Search Results (34)

Unmanned aerial vehicle (UAV) imaging systems are increasingly deployed in surveillance, infrastructure monitoring, and smart-city applications, where the integrity of captured visual data is critical. Recent advances in generative models enable highly realistic deepfake manipulations that can compromise aerial sensor streams, particularly under real-world degradations such as motion blur, sensor noise, and compression artifacts. This paper introduces DeepLayer-ID, a degradation-aware multi-domain forensic framework specifically designed for UAV sensing environments. The proposed architecture decomposes forensic evidence into complementary spatial, frequency, and residual domains. A discrete wavelet transform module captures sub-band energy inconsistencies, while high-pass residual filtering isolates sensor pattern anomalies. A lightweight transformer-based fusion mechanism adaptively integrates cross-domain representations to enhance robustness under heterogeneous acquisition conditions. To emulate operational UAV pipelines, we construct a balanced dataset of 1096 aerial frames derived from the VisDrone2019-DET validation subset, incorporating synthetic manipulations and physics-consistent degradations. The experimental results show that DeepLayer-ID achieves 97.8% accuracy and 0.991 AUC, outperforming ResNet-50 (90.9%, 0.942 AUC), XceptionNet (92.4%, 0.957 AUC), and Noiseprint CNN (93.1%, 0.964 AUC). Notably, the model maintains real-time feasibility, with only 5.4 M parameters and 9.8 ms inference latency. These findings demonstrate that structured multi-domain signal decomposition combined with attention-guided fusion provides a robust and computationally efficient solution for deepfake detection in degraded UAV sensing systems. Full article

Multi-Object Tracking (MOT) is a fundamental research topic in the field of computer vision, with broad application potential in unmanned aerial vehicle (UAV) videos. However, existing methods still face significant challenges in detection discriminability and identity association stability due to the small scale and weak appearance of objects under aerial viewpoints, as well as complex background interference. To address these issues, we propose an Edge-Graph Enhanced Network (EGEN) for UAV aerial MOT, aiming to improve the performance of small object detection (SOD) and tracking in complex scenes. The framework follows a one-step tracking paradigm and consists of three main components: object detection, embedding feature extraction, and data association. In the detection stage, we design an Edge-Guided Gaussian Enhancement Module (EGGEM), which models edge relationships between objects and backgrounds from a global perspective and selectively enhances Gaussian features guided by edge information, thereby strengthening key structural features of small objects while suppressing background interference. In the embedding feature extraction stage, we develop a Graph-Guided Embedding Enhancement Module (GGEEM), which explicitly represents re-identification (ReID) embeddings as a graph structure and jointly models nodes and their neighborhood relationships to fully capture inter-object associations and enhance embedding discriminability. In the data association stage, we introduce a hierarchical two-stage association strategy to match objects with different confidence levels separately, improving tracking stability and robustness. Extensive experiments on the VisDrone, UAVDT, and self-constructed WildDrone datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches in both SOD and MOT, demonstrating strong generalization and practical applicability. Full article

This study aims to enhance the security of unmanned aerial vehicles (UAVs) within the Internet of Drones (IoD) ecosystem by detecting and preventing Denial-of-Service (DoS) attacks. We introduce DroneDefender, a web-based intrusion detection system (IDS) that employs machine learning (ML) techniques to identify anomalous network traffic patterns associated with DoS attacks. The system is evaluated using the CIC-IDS 2018 dataset and utilizes the Random Forest algorithm, optimized with the SMOTEENN technique to tackle dataset imbalance. Our results demonstrate that DroneDefender significantly outperforms traditional IDS solutions, achieving an impressive detection accuracy of 99.93%. Key improvements include reduced latency, enhanced scalability, and a user-friendly graphical interface for network administrators. The innovative aspect of this research lies in the development of an ML-driven, web-based IDS specifically designed for IoD environments. This system provides a reliable, adaptable, and highly accurate method for safeguarding drone operations against evolving cyber threats, thereby bolstering the security and resilience of UAV applications in critical sectors such as emergency services, delivery, and surveillance. Full article

Airport airspace safety is increasingly threatened by small, unmanned aircraft systems and wildlife that traditional radar cannot detect. While earlier reviews addressed general counter-UAS techniques, individual sensors, or the detection of single objects such as birds or drones, none has systematically reviewed airport-based, multi-sensor surveillance strategies through a safety-theoretical lens. A systematic review, performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement, synthesized recent research on fixed, ground-based aerial detection capabilities for small aerial hazards, specifically unmanned aircraft systems (sUAS) and avian targets, within operational airport environments. Searches targeted English-language, peer-reviewed articles from 2016 through 2025 in Web of Science and Scopus. Due to methodological heterogeneity across sensor technologies, a narrative synthesis was executed. The review of thirty-six studies, analyzed through Reason’s Swiss Cheese Model and Endsley’s Situational Awareness framework, found that only layered multi-sensor fusion architectures effectively address detection gaps for Low-Slow-Small (LSS) threats. Based on these findings, the review proposes seamless integration with Air Traffic Management (ATM) and UAS Traffic Management (UTM) systems through standardized data-exchange interfaces, complemented by theoretically grounded risk-based deployment strategies aligning surveillance technology tiers with operational risk profiles, from basic Remote ID receivers in low-risk rural environments to comprehensive multi-sensor fusion at high-density hubs, major airports, and urban vertiports. Full article

The importation of prefabricated buildings into colonies was a prevalent practice during the British colonial expansionist venture. However, in post-colonial Nigeria today, many of these prefabricated houses have either been largely modified or have vanished without architectural or written records. This undocumented disappearance poses a challenge to the development of architectural restoration proposals for the remaining few, especially with the authenticity of materials, as well as their morphology, configuration, use, and function being heavily contested. Among the remaining few that have undergone layers of modifications and are on the verge of total collapse is the Egbo Egbo Bassey House, imported and built in Old Calabar between 1883 and 1886 and declared a National Monument of Nigeria in 1959. Given the dearth of architectural and historical data, this paper aims to reconstruct its architectural morphology, chronological modification, and historical uses and functions, with the view of developing an evidence-based architectural restoration proposal for its adaptive reuse. The data was collected through semi-structured interviews (n = 16), archival research at the National Museum (archival file ID: TF128/C.25/A and TF120/C.20/A), and a measured architectural survey, which was performed using laser tapes and laser rangefinders. Annotated building images were captured using a Canon 5D Mark III and a DJI Marvic 3 drone. Comparative analysis with two other exemplars of prefabricated houses in the region was also conducted to consolidate oral, archival, and field data. Three architectural modification stages, namely 1886, 1959, and 2012, were determined for the analytical framework. Architectural outputs include measured 2-dimensional drawings (scale 1:50) and 3-dimensional models for the three historical stages. The accuracy of each model was ensured through methodical triangulation and confidence rubric ratings. The result of this paper provides a replicable inquiry methodology, which can be used to develop an evidence-based workflow for developing a restoration proposal for architectural heritage in contexts where architectural and historical data are not available or contested. As a limitation, this research does not include an analysis of wood typology, structural testing, and statistical analysis of material. Full article

Demodulating Orthogonal Frequency Division Multiplexing (OFDM) signals in complex wireless environments remains a fundamental challenge, especially when traditional receiver designs rely on explicit channel estimation under adverse conditions such as low signal-to-noise ratio (SNR) or carrier frequency offset (CFO). Motivated by practical challenges in decoding DroneID—a proprietary OFDM-like signaling format used by DJI drones with a nonstandard frame structure—we present TranSIC-Net, a Transformer-based end-to-end neural network that unifies channel estimation and symbol detection within a single architecture. Unlike conventional methods that treat these steps separately, TranSIC-Net implicitly learns channel dynamics from pilot patterns and exploits the attention mechanism to capture inter-subcarrier correlations. While initially developed to tackle the unique structure of DroneID, the model demonstrates strong generalizability: with minimal adaptation, it can be applied to a wide range of OFDM systems. Extensive evaluations on both synthetic OFDM waveforms and real-world unmanned aerial vehicle (UAV) signals show that TranSIC-Net consistently outperforms least-squares plus zero-forcing (LS+ZF) and leading deep learning baselines such as ProEsNet in terms of bit error rate (BER), estimation accuracy, and robustness—highlighting its effectiveness and flexibility in practical wireless communication scenarios. Full article

Traditional unmanned aerial vehicle (UAV) detection and tracking methods have long faced the twin challenges of high cost and poor efficiency. In real-world battlefield environments with complex backgrounds, occlusions, and varying speeds, existing techniques struggle to track small UAVs accurately and stably. To tackle these issues, this paper presents an enhanced YOLOv8N-Drone-based algorithm for improved target tracking of small UAVs. Firstly, a novel module named C2f-DSFEM (Depthwise-Separable and Sobel Feature Enhancement Module) is designed, integrating Sobel convolution with depthwise separable convolution across layers. Edge detail extraction and multi-scale feature representation are synchronized through a bidirectional feature enhancement mechanism, and the discriminability of target features in complex backgrounds is thus significantly enhanced. For the feature confusion problem, the improved lightweight Context Anchored Attention (CAA) mechanism is integrated into the Neck network, which effectively improves the system’s adaptability to complex scenes. By employing a position-aware weight allocation strategy, this approach enables adaptive suppression of background interference and precise focus on the target region, thereby improving localization accuracy. At the level of loss function optimization, the traditional classification loss is replaced by the focal loss (Focal Loss). This mechanism effectively suppresses the contribution of easy-to-classify samples through a dynamic weight adjustment strategy, while significantly increasing the priority of difficult samples in the training process. The class imbalance that exists between the positive and negative samples is then significantly mitigated. Experimental results show the enhanced YOLOv8 boosts mean average precision (Map@0.5) by 12.3%, hitting 99.2%. In terms of tracking performance, the proposed YOLOv8 N-Drone algorithm achieves a 19.2% improvement in Multiple Object Tracking Accuracy (MOTA) under complex multi-scenario conditions. Additionally, the IDF1 score increases by 6.8%, and the number of ID switches is reduced by 85.2%, indicating significant improvements in both accuracy and stability of UAV tracking. Compared to other mainstream algorithms, the proposed improved method demonstrates significant advantages in tracking performance, offering a more effective and reliable solution for small-target tracking tasks in UAV applications. Full article

Vehicle re-identification (Re-ID) is a critical computer vision task that aims to match the same vehicle across spatially distributed cameras, especially in the context of remote sensing imagery. While prior research has primarily focused on Re-ID using remote sensing images captured from similar, typically elevated viewpoints, these settings do not fully reflect complex aerial-ground collaborative remote sensing scenarios. In this work, we introduce a novel and challenging task: aerial-ground cross-view vehicle Re-ID, which involves retrieving vehicles in ground-view image galleries using query images captured from aerial (top-down) perspectives. This task is increasingly relevant due to the integration of drone-based surveillance and ground-level monitoring in multi-source remote sensing systems, yet it poses substantial challenges due to significant appearance variations between aerial and ground views. To support this task, we present AGID (Aerial-Ground Vehicle Re-Identification), the first benchmark dataset specifically designed for aerial-ground cross-view vehicle Re-ID. AGID comprises 20,785 remote sensing images of 834 vehicle identities, collected using drones and fixed ground cameras. We further propose a novel method, Enhanced Self-Correlation Feature Computation (ESFC), which enhances spatial relationships between semantically similar regions and incorporates shape information to improve feature discrimination. Extensive experiments on the AGID dataset and three widely used vehicle Re-ID benchmarks validate the effectiveness of our method, which achieves a Rank-1 accuracy of 69.0% on AGID, surpassing state-of-the-art approaches by 2.1%. Full article

Accurate prediction of drone motion within structured urban air corridors is essential for ensuring safe and efficient operations in Urban Air Mobility (UAM) systems. Although real-world Remote Identification (Remote ID) regulations require drones to broadcast critical flight information such as velocity, access to large-scale, high-quality broadcast data remains limited. To address this, this study leverages a Digital Twin (DT) framework to augment Remote ID spatio-temporal broadcasts, emulating the sensing environment of dense urban airspace. Using Remote ID data, we propose BiDGCNLLM, a hybrid prediction framework that integrates a Bidirectional Graph Convolutional Network (BiGCN) with Dynamic Edge Weighting and a reprogrammed Large Language Model (LLM, Qwen2.5–0.5B) to capture spatial dependencies and temporal patterns in drone speed trajectories. The model forecasts near-future speed variations in surrounding drones, supporting proactive conflict avoidance in constrained air corridors. Results from the AirSUMO co-simulation platform and a DT replica of the Cranfield University campus show that BiDGCNLLM outperforms state-of-the-art time series models in short-term velocity prediction. Compared to Transformer-LSTM, BiDGCNLLM marginally improves the $R^2$ by 11.59%. This study introduces the integration of LLMs into dynamic graph-based drone prediction. It shows the potential of Remote ID broadcasts to enable scalable, real-time airspace safety solutions in UAM. Full article

The dependency of Unmanned Aerial Vehicles (UAVs), also known as drones, on off-board data, such as control and position data, makes them highly susceptible to serious safety and security threats, including data interceptions, Global Positioning System (GPS) jamming, and spoofing attacks. This indeed necessitates the existence of an Intrusion Detection System (IDS) in place to detect potential security threats/intrusions promptly. Recently, machine-learning-based IDSs have gained popularity due to their high performance in detecting known as well as novel cyber-attacks. However, the time and computation efficiencies of ML-based IDSs still present a challenge in the UAV domain. Therefore, this paper proposes a hybrid Recursive Feature Elimination (RFE) technique based on feature importance ranking along with a Spearman Correlation Analysis (SCA). This technique is built on ensemble learning approaches, namely, bagging, boosting, stacking, and voting classifiers, to efficiently detect GPS spoofing attacks. Two benchmark datasets are employed: the GPS spoofing dataset and the UAV location GPS spoofing dataset. The results show that our proposed ensemble models achieved a notable balance between efficacy and efficiency, showing that the bagging classifier achieved the highest accuracy rate of 99.50%. At the same time, the Decision Tree (DT) and the bagging classifiers achieved the lowest processing time of 0.003 s and 0.029 s, respectively, using the GPS spoofing dataset. For the UAV location GPS spoofing dataset, the bagging classifier emerged as the top performer, achieving 99.16% accuracy and 0.002 s processing time compared to other well-known ML models. In addition, the experimental results show that our proposed methodology (RFE) outperformed other well-known ML models built on conventional feature selection techniques for detecting GPS spoofing attacks, such as mutual information gain, correlation matrices, and the chi-square test. Full article

In aerial surveillance using drones, person re-identification (ReID) is crucial for public safety. However, low resolutions in drone footage often leads to a significant drop in ReID performance of subjects. To investigate this issue, rather than relying solely on real-world datasets, we employed a synthetic dataset that systematically captures variations in drone altitude and distance. We also utilized an eXplainable Artificial Intelligence (XAI) framework to analyze how low resolutions affect ReID. Based on our findings, we propose a method that improves ReID accuracy by filtering out attributes that are not robust in low-resolution environments and retaining only those features that remain reliable. Experiments on the Market1501 dataset show a 6.59% percentage point improvement in accuracy at a 16% resolution scale. We further discuss the effectiveness of our approach in drone-based aerial surveillance systems under Fog/Edge Computing paradigms. Full article

Due to Internet of Drones (IoD) technology, drone networks have proliferated, transforming surveillance, logistics, and disaster management. Distributed Denial of Service (DDoS) attacks, malware infections, and communication abnormalities increase cybersecurity dangers to these networks, threatening operational safety and efficiency. Current Intrusion Detection Systems (IDSs) fail to handle drone transmission data’s dynamic, high-dimensional nature, resulting in inadequate real-time anomaly identification and mitigation. This study presents the Cross-Layer Convolutional Attention Network (CLCAN), a new IDS architecture for IoD networks. CLCAN accurately detects complex cyber threats using multi-scale convolutional processing, hierarchical contextual attention, and dynamic feature fusion. Preprocessing methods like weighted differential scaling and gradient-based adaptive resampling improve data quality and reduce class imbalances. Contextual attribute transformation captures the nuanced network behaviors needed for anomaly identification. The proposed technique is shown to be necessary and effective by real-world drone communication dataset evaluations. CLCAN outperforms CNN, LSTM, and XGBoost with 98.4% accuracy, 98.7% recall, and 98.1% F1-score. The model has a remarkable AUC of 0.991. CLCAN can handle datasets of over 118,000 balanced data records in 85 s, compared to 180 s for comparable frameworks. This study pioneers a unified security solution for Drone-to-Drone (D2D) and Drone-to-Base Station (D2BS) communications, filling a crucial IoD security gap. It protects mission-critical drone operations with a strong, efficient, and scalable IDS from emerging cyber threats. Full article

Traditional Re-Identification (Re-ID) schemes often rely on multiple cameras from the same perspective to search for targets. However, the collaboration between fixed cameras and unmanned aerial vehicles (UAVs) is gradually becoming a new trend in the surveillance field. Facing the significant perspective differences between fixed cameras and UAV cameras, the task of Re-ID is facing unprecedented challenges. In the setting of a single perspective, although significant advancements have been made in person Re-ID models, their performance markedly deteriorates when confronted with drastic viewpoint changes, such as transitions from aerial to ground-level perspectives. This degradation in performance is primarily attributed to the stark variations between viewpoints and the significant differences in subject posture and background across various perspectives. Existing methods focusing on learning local features have proven to be suboptimal in cross-perspective Re-ID tasks. The reason lies in the perspective distortion caused by the top-down viewpoint of drones, and the richer and more detailed texture information observed from a ground-level perspective, which leads to notable discrepancies in local features. To address this issue, the present study introduces a Multi-scale Across View Model (MAVM) that extracts features at various scales to generate a richer and more robust feature representation. Furthermore, we incorporate a Cross-View Alignment Module (AVAM) that fine-tunes the attention weights, optimizing the model’s response to critical areas such as the silhouette, attire textures, and other key features. This enhancement ensures high recognition accuracy even when subjects change posture and lighting conditions. Extensive experiments conducted on the public dataset AG-ReID have demonstrated the superiority of our proposed method, which significantly outperforms existing state-of-the-art techniques. Full article

This paper focuses on the application of ${\mathcal{L}}_1$ adaptive control to the speed autopilot loop of small-scale unmanned helicopters. The ${\mathcal{L}}_1$ adaptive control technique is investigated for its potential to provide reliable speed control, particularly in handling external disturbances and model uncertainties. Although ${\mathcal{L}}_1$ adaptive control has been widely studied, its application to small-scale unmanned helicopters remains relatively unexplored. Through numerical simulations and a preliminary experimental test campaign conducted on a small rotary-wing platform, this paper contributes to validating ${\mathcal{L}}_1$ adaptive control as a promising solution for speed regulation in unmanned helicopter platforms. Full article

In this paper, we introduce a high-altitude multi-drone multi-target (HAMDMT) tracking method called STCA, which aims to collaboratively track similar targets that are easily confused. We approach this challenge by categorizing the HAMDMT tracking into two principal tasks: Single-Drone Tracking and Cross-Drone Association. Single-Drone Tracking employs positional and appearance data vectors to overcome the challenges arising from similar target appearances within the field of view of a single drone. The Cross-Drone Association employs image-matching technology (LightGlue) to ascertain the topological relationships between images captured by disparate drones, thereby accurately determining the associations between targets across multiple drones. In Cross-Drone Association, we enhanced LightGlue into a more efficacious method, designated T-LightGlue, for cross-drone target tracking. This approach markedly accelerates the tracking process while reducing indicator dropout. To narrow down the range of targets involved in the cross-drone association, we develop a Common View Area Model based on the four vertices of the image. Considering to mitigate the occlusion encountered by high-altitude drones, we design a Local-Matching Model that assigns the same ID to the mutually nearest pair of targets from different drones after mapping the centroids of the targets across drones. The MDMT dataset is the only one captured by a high-altitude drone and contains a substantial number of similar vehicles. In the MDMT dataset, the STCA achieves the highest MOTA in Single-Drone Tracking, with the IDF1 system achieving the second-highest performance and the MDA system achieving the highest performance in Cross-Drone Association. Full article