Search Results (1,277)

The utilization of Unmanned Aerial Vehicles (UAVs) in missions such as reconnaissance and surveillance has grown rapidly, underscoring the need for efficient path planning algorithms that ensure both optimality and collision avoidance. The A-star algorithm is widely used for global path planning due to its ability to generate optimal routes; however, its high computational cost makes it unsuitable for real-time applications, particularly in unknown or dynamic environments. For local path planning, the Artificial Potential Field (APF) algorithm enables real-time navigation by attracting the UAV toward the target while repelling it from obstacles. Despite its efficiency, APF suffers from local minima and limited performance in dynamic settings. To address these challenges, this paper proposes the A-star-Guided Potential Field (AGPF) algorithm, which integrates the strengths of A-star and APF to achieve robust performance in both global and local path planning. The AGPF algorithm was validated through simulations conducted in the Robot Operating System (ROS) environment. Simulation results demonstrate that AGPF produces smoother and more optimal paths than A-star, while avoiding the local minima issues inherent in APF. Furthermore, AGPF effectively handles moving and previously unknown obstacles by generating real-time avoidance trajectories, demonstrating strong adaptability in dynamic and uncertain environments. Full article

The growth and sustainability of today’s global economy heavily relies on smooth maritime operations. The increasing security concerns to marine environments pose complex security challenges, such as smuggling, illegal fishing, human trafficking, and environmental threats, for traditional surveillance methods due to their limitations. Artificial intelligence (AI), particularly deep learning, has offered strong capabilities for automating object detection, anomaly identification, and situational awareness in maritime environments. In this paper, we have reviewed the state-of-the-art deep learning models mainly proposed in recent literature (2020–2025), including convolutional neural networks, recurrent neural networks, Transformers, and multimodal fusion architectures. We have highlighted their success in processing diverse data sources such as satellite imagery, AIS, SAR, radar, and sensor inputs from UxVs. Additionally, multimodal data fusion techniques enhance robustness by integrating complementary data, yielding more detection accuracy. There still exist challenges in detecting small or occluded objects, handling cluttered scenes, and interpreting unusual vessel behaviours, especially under adverse sea conditions. Additionally, explainability and real-time deployment of AI models in operational settings are open research areas. Overall, the review of existing maritime literature suggests that deep learning is rapidly transforming maritime domain awareness and response, with significant potential to improve global maritime security and operational efficiency. We have also provided key datasets for deep learning models in the maritime security domain. Full article

Unmanned aerial vehicles (UAVs) are widely used in surveillance and combat for their efficiency and autonomy, whilst complex, dynamic environments challenge the modeling of inter-agent relations and information transmission. This research proposes a novel UAV tactical choice-making algorithm utilizing graph neural networks to tackle these challenges. The proposed algorithm employs a graph neural network to process the observed state information, the convolved output of which is then fed into a reconstructed critic network incorporating a Laplacian convolution kernel. This research first enhances the accuracy of obtaining unstable state information in hostile environments. The proposed algorithm uses this information to train a more precise critic network. In turn, this improved critic network guides the actor network to make decisions that better meet the needs of the battlefield. Coupled with a policy transfer mechanism, this architecture significantly enhances the decision-making efficiency and environmental adaptability within the multi-agent system. Results from the experiments show that the average effectiveness of the proposed algorithm across the six planned scenarios is 97.4%, surpassing the baseline by 23.4%. In addition, the integration of transfer learning makes the network convergence speed three times faster than that of the baseline algorithm. This algorithm effectively improves the information transmission efficiency between the environment and the UAV and provides strong support for UAV formation combat. Full article

Recent outbreaks of highly pathogenic human RNA viruses from probable zoonotic origin have highlighted the relevance of epidemic preparedness as a society. However, research in vaccinology and virology, as well as epidemiologic surveillance, is often constrained by the biological risk that live virus experimentation entails. These also involve expensive costs, time-consuming procedures, and advanced personnel expertise, hampering market access for many drugs. Most of these drawbacks can be circumvented with the use of pseudotyped viruses, which are surrogate, non-pathogenic recombinant viral particles bearing the surface envelope protein of a virus of interest. Pseudotyped viruses significantly expand the research potential in virology, enabling the study of non-culturable or highly infectious pathogens in a safer environment. Most are derived from lentiviral vectors, which confer a series of advantages due to their superior efficiency. During the past decade, many studies employing pseudotyped viruses have evaluated the efficacy of vaccines or monoclonal antibodies for relevant pathogens such as HIV-1, Ebolavirus, Influenza virus, or SARS-CoV-2. In this review, we aim to provide an overview of the applications of pseudotyped viruses when evaluating the neutralization capacity of exposed individuals, or candidate vaccines and antivirals in both preclinical models and clinical trials, to further help develop effective countermeasures against emerging neutralization-escape phenotypes. Full article

Infrared ship detection plays a vital role in maritime surveillance systems. As a critical remote sensing application, it enables maritime surveillance across diverse geographic scales and operational conditions while offering robust all-weather operation and resilience to environmental interference. However, infrared imagery in complex maritime environments presents significant challenges, including low contrast, background clutter, and difficulties in detecting small-scale or distant targets. To address these issues, we propose an Infrared Ship Detection Network (IRSD-Net), a lightweight and efficient detection network built upon the YOLOv11n framework and specially designed for infrared maritime imagery. IRSD-Net incorporates a Hierarchical Multi-Kernel Convolution Network (HMKCNet), which employs parallel multi-kernel convolutions and channel division to enhance multi-scale feature extraction while reducing redundancy and memory usage. To further improve cross-scale fusion, we design the Dynamic Cross-Scale Feature Pyramid Network (DCSFPN), a bidirectional architecture that combines up- and downsampling to integrate low-level detail with high-level semantics. Additionally, we introduce Wise-PIoU, a novel loss function that improves bounding box regression by enforcing geometric alignment and adaptively weighting gradients based on alignment quality. Experimental results demonstrate that IRSD-Net achieves 92.5% ${\mathrm{mAP}}_{50}$ on the ISDD dataset, outperforming YOLOv6n and YOLOv11n by 3.2% and 1.7%, respectively. With a throughput of 714.3 FPS, IRSD-Net delivers high-accuracy, real-time performance suitable for practical maritime monitoring systems. Full article

This review examines advancements in smart home security through the integration of home automation technologies. Various security systems, including surveillance cameras, smart locks, and motion sensors, are analyzed, highlighting their effectiveness in enhancing home security. These systems enable users to monitor and control their homes in real-time, providing an additional layer of security. The document also examines how these security systems can enhance the quality of life for users by providing greater convenience and control over their domestic environment. The ability to receive instant alerts and access video recordings from anywhere allows users to respond quickly to unexpected situations, thereby increasing their sense of security and well-being. Additionally, the challenges and future trends in this field are addressed, emphasizing the importance of designing solutions that are intuitive and easy to use. As technology continues to evolve, it is crucial for developers and manufacturers to focus on creating products that seamlessly integrate into users’ daily lives, facilitating their adoption and use. This comprehensive state-of-the-art review, based on the Scopus database, provides a detailed overview of the current status and future potential of smart home security systems. It highlights how ongoing innovation in this field can lead to the development of more advanced and efficient solutions that not only protect homes but also enhance the overall user experience. Full article

Bird-dropping fouling and hotspot anomalies remain the most prevalent and detrimental defects in utility-scale photovoltaic (PV) plants; their co-occurrence on a single module markedly curbs energy yield and accelerates irreversible cell degradation. However, markedly disparate visual–thermal signatures of the two phenomena impede high-fidelity concurrent detection in existing robotic inspection systems, while stringent onboard compute budgets also preclude the adoption of bulky detectors. To resolve this accuracy–efficiency trade-off for dual-defect detection, we present YOLOv8-SG, a lightweight yet powerful framework engineered for mobile PV inspectors. First, a rigorously curated multi-modal dataset—RGB for stains and long-wave infrared for hotspots—is assembled to enforce robust cross-domain representation learning. Second, the HSV color space is leveraged to disentangle chromatic and luminance cues, thereby stabilizing appearance variations across sensors. Third, a single-head self-attention (SHSA) block is embedded in the backbone to harvest long-range dependencies at negligible parameter cost, while a global context (GC) module is grafted onto the detection head to amplify fine-grained semantic cues. Finally, an auxiliary bounding box refinement term is appended to the loss to hasten convergence and tighten localization. Extensive field experiments demonstrate that YOLOv8-SG attains 86.8% mAP@0.5, surpassing the vanilla YOLOv8 by 2.7 pp while trimming 12.6% of parameters (18.8 MB). Grad-CAM saliency maps corroborate that the model’s attention consistently coincides with defect regions, underscoring its interpretability. The proposed method, therefore, furnishes PV operators with a practical low-latency solution for concurrent bird-dropping and hotspot surveillance. Full article

Unmanned aerial vehicles (UAVs), commonly known as drones, offer unprecedented flexibility for complex missions such as area surveillance, search and rescue, and cooperative inspection. This paper presents a unified evaluation framework for the comparison of centralized and distributed task allocation algorithms specifically tailored to multi-UAV operations. We first contextualize the classical assignment problem (AP) under UAV mission constraints, including the flight time, propulsion energy capacity, and communication range, and evaluate optimal one-to-one solvers including the Hungarian algorithm, the Bertsekas $ϵ$-auction algorithm, and a minimum cost maximum flow formulation. To reflect the dynamic, uncertain environments that UAV fleets encounter, we extend our analysis to distributed multi-UAV task allocation (MUTA) methods. In particular, we examine the consensus-based bundle algorithm (CBBA) and a distributed auction 2-opt refinement strategy, both of which iteratively negotiate task bundles across UAVs to accommodate real-time task arrivals and intermittent connectivity. Finally, we outline how reinforcement learning (RL) can be incorporated to learn adaptive policies that balance energy efficiency and mission success under varying wind conditions and obstacle fields. Through simulations incorporating UAV-specific cost models and communication topologies, we assess each algorithm’s mission completion time, total energy expenditure, communication overhead, and resilience to UAV failures. Our results highlight the trade-off between strict optimality, which is suitable for small fleets in static scenarios, and scalable, robust coordination, necessary for large, dynamic multi-UAV deployments. Full article

Forest fire detection is an essential application in environmental surveillance since wildfires cause devastating damage to ecosystems, human life, and property every year. The effective and accurate detection of fire is necessary to allow for timely response and efficient management of disasters. Traditional techniques for fire detection often experience false alarms and delayed responses in various environmental situations. Therefore, developing robust, intelligent, and real-time detection systems has emerged as a central challenge in remote sensing and computer vision research communities. Despite recent achievements in deep learning, current forest fire detection models still face issues with generalizability, lightweight deployment, and accuracy trade-offs. In order to overcome these limitations, we introduce a novel technique (FireNet-KD) that makes use of knowledge distillation, a method that maps the learning of hard models (teachers) to a light and efficient model (student). We specifically utilize two opposing teacher networks: a Vision Transformer (ViT), which is popular for its global attention and contextual learning ability, and a Convolutional Neural Network (CNN), which is esteemed for its spatial locality and inductive biases. These teacher models instruct the learning of a Swin Transformer-based student model that provides hierarchical feature extraction and computational efficiency through shifted window self-attention, and is thus particularly well suited for scalable forest fire detection. By combining the strengths of ViT and CNN with distillation into the Swin Transformer, the FireNet-KD model outperforms state-of-the-art methods with significant improvements. Experimental results show that the FireNet-KD model obtains a precision of 95.16%, recall of 99.61%, F1-score of 97.34%, and mAP@50 of 97.31%, outperforming the existing models. These results prove the effectiveness of FireNet-KD in improving both detection accuracy and model efficiency for forest fire detection. Full article

The Medium Earth Orbit (MEO) spaceborne Synthetic Aperture Radar (SAR) has great coverage ability, which can improve maritime ship target surveillance performance significantly. However, due to the huge computational load required for imaging processing and the severe defocusing caused by ship motions, traditional ship recognition conducted in focused image domains cannot process MEO SAR data efficiently. To address this issue, a multi-level focusing-classification strategy for MEO SAR ship recognition is proposed, which is applied to the range-compressed ship data domain. Firstly, global fast coarse-focusing is conducted to compensate for sailing motion errors. Then, a coarse-classification network is designed to realize major target category classification, based on which local region image slices are extracted. Next, fine-focusing is performed to correct high-order motion errors, followed by applying fine-classification applied to the image slices to realize final ship classification. Equivalent MEO SAR ship images generated by real LEO SAR data are utilized to construct training and testing datasets. Simulated MEO SAR ship data are also used to evaluate the generalization of the whole method. The experimental results demonstrate that the proposed method can achieve high classification precision. Since only local region slices are used during the second-level processing step, the complex computations induced by fine-focusing for the full image can be avoided, thereby significantly improving overall efficiency. Full article

The integration of radar and Automatic Dependent Surveillance–Broadcast (ADS-B) surveillance data is critical for increasing the accuracy of air traffic monitoring; however, effective track associations remain challenging due to inherent sensor discrepancies and computational constraints. To achieve accurate identification and association between radar tracks and ADS-B tracks, this study proposes an adaptive feature extraction method based on the longest common subsequence (LCSS) combined with classification theory to address the limitations inherent in traditional machine learning-based track association approaches. These limitations encompass challenges in acquiring training samples, extended training times, and limited model generalization performance. The proposed method employs LCSS to measure the similarity between two types of trajectories and categorizes tracks into three groups—definite associations, definite nonassociations, and fuzzy associations—using a similarity matrix and an adaptive sample classification model (adaptive classification model). Fuzzy mathematical techniques are subsequently applied to extract discriminative features from both definite association and nonassociation sets, followed by training a support vector machine (SVM) model. Finally, the SVM performs classification and association of trajectories in the fuzzy association group. The computational results show that, compared with conventional statistical methods, the proposed methodology achieves both superior precision and recall rates while maintaining computational efficiency threefold that of traditional machine learning algorithms. Full article

Deep learning (DL) continues to play a pivotal role in a wide range of intelligent systems, including autonomous machines, smart surveillance, industrial automation, and portable healthcare technologies. These applications often demand low-latency inference and efficient resource utilization, especially when deployed on embedded or edge devices with limited computational capacity. As DL models become increasingly complex, selecting the right inference framework is essential to meeting performance and deployment goals. In this work, we conduct a comprehensive comparison of five widely adopted inference frameworks: PyTorch, ONNX Runtime, TensorRT, Apache TVM, and JAX. All experiments are performed on the NVIDIA Jetson AGX Orin platform, a high-performance computing solution tailored for edge artificial intelligence workloads. The evaluation considers several key performance metrics, including inference accuracy, inference time, throughput, memory usage, and power consumption. Each framework is tested using a wide range of convolutional and transformer models and analyzed in terms of deployment complexity, runtime efficiency, and hardware utilization. Our results show that certain frameworks offer superior inference speed and throughput, while others provide advantages in flexibility, portability, or ease of integration. We also observe meaningful differences in how each framework manages system memory and power under various load conditions. This study offers practical insights into the trade-offs associated with deploying DL inference on resource-constrained hardware. Full article

The goal of single-image super-resolution (SISR) tasks is to generate high-definition images from low-quality inputs, with practical uses spanning healthcare diagnostics, aerial imaging, and surveillance systems. Although cnns have considerably improved image reconstruction quality, existing methods still face limitations, including inadequate restoration of high-frequency details, high computational complexity, and insufficient adaptability to complex scenes. To address these challenges, we propose an Omni-dimensional Dynamic Convolutional Network (ODConvNet) tailored for SISR tasks. Specifically, ODConvNet comprises four key components: a Feature Extraction Block (FEB) that captures low-level spatial features; an Omni-dimensional Dynamic Convolution Block (DCB), which utilizes a multidimensional attention mechanism to dynamically reweight convolution kernels across spatial, channel, and kernel dimensions, thereby enhancing feature expressiveness and context modeling; a Deep Feature Extraction Block (DFEB) that stacks multiple convolutional layers with residual connections to progressively extract and fuse high-level features; and a Reconstruction Block (RB) that employs subpixel convolution to upscale features and refine the final HR output. This mechanism significantly enhances feature extraction and effectively captures rich contextual information. Additionally, we employ an improved residual network structure combined with a refined Charbonnier loss function to alleviate gradient vanishing and exploding to enhance the robustness of model training. Extensive experiments conducted on widely used benchmark datasets, including DIV2K, Set5, Set14, B100, and Urban100, demonstrate that, compared with existing deep learning-based SR methods, our ODConvNet method improves Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), and the visual quality of SR images is also improved. Ablation studies further validate the effectiveness and contribution of each component in our network. The proposed ODConvNet offers an effective, flexible, and efficient solution for the SISR task and provides promising directions for future research. Full article

Detecting airborne viruses using an integrated aerosol sampling detection device is of great significance in epidemic prevention and control. Most of the applicable aerosol samplers have a flow rate of less than 1000 L/min, which is insufficient for application in large public spaces. Recent research, on the other hand, has revealed the advantages of microfluidic chip-based LAMP–CRISPR in airborne virus detection; however, this promising detection method has yet to be integrated with an aerosol sampler. Herein, we present an aerosol sampling and microfluidic chip-based detection (ASMD) device that couples a high-flow-rate aerosol sampling (HFAS) system with a microfluidic LAMP–CRISPR detection (MLCD) chip for surveilling airborne viruses, as represented by SARS-CoV-2. The HFAS system achieved a 6912 L/min flow rate while retaining a satisfactory collection efficiency, and achieved an enrichment ratio of 1.93 × 10⁷ that facilitated subsequent detection by the MLCD chip. The MLCD chip integrates the whole LAMP–CRISPR procedure into a single chip and is compatible with the HFAS system. Environmental detection experiments show the feasibility of the ASMD device for aerosol sampling and detection. Our ASMD device is a promising tool for large space aerosol detection for airborne virus surveillance. Full article

Large language models (LLMs) are increasingly being applied to clinical tasks, but it remains unclear whether medical-specific models consistently outperform smaller, generalpurpose ones. This study investigates that assumption in the context of cardiovascular disease (CVD) risk assessment. We fine-tuned eight LLMs—both general-purpose and medical-specific—using textualized data from the Behavioral Risk Factor Surveillance System (BRFSS) to classify individuals as “High Risk” or “Low Risk”. To provide actionable insights, we integrated a Retrieval-Augmented Generation (RAG) framework for personalized recommendation generation and deployed the system within an interactive chatbot interface. Notably, Gemma2, a compact 2B-parameter general-purpose model, achieved a high recall (0.907) and F1-score (0.770), performing on par with larger or medical-specialized models such as Med42 and BioBERT. These findings challenge the common assumption that larger or specialized models always yield superior results, and highlight the potential of lightweight, efficiently fine-tuned LLMs for clinical decision support—especially in resource-constrained settings. Overall, our results demonstrate that general-purpose models, when fine-tuned appropriately, can offer interpretable, high-performing, and accessible solutions for CVD risk assessment and personalized healthcare delivery. Full article