposed technique can be integrated into portable hyperspectral imaging devices, enabling real-time and non-destructive detection of heavy metal stress in modern agricultural practices. Full article

Radar echo extrapolation is a critical forecasting tool in the field of meteorology, playing an especially vital role in nowcasting and weather modification operations. In recent years, spatiotemporal sequence prediction models based on deep learning have garnered significant attention and achieved notable progress in radar echo extrapolation. However, most of these extrapolation network architectures are built upon convolutional neural networks, using radar echo images as input. Typically, radar echo intensity values ranging from −5 to 70 dBZ with a resolution of 5 dBZ are converted into 0–255 grayscale images from pseudo-color representations, which inevitably results in the loss of important echo details. Furthermore, as the extrapolation time increases, the smoothing effect inherent to convolution operations leads to increasingly blurred predictions. To address the algorithmic limitations of deep learning-based echo extrapolation models, this study introduces three major improvements: (1) A Deep Convolutional Generative Adversarial Network (DCGAN) is integrated into the ConvLSTM-based extrapolation model to construct a DCGAN-enhanced architecture, significantly improving the quality of radar echo extrapolation; (2) Considering that the evolution of radar echoes is closely related to the surrounding meteorological environment, the study incorporates specific physical variable products from the initial zero-hour field of RMAPS-NOW (the Rapid-update Multiscale Analysis and Prediction System—NOWcasting subsystem), developed by the Institute of Urban Meteorology, China. These variables are encoded jointly with high-resolution (0.5 dB) radar mosaic data to form multiple radar cells as input. A multi-channel radar echo extrapolation network architecture (MR-DCGAN) is then designed based on the DCGAN framework; (3) Since radar echo decay becomes more prominent over longer extrapolation horizons, this study departs from previous approaches that use a single model to extrapolate 120 min. Instead, it customizes time-specific loss functions for spatiotemporal attenuation correction and independently trains 20 separate models to achieve the full 120 min extrapolation. The dataset consists of radar composite reflectivity mosaics over North China within the range of 116.10–117.50°E and 37.77–38.77°N, collected from June to September during 2018–2022. A total of 39,000 data samples were matched with the initial zero-hour fields from RMAPS-NOW, with 80% (31,200 samples) used for training and 20% (7800 samples) for testing. Based on the ConvLSTM and the proposed MR-DCGAN architecture, 20 extrapolation models were trained using four different input encoding strategies. The models were evaluated using the Critical Success Index (CSI), Probability of Detection (POD), and False Alarm Ratio (FAR). Compared to the baseline ConvLSTM-based extrapolation model without physical variables, the models trained with the MR-DCGAN architecture achieved, on average, 18.59%, 8.76%, and 11.28% higher CSI values, 19.46%, 19.21%, and 19.18% higher POD values, and 19.85%, 11.48%, and 9.88% lower FAR values under the 20 dBZ, 30 dBZ, and 35 dBZ reflectivity thresholds, respectively. Among all tested configurations, the model that incorporated three physical variables—relative humidity (rh), u-wind, and v-wind—demonstrated the best overall performance across various thresholds, with CSI and POD values improving by an average of 16.75% and 24.75%, respectively, and FAR reduced by 15.36%. Moreover, the SSIM of the MR-DCGAN models demonstrates a more gradual decline and maintains higher overall values, indicating superior capability in preserving echo structural features. Meanwhile, the comparative experiments demonstrate that the MR-DCGAN (u, v + rh) model outperforms the MR-ConvLSTM (u, v + rh) model in terms of evaluation metrics. In summary, the model trained with the MR-DCGAN architecture effectively enhances the accuracy of radar echo extrapolation. Full article

Accurate pigment classification is essential for the analysis and conservation of historical paintings. This study presents a non-invasive approach based on supervised machine learning for classifying pigments using image data acquired under three distinct spectral illumination conditions: visible-light reflectography (VIS), ultraviolet false-color imaging (UVFC), and infrared false-color imaging (IRFC). A dataset was constructed by extracting 32 × 32 pixel patches from pigment samples, resulting in 200 classes representing 40 unique pigments with five preparation variants each. A total of 600 initial raw images were acquired, from which 4000 image patches were extracted for feature engineering. Feature vectors were obtained from visible reflectography, ultraviolet false-color imaging (UVFC), and infrared false-color imaging (IRFC) using statistical descriptors derived from RGB channels. This study demonstrates that accurate pigment classification can be achieved with a minimal set of three illumination types, offering a practical and cost-effective alternative to hyperspectral imaging in real-world conservation practice. Among the evaluated classifiers, the random forest model achieved the highest accuracy (99.30 $\pm 0.15$%). The trained model was subsequently validated on annotated regions of historical paintings, demonstrating its robustness and applicability. The proposed framework offers a lightweight, interpretable, and scalable solution for non-invasive pigment analysis in cultural heritage research that can be implemented with accessible imaging hardware and minimal post-processing. Full article

The present study aims to characterize complex geological structures and significant mineralization using remote sensing and aeromagnetic studies. Structural lineaments play a crucial role in the localization and concentration of mineral deposits. For the first time over the study district, a combination of aeromagnetic data, Landsat 9, ASTER, and PRISMA hyperspectral data was utilized to enhance the characterization of both lithological units and structural features. Advanced image processing techniques, including false color composites, principal component analysis (PCA), independent component analysis (ICA), and SMACC, were applied to the remote sensing datasets. These methods enabled effective discrimination between Phanerozoic rock formations and the complex basement units, which comprise the island arc assemblage, Dokhan volcanics, and late-orogenic granites. The local and deep magnetic sources were separated using Gaussian filters. The Neoproterozoic basement rocks were estimated using the radial average power spectrum technique and the Euler deconvolution technique (ED). According to the RAPS technique, the average depths to shallow and deep magnetic sources are approximately 0.4 km and 1.6 km, respectively. The obtained ED contacts range in depth from 0.081 to 1.5 km. The research area revealed massive structural lineaments, particularly in the northeast and northwest sides, where a dense concentration of these lineaments was identified. The locations with the highest densities are thought to signify more fracturization in the rocks that are thought to be connected to mineralization. According to the automatic lineament extraction methods and rose diagram, NW-SE, NNE-SSW, and N-S are the major structural directions. These trends were confirmed and visually represented through textural analysis and drainage pattern control. The lithological mapping results were validated through field observations and petrographic analysis. This integrated approach has proven highly effective, showcasing significant potential for both detailed structural analysis and accurate lithological discrimination, which may be related to further mineralization exploration. Full article

Road traffic emissions are still a significant contributor to air pollution, which causes adverse health effects. Remote emission sensing (RES) is a state-of-the-art technique that continuously monitors the emissions of thousands of vehicles in traffic. Automatic number plate recognition (ANPR) systems are an essential part of RES systems to identify the registered owners of high-emitting vehicles. Recognizing number plates on L-vehicles (two-wheelers) with a standard ANPR system is challenging due to differences in size and placement across various categories. No ANPR system is designed explicitly for Category L vehicles, especially mopeds. In this work, we present an automatic number plate detection and recognition system for Category L vehicles (L-ANPR) specially developed to recognize L-vehicle number plates of various sizes and colors from different categories and countries. The cost-effective and energy efficient L-ANPR system was implemented on roads during remote emission measurement campaigns in multiple European cities and tested with hundreds of vehicles. The L-ANPR system recognizes Category L vehicles by calculating the size of each passing vehicle using photoelectric sensors. It can then trigger the L-ANPR detection system, which begins detecting license plates and recognizing license plate numbers with the L-ANPR recognizing system. The L-ANPR system’s license plate detection model is trained using thousands of images of license plates from various types of Category L vehicles across different countries, and the overall detection accuracy with test images exceeded 90%. The L-ANPR system’s character recognition is designed to identify large characters on standard number plates as well as smaller characters in various colors on small, moped license plates, achieving a recognition accuracy surpassing 70%. The reasons for false recognitions are identified and the solutions are discussed in detail. Full article

Power equipment anomaly detection is essential for ensuring the stable operation of power systems. Existing models have high false and missed detection rates in complex weather and multi-scale equipment scenarios. This paper proposes a YOLO-SRSA-based anomaly detection algorithm. For data enhancement, geometric and color transformations and rain-fog simulations are applied to preprocess the dataset, improving the model’s robustness in outdoor complex weather. In the network structure improvements, first, the ACmix module is introduced to reconstruct the SPPCSPC network, effectively suppressing background noise and irrelevant feature interference to enhance feature extraction capability; second, the BiFormer module is integrated into the efficient aggregation network to strengthen focus on critical features and improve the flexible recognition of multi-scale feature images; finally, the original loss function is replaced with the MPDIoU function, optimizing detection accuracy through a comprehensive bounding box evaluation strategy. The experimental results show significant improvements over the baseline model: mAP@0.5 increases from 89.2% to 93.5%, precision rises from 95.9% to 97.1%, and recall improves from 95% to 97%. Additionally, the enhanced model demonstrates superior anti-interference performance under complex weather conditions compared to other models. Full article