Search Results (934)

The irregular and highly non-uniform spatial distribution inherent to dynamic three-dimensional (3D) point clouds (DPCs) severely hampers the extraction of reliable temporal context, rendering inter-frame compression a formidable challenge. Inspired by two-dimensional (2D) image and video compression methods, existing approaches attempt to model the temporal dependence of DPCs through a motion estimation/motion compensation (ME/MC) framework. However, these approaches represent only preliminary applications of this framework; point consistency between adjacent frames is insufficiently explored, and temporal correlation requires further investigation. To address this limitation, we propose a hierarchical ME/MC framework that adaptively selects the granularity of the estimated motion field, thereby ensuring a fine-grained inter-frame prediction process. To further enhance motion estimation accuracy, we introduce a dual-attention-based KNN block-matching (DA-KBM) network. This network employs a bidirectional attention mechanism to more precisely measure the correlation between points, using closely correlated points to predict inter-frame motion vectors and thereby improve inter-frame prediction accuracy. Experimental results show that the proposed DPC compression method achieves a significant improvement (gain of 70%) in the BD-Rate metric on the 8iFVBv2 dataset. compared with the standardized Video-based Point Cloud Compression (V-PCC) v13 method, and a 16% gain over the state-of-the-art deep learning-based inter-mode method. Full article

Nighttime sea fog exhibits high frequency and prolonged duration, posing significant risks to maritime navigation safety. Current detection methods primarily rely on the dual-infrared channel brightness temperature difference technique, which faces challenges such as threshold selection difficulties and a tendency toward overestimation. In contrast, the VIIRS Day/Night Band (DNB) offers exceptional nighttime visible-like cloud imaging capabilities, offering a new solution to alleviate the overestimation issues inherent in infrared detection algorithms. Recent advances in artificial intelligence have further addressed the threshold selection problem in traditional detection methods. Leveraging these developments, this study proposes a novel generative adversarial network model incorporating attention mechanisms (SEGAN) to achieve accurate nighttime sea fog detection using DNB data. Experimental results demonstrate that SEGAN achieves satisfactory performance, with probability of detection, false alarm rate, and critical success index reaching 0.8708, 0.0266, and 0.7395, respectively. Compared with the operational infrared detection algorithm, these metrics show improvements of 0.0632, 0.0287, and 0.1587. Notably, SEGAN excels at detecting sea fog obscured by thin cloud cover, a scenario where conventional infrared detection algorithms typically fail. SEGAN emphasizes semantic consistency in its output, endowing it with enhanced robustness across varying sea fog concentrations. Full article

This article introduces an algorithm that uses a U-Net architecture to determine vertical ground surface displacements from unmanned aerial vehicle (UAV)-photogrammetry point clouds, offering an alternative to traditional ground filtering methods. Unlike conventional ground filters that rely on point cloud classification, the proposed approach employs heteroscedastic regression. The U-Net model predicts the conditional expected values of the elevation corrections, aiming to reduce the impact of vegetation on determined ground surface elevations. Concurrently, it estimates the logarithm of the elevation correction variance, allowing for direct quantification of the uncertainty associated with each elevation correction value. The algorithm was evaluated using three metrics: the root mean square error (RMSE) of vertical displacements, the percentage of nodes with determined displacement values, and the percentage of outliers among those values. Performance was assessed using the technique for order of preference by similarity to ideal solution (TOPSIS) method and compared against several ground-filter-based algorithms across four datasets, each including at least two time intervals. In most cases, the U-Net-based approach demonstrated a slight performance advantage over traditional ground filtering techniques. For example, for the U-Net-based algorithm, for one of the test datasets, the RMSE of the determined subsidences was 6.1 cm, the percentage of nodes with determined subsidences was 80.5%, and the percentage of outliers was 0.2%. For the same case, the algorithm based on the next best model (SMRF) allowed an RMSE of 7.7 cm to be obtained; for 77.3% of nodes, the subsidences were determined; and the percentage of outliers was 0.3%. Full article

Accurate detection of road surface information is crucial for enhancing vehicle driving safety and ride comfort. To overcome the limitation that traditional suspension systems struggle to respond to road excitations in real time due to time delays in signal acquisition and control, suspension preview control technology has attracted significant attention for its proactive adjustment capability, with efficient road surface information perception being a critical prerequisite for its implementation. This paper systematically reviews road surface information detection technologies for suspension preview, focusing on the identification of potholes and speed bumps. Firstly, it summarizes relevant publicly available datasets. Secondly, it sorts out mainstream detection methods, including traditional dynamic methods, 2D image processing, 3D point cloud analysis, machine/deep learning methods, and multi-sensor fusion methods, while comparing their applicable scenarios and evaluation metrics. Furthermore, it emphasizes the core role of elevation information (e.g., pothole depth, speed bump height) in suspension preview control and summarizes elevation reconstruction technologies based on LiDAR, stereo vision, and multi-modal fusion. Finally, it prospects future research directions such as optimizing robustness, improving real-time performance, and reducing labeling costs. This review provides technical references for enhancing the accuracy of road surface information detection and the control efficiency of suspension preview systems, and it is of great significance for promoting the development of intelligent chassis. Full article

The impact of aerosols and clouds on solar energy production is a critical factor for the performance of photovoltaic systems, particularly in regions with dynamic and seasonally variable atmospheric conditions. In Northwestern Greece, the bifacial solar park in Kozani—the largest in Eastern Europe—serves as a valuable case study for evaluating these effects over a 20-year period (2004–2024). By integrating ERA5 reanalysis data and CAMS satellite-based radiation products with modeling tools such as PVGIS, seasonal and annual trends in solar irradiance attenuation were investigated. Results indicate that aerosols have the greatest impact on solar energy production during spring and summer, primarily due to increased anthropogenic and natural emissions, while cloud cover exerts the strongest effect in winter, consistent with the region’s climatic characteristics. ERA5’s estimation of absolute energy output shows a strong correlation with CAMS satellite data (R² = 0.981), supporting its reliability for trend analysis and climatological studies related to solar potential dynamics in the Southern Balkans. The bifacial park demonstrates an increasing energy yield of approximately 800.71 MWh/year over the study period, corresponding to an annual reduction of ~538 metric tons of CO₂ and a financial gain of ~12,827 €. This is the first study in the Eastern Mediterranean that combined ERA5 and CAMS datasets with the PVGIS simulation tool in a long-term evaluation of bifacial PV systems. The combined use of reanalysis and satellite datasets, rarely applied in previous studies, highlights the importance of localized, climate-informed modeling for energy planning and management, especially in a region undergoing delignification and decarbonization. Full article

The paper presents AgriMicro, a modern Farm Management Information System (FMIS) designed to help farmers monitor and optimize corn crops from sowing to harvest, by leveraging cloud technologies and machine learning algorithms. The platform is built on a modular architecture composed of multiple components implemented through microservices such as the weather and soil service, recommendation and alert engine, field service, and crop service—which continuously communicate to centralize field data and provide real-time insights. Through the ongoing exchange of data between these services, different information pieces about soil conditions, crop health, and agricultural operations are processed and analyzed, resulting in predictions of crop evolution and practical recommendations for future interventions (e.g., fertilization or irrigation). This integrated FMIS transforms collected data into concrete actions, supporting farmers and agricultural consultants in making informed decisions, improving field productivity, and ensuring more efficient resource use. Its microservice-based architecture provides scalability, modularity, and straightforward integration with other information systems. The objectives of this study are threefold. First, to specify and design a modular FMIS architecture based on microservices and cloud computing, ensuring scalability, interoperability and adaptability to different farm contexts. Second, to prototype and integrate initial components and Internet of Things (IoT)-based data collection with machine learning models, specifically Random Forest and XGBoost, to provide maize yield forecasting as a proof of concept. Model performance was evaluated using standard predictive accuracy metrics, including the coefficient of determination (R²) and the root mean square error (RMSE), confirming the reliability of the forecasting pipeline and validated against official harvest data (average maize yield) from the Romanian National Institute of Statistics (INS) for 2024. These results confirm the reliability of the forecasting pipeline under controlled conditions; however, in real-world practice, broader regional and inter-annual variability typically results in considerably higher errors, often on the order of 10–20%. Third, to present a Romania based case study which illustrates the end-to-end workflow and outlines an implementation roadmap toward full deployment. As this is a design-oriented study currently under development, several services remain at the planning or early prototyping stage, and comprehensive system level benchmarks are deferred to future work. Full article

As smart cities evolve, integrating new technologies into school transportation is becoming increasingly important to ensure student comfort and safety. Monitoring and enhancing comfort during daily commutes can significantly influence well-being and learning readiness. However, most existing research addresses isolated factors, which limits the development of comprehensive and scalable solutions. This study presents the design and implementation of a low-cost, generalized IoT-based system for monitoring comfort in school transportation. The system processes multiple environmental and operational signals, and these data are transmitted to a cloud computing platform for real-time analysis. Signal processing incorporates standardized metrics, such as root mean square (RMS) values from ISO 2631-1 for vibration assessment. In addition, machine learning techniques, including a Random Forest classifier and ensemble-based models, are applied to classify ride comfort levels using both road roughness and environmental variables. The results show that stacked multisensor fusion achieved a significant improvement in classification performance compared with vibration-only models. The platform also integrates route visualization with commuting time per student, providing valuable information to assess the impact of travel duration on school mobility. Full article

Grassland classification via remote sensing is essential for ecosystem monitoring and precision management, yet conventional satellite-based approaches are fundamentally constrained by coarse spatial resolution. To overcome this limitation, we harness high-resolution UAV multi-sensor data, integrating multi-scale image fusion with deep learning to achieve fine-scale grassland classification that satellites cannot provide. First, four categories of UAV data, including RGB, multispectral, thermal infrared, and LiDAR point cloud, were collected, and a fused image tensor consisting of 10 channels (NDVI, VCI, CHM, etc.) was constructed through orthorectification and resampling. For feature-level fusion, four deep fusion networks were designed. Among them, the MultiScale Pyramid Fusion Network, utilizing a pyramid pooling module, effectively integrated spectral and structural features, achieving optimal performance in all six image fusion evaluation metrics, including information entropy (6.84), spatial frequency (15.56), and mean gradient (12.54). Subsequently, training and validation datasets were constructed by integrating visual interpretation samples. Four backbone networks, including UNet++, DeepLabV3+, PSPNet, and FPN, were employed, and attention modules (SE, ECA, and CBAM) were introduced separately to form 12 model combinations. Results indicated that the UNet++ network combined with the SE attention module achieved the best segmentation performance on the validation set, with a mean Intersection over Union (mIoU) of 77.68%, overall accuracy (OA) of 86.98%, F1-score of 81.48%, and Kappa coefficient of 0.82. In the categories of Leymus chinensis and Puccinellia distans, producer’s accuracy (PA)/user’s accuracy (UA) reached 86.46%/82.30% and 82.40%/77.68%, respectively. Whole-image prediction validated the model’s coherent identification capability for patch boundaries. In conclusion, this study provides a systematic approach for integrating multi-source UAV remote sensing data and intelligent grassland interpretation, offering technical support for grassland ecological monitoring and resource assessment. Full article

This paper presents a comprehensive pipeline for automated prediction of branches to be pruned, integrating 3D reconstruction of fruit trees, automatic branch labeling, and pruning prediction. The workflow begins with capturing multi-view RGB-D images in orchard settings, followed by generating and preprocessing point clouds to reconstruct partial 3D models of pear trees using the TEASER++ algorithm. Differences between pre- and post-pruning models are used to automatically label branches to be pruned, creating a valuable dataset for both reconstruction methods and training machine learning models. A neural network based on PointNet++ is trained to predict branches to be pruned directly on point clouds, with performance evaluated through quantitative metrics and visual inspections. The pipeline demonstrates promising results, enabling real-time prediction suitable for robotic implementation. While some inaccuracies remain, this work lays a solid foundation for future advancements in autonomous orchard management, aiming to improve precision, speed, and practicality of robotic pruning systems. Full article

Tropical cyclones (TCs) rank among the most destructive natural hazards globally, with core damaging potential originating from regions of intense wind shear and steep wind speed gradients within the eyewall and spiral rainbands. Accurately characterizing these fine-scale structural features is therefore critical for understanding TC intensity evolution, wind hazard distribution, and disaster mitigation. Recently, the deep learning-based downscaling methods have shown significant advantages in efficiently obtaining high-resolution wind field distributions. However, existing methods are mainly used to downscale general wind fields, and research on downscaling extreme wind field events remains limited. There are two main difficulties in downscaling TC wind fields. The first one is that high-quality datasets for TC wind fields are scarce; the other is that general deep learning frameworks lack the ability to capture the dynamic characteristics of TCs. Consequently, this study proposes a novel deep learning framework, CycloneWind, for downscaling TC surface wind fields: (1) a high-quality dataset is constructed by integrating Cyclobs satellite observations with ERA5 reanalysis data, incorporating auxiliary variables like low cloud cover, surface pressure, and top-of-atmosphere incident solar radiation; (2) we propose CycloneWind, a dynamically constrained Transformer-based architecture incorporating three wind field dynamical operators, along with a wind dynamics-constrained loss function formulated to enforce consistency in wind divergence and vorticity; (3) an Adaptive Dynamics-Guided Block (ADGB) is designed to explicitly encode TC rotational dynamics using wind shear detection and wind vortex diffusion operators; (4) Filtering Transformer Layers (FTLs) with high-frequency filtering operators are used for modeling wind field small-scale details. Experimental results demonstrate that CycloneWind successfully achieves an 8-fold spatial resolution reconstruction in TC regions. Compared to the best-performing baseline model, CycloneWind reduces the Root Mean Square Error (RMSE) for the U and V wind components by 9.6% and 4.9%, respectively. More significantly, it achieves substantial improvements of 23.0%, 22.6%, and 20.5% in key dynamical metrics such as divergence difference, vorticity difference, and direction cosine dissimilarity. Full article

Cloud coverage and obstruction significantly affect the usability of remote sensing images, making cloud detection a key prerequisite for optical remote sensing applications. In existing cloud detection methods, using U-shaped convolutional networks alone has limitations in modeling long-range contexts, while Vision Transformers fall short in capturing local spatial features. To address these issues, this study proposes a dual-branch framework, TransCNet, which combines Transformer and CNN architectures to enhance the accuracy and effectiveness of cloud detection. TransCNet addresses this by designing dual encoder branches: a Transformer branch capturing global dependencies and a CNN branch extracting local details. A novel feature aggregation module enables the complementary fusion of multi-level features from both branches at each encoder stage, enhanced by channel attention mechanisms. To mitigate feature dilution during decoding, aggregated features compensate for information loss from sampling operations. Evaluations on 38-Cloud, SPARCS, and a high-resolution Landsat-8 dataset demonstrate TransCNet’s competitive performance across metrics, effectively balancing global semantic understanding and local edge preservation for clearer cloud boundary detection. The approach resolves key limitations in existing cloud detection frameworks through synergistic multi-branch feature integration. Full article

Cloud imagery analysis from terrestrial observation points represents a fundamental capability within contemporary atmospheric monitoring infrastructure, serving essential functions in meteorological prediction, climatic surveillance, and hazard alert systems. However, traditional ground-based cloud image segmentation methods have fundamental limitations, particularly their inability to effectively model the graph structure and symmetry in cloud data. To address this, we propose G-CLIP, a ground-based cloud image segmentation method based on graph symmetry. G-CLIP synergistically integrates four innovative modules. First, the Prototype-Driven Asymmetric Attention (PDAA) module is designed to reduce complexity and enhance feature learning by leveraging permutation invariance and graph symmetry principles. Second, the Symmetry-Adaptive Graph Convolution Layer (SAGCL) is constructed, modeling pixels as graph nodes, using cosine similarity to build a sparse discriminative structure, and ensuring stability through symmetry and degree normalization. Third, the Multi-Scale Directional Edge Optimizer (MSDER) is developed to explicitly model complex symmetric relationships in cloud features from a graph theory perspective. Finally, the Uncertainty-Driven Loss Optimizer (UDLO) is proposed to dynamically adjust weights to address foreground–background imbalance and provide uncertainty quantification. Extensive experiments on four benchmark datasets demonstrate that our method achieves state-of-the-art performance across all evaluation metrics. Our work provides a novel theoretical framework and practical solution for applying graph neural networks (GNNs) to meteorology, particularly by integrating graph properties with uncertainty and leveraging symmetries from graph theory for complex spatial modeling. Full article

This work presents the development of a web system using deep learning (DL) neural networks to solve the inverse kinematics problem of the Quetzal robotic arm, designed for academic and research purposes. Two architectures, LSTM and CNN, were designed, trained, and evaluated using data generated through the Denavit–Hartenberg (D-H) model, considering the robot’s workspace. The evaluation employed the mean squared error (MSE) as the loss metric and mean absolute error (MAE) and accuracy as performance metrics. The CNN model, featuring four convolutional layers and an input of 4 timesteps, achieved the best overall performance (95.9% accuracy, MSE of 0.003, and MAE of 0.040), significantly outperforming the LSTM model in training time. A hybrid web application was implemented, allowing offline training and real-time online inference under one second via an interactive interface developed with Streamlit 1.16. The solution integrates tools such as TensorFlow™ 2.15, Python 3.10, and Anaconda Distribution 2023.03-1, ensuring portability to fog or cloud computing environments. The proposed system stands out for its fast response times (1 s), low computational cost, and high scalability to collaborative robotics environments. It is a viable alternative for applications in educational or research settings, particularly in projects focused on industrial automation. Full article

In the field of Autonomous Surface Vehicle (ASV), research on advanced perception technologies is crucial for enhancing their intelligence and autonomy. In particular, laser point cloud registration technology serves as a foundation for improving the navigation accuracy and environmental awareness of ASV in complex environments. To address the issues of low computational efficiency, insufficient robustness, and incompatibility with low-power devices in laser point cloud registration technology for ASV, a novel point cloud matching method has been proposed. The proposed method includes laser point cloud data processing, feature extraction based on an improved Fast Point Feature Histogram (FPFH), followed by a two-step registration process using SAC-IA (Sample Consensus Initial Alignment) and Small_GICP (Small Generalized Iterative Closest Point). Registration experiments conducted on the KITTI benchmark dataset and the Pohang Canal dataset demonstrate that the relative translation error (RTE) of the proposed method is 16.41 cm, which is comparable to the performance of current state-of-the-art point cloud registration algorithms. Furthermore, deployment experiments on multiple low-power computing devices showcase the performance of the proposed method under low computational capabilities, providing reference metrics for engineering applications in the field of autonomous navigation and perception research for ASV. Full article

In this paper, a high-precision 3D object detector—Voxel–RCNN—is adopted as the baseline detector, and an improved detector named RCAVoxel-RCNN is proposed. To address various issues present in current mainstream 3D point cloud voxelisation methods, such as the suboptimal performance of Region Proposal Networks (RPNs) in generating candidate regions and the inadequate detection of small-scale objects caused by overly deep convolutional layers in both 3D and 2D backbone networks, this paper proposes a Cascade Attention Network (CAN). The CAN is designed to progressively refine and enhance the proposed regions, thereby producing more accurate detection results. Furthermore, a 3D Residual Network is introduced, which improves the representation of small objects by reducing the number of convolutional layers while incorporating residual connections. In the Bird’s-Eye View (BEV) feature extraction network, a Residual Attention Network (RAN) is developed. This follows a similar approach to the aforementioned 3D backbone network, leveraging the spatial awareness capabilities of the BEV. Additionally, the Squeeze-and-Excitation (SE) attention mechanism is incorporated to assign dynamic weights to features, allowing the network to focus more effectively on informative features. Experimental results on the KITTI validation dataset demonstrate the effectiveness of the proposed method, with detection accuracy for cars, pedestrians, and bicycles improving by 3.34%, 10.75%, and 4.61%, respectively, under the KITTI hard level. The primary evaluation metric adopted is the 3D Average Precision (AP), computed over 40 recall positions (R40). The Intersection over IoU thresholds used are 0.7 for cars and 0.5 for both pedestrians and bicycles. Full article