Search Results (101)

Edge detection is a key building block in real-time image-processing applications such as drone-based infrastructure inspection, autonomous navigation, and remote sensing. However, its computational cost remains a challenge for resource-constrained embedded systems. This work presents a hardware-accelerated edge detection architecture based on a homogeneous 2D-mesh Network-on-Chip (NoC) integrating systolic arrays to efficiently perform the convolution operations required by the Sobel filter. The proposed architecture was first developed and validated as a 3 × 3 mesh prototype on FPGA (Xilinx Zynq-7000, Zynq-7010, XC7Z010-CLG400A, Zybo board, utilizing 26,112 LUTs, 24,851 flip-flops, and 162 DSP blocks), achieving a throughput of 8.8 Gb/s with a power consumption of 0.79 W at 100 MHz. Building upon this validated prototype, a reduced 2 × 2 node cluster with 14-bit word width was subsequently synthesized at the physical level as a proof-of-concept using the OpenLane RTL-to-GDSII open-source flow targeting the SkyWater 130 nm PDK (sky130A). Post-layout analysis confirms the manufacturability of the design, with a total power consumption of 378 mW and compliance with timing constraints, demonstrating the feasibility of mapping the proposed architecture to silicon and its suitability for drone-based infrastructure monitoring applications. Full article

Modern agricultural operations generate high-volume and diverse data (historical and stream) from various sources, including IoT devices, robots, and drones. This paper presents a novel smart farming architecture specifically designed to efficiently manage and process this complex data landscape.The proposed architecture comprises five distinct, interconnected layers: The Source Layer, the Ingestion Layer, the Batch Layer, the Speed Layer, and the Governance Layer. The Source Layer serves as the unified entry point, accommodating structured, spatial, and image data from sensors, Drones, and ROS-equipped robots. The Ingestion Layer uses a hybrid fog/cloud architecture with Kafka for real-time streams and for batch processing of historical data. Data is then segregated for processing: The cloud-deployed Batch Layer employs a Hadoop cluster, Spark, Hive, and Drill for large-scale historical analysis, while the Speed Layer utilizes Geoflink and PostGIS for low-latency, real-time geovisualization. Finally, the Governance Layer guarantees data quality, lineage, and organization across all components using Open Metadata. This layered, hybrid approach provides a scalable and resilient framework capable of transforming raw agricultural data into timely, actionable insights, addressing the critical need for advanced data management in smart farming. Full article

Open-pit coal mining is characterized by multiple pollution sources, diverse types, and extensive affected areas, leading to complex air pollution with wide diffusion. Traditional fixed monitoring methods cannot address these limitations. Taking a coal mine in Xinjiang as a case study, this study developed a drone-mounted mobile atmospheric monitoring system, focusing on nitrogen dioxide (NO₂) and suspended particulate matter (PM_2.5 and PM₁₀) to explore their distribution, diffusion patterns, and influencing factors. The results show distinct seasonal pollutant characteristics: NO₂ and ozone (O₃) dominate in summer, while particulate matter prevails in winter. The temporal distribution exhibits a bimodal pattern, with high levels in the early morning and evening hours. Spatially, higher pollutant concentrations accumulate vertically below ground level, while lower levels are observed above it. Horizontally, elevated concentrations are found along northern transport corridors; however, these levels become more uniform at greater heights. A spatiotemporal prediction model integrating convolutional neural network (CNN) and long short-term memory (LSTM) network was successfully applied to real-time pollutant prediction in open-pit coal mining areas. This study provides a reliable mobile monitoring solution for open-pit coal mine air pollution and offers valuable insights for targeted pollution control in similar mining areas. Full article

Unmanned aerial vehicles (UAVs) equipped with thermal cameras are increasingly used in search and rescue (SAR) operations, where low visibility and small human footprints make detection a critical challenge. Existing datasets are mostly limited to urban or open-field scenarios, and our experiments show that models trained on such heterogeneous data achieve poor results. To address this gap, we collected and annotated thermal images in mountainous environments using a DJI M3T drone under clear daytime conditions. This mountain-specific set was integrated with ten existing sources to form an extensive benchmark of over 75,000 images. We then performed a comparative evaluation of object detection models (YOLOv8/9/10, RT-DETR) and semantic segmentation networks (U-Net variants), analyzing accuracy, inference speed, and energy consumption on an NVIDIA Jetson AGX Orin. Results demonstrate that human detection tasks can be accurately solved through both semantic segmentation and object detection, achieving 90% detection accuracy using segmentation models and 85% accuracy using the YOLOv8 X detection model in mountain scenarios. On the Jetson platform, segmentation achieves real-time performance with up to 27 FPS in FP16 mode. Our contributions are as follows: (i) the introduction of a new mountainous thermal image collection extending current benchmarks and (ii) a comprehensive evaluation of detection methods on embedded hardware for SAR applications. Full article

In facility horticultural production, intelligent disease recognition and precise intervention are vital for crop health and economic efficiency. We construct a multi-source dataset from Bayan Nur, Weifang, and Honghe that integrates handheld camera photos, drone field images, and laboratory-controlled samples. Handheld images capture fine lesion texture for close-up diagnosis common in greenhouses; drone images provide canopy-scale patterns and spatial context suited to open-field management; laboratory images offer controlled illumination and background for stable supervision and cross-crop feature learning. Our objective is robust cross-crop, cross-regional diagnosis and economically rational control. To this end, a model named CCGD-Net is proposed. It is designed as a multi-task framework. The framework incorporates a multi-scale perception module (MSFE) to produce hierarchical representations. It includes a cross-domain alignment module (CDAM) that reduces distribution shifts between greenhouse and open-field environments. The training follows an unsupervised domain adaptation setting that uses unlabeled target-region images. When such images are not available, the model functions in a pure generalization mode. The framework also integrates a regional economic strategy module (RESM) that transforms recognition outputs and local cost information into optimized intervention intensity. Experiments show an accuracy of 91.6%, an F1-score of 89.8%, and an mAP of 88.9%, outperforming Swin Transformer and ConvNeXt; removing RESM reduces F1 to 87.2%. In cross-regional testing (Weifang training → Honghe testing), the model attains an F1 of 88.0% and mAP of 86.5%. These results indicate that integrating complementary imaging modalities with domain alignment and economic optimization provides an effective solution for disease diagnosis across greenhouse and field systems. Full article

This study presents the design and implementation of a low-cost, open-source, 3D-printed drone platform for university-level STEM education in mechatronics, robotics, control theory, and artificial intelligence. The platform addresses key limitations of existing educational drones, such as high cost, the proprietary nature of systems, and limited customizability, by integrating accessible materials, Arduino-compatible microcontrollers, and modular design principles, with all design files and instructional materials openly available. This work introduces technical improvements, including enhanced safety features and greater modularity, alongside pedagogical advancements such as structured lesson plans, a workflow bridging simulation, and hardware implementation. Educational impact was evaluated through a case study in a postgraduate course with 39 students participating in project-based activities involving 3D modeling, electronics integration, programming, and flight testing. Data collected via a Technology Acceptance Model-based survey and researcher observations showed high student engagement and satisfaction, with average scores of 4.49/5 for overall experience, 4.31/5 for perceived usefulness, and 4.38/5 for intention to use the drone in future activities. These results suggest the platform is a practical and innovative teaching tool for academic settings. Future work will extend its educational evaluation and application across broader contexts. Full article

We investigate the applicability of visual foundation models, a recent advancement in artificial intelligence, for archaeological remote sensing. In contrast to earlier approaches, we employ a strictly zero-shot methodology, testing the hypothesis that such models can perform archaeological feature detection without any fine-tuning or other adaptation for the remote sensing domain. Across five experiments using satellite imagery, aerial LiDAR, and drone video data, we assess the models’ ability to detect archaeological features. Our results demonstrate that such foundation models can achieve detection performance comparable to that of human experts and established automated methods. A key advantage lies in the substantial reduction of required human effort and the elimination of the need for training data. To support reproducibility and future experimentation, we provide open-source scripts and datasets and suggest a novel workflow for remote sensing projects. If current trends persist, foundation models may offer a scalable and accessible alternative to conventional archaeological prospection. Full article

To tackle the challenges posed by substantial variations in target scale, intricate background interference, and the likelihood of missing small targets in multi-temporal UAV maize tassel imagery, an optimized lightweight detection model derived from YOLOv11 is introduced, named OTB-YOLO. Here, “OTB” is an acronym derived from the initials of the model’s core improved modules: Omni-dimensional dynamic convolution (ODConv), Triplet Attention, and Bi-directional Feature Pyramid Network (BiFPN). This model integrates the PaddlePaddle open-source maize tassel recognition benchmark dataset with the public Multi-Temporal Drone Corn Dataset (MTDC). Traditional convolutional layers are substituted with omni-dimensional dynamic convolution (ODConv) to mitigate computational redundancy. A triplet attention module is incorporated to refine feature extraction within the backbone network, while a bidirectional feature pyramid network (BiFPN) is engineered to enhance accuracy via multi-level feature pyramids and bidirectional information flow. Empirical analysis demonstrates that the enhanced model achieves a precision of 95.6%, recall of 92.1%, and mAP@0.5 of 96.6%, marking improvements of 3.2%, 2.5%, and 3.1%, respectively, over the baseline model. Concurrently, the model’s computational complexity is reduced to 6.0 GFLOPs, rendering it appropriate for deployment on UAV edge computing platforms. Full article

Metal–air batteries have excellent theoretical energy density and economic advantages through abundant anode materials and open cathode structures. However, the actual energy efficiency of metal–air batteries is much lower than the theoretical value due to the effect of polarization voltage during battery operation, limiting the power output and thus hindering their practical application. This review systematically dissects the origins of polarization: slow oxygen reduction/evolution reaction (ORR/OER) kinetics, interfacial resistance, and mass transfer bottlenecks. We highlight cutting-edge strategies to mitigate polarization, including atomic-level engineering of air cathodes (e.g., single-atom catalysts, low Pt catalysts), biomass-derived 3D porous electrodes, and electrolyte innovations (additives to inhibit corrosion, solid-state electrolytes to improve stability). In addition, breakthroughs in metal–H₂O₂ battery design using concentrated liquid oxygen sources are discussed. Together, these advances alleviate the battery polarization bottleneck and pave the way for practical applications of metal–air batteries in electric vehicles, drones, and deep-sea devices. Full article

With the rapid development of the low-altitude economy, the application of drones in both military and civilian fields has become increasingly widespread. The safety and accuracy of their positioning and navigation have become critical factors in ensuring the successful execution of missions. Currently, GNSS spoofing attack techniques are becoming increasingly sophisticated, posing a serious threat to the reliability of drone positioning. This paper proposes a GNSS spoofing detection and autonomous positioning method for drones operating in mission mode, which is based on visual sensors and does not rely on additional hardware devices. First, during the deception detection phase, the ResNet50-SE twin network is used to extract and match real-time aerial images from the drone’s camera with satellite image features obtained via GNSS positioning, thereby identifying positioning anomalies. Second, once deception is detected, during the positioning recovery phase, the system uses the SuperGlue network to match real-time aerial images with satellite image features within a specific area, enabling the drone’s absolute positioning. Finally, experimental validation using open-source datasets demonstrates that the method achieves a GNSS spoofing detection accuracy of 89.5%, with 89.7% of drone absolute positioning errors controlled within 13.9 m. This study provides a comprehensive solution for the safe operation and stable mission execution of drones in complex electromagnetic environments. Full article

A primary objective of this research entails the development of an innovative algorithm capable of tracking a drone in real-time. This objective serves as a fundamental requirement across various applications, including collision avoidance, formation flying, and the interception of moving targets. Nonetheless, regardless of the efficacy of any detection algorithm, achieving 100% performance remains unattainable. Deep neural networks (DNNs) were employed to enhance this performance. To facilitate real-time operation, the DNN must be executed within a Deep Learning Processing Unit (DPU), Neural Processing Unit (NPU), Tensor Processing Unit (TPU), or Graphics Processing Unit (GPU) system on board the UAV. Given the constraints of these processing units, it may be necessary to quantify the DNN or utilize a less complex variant, resulting in an additional reduction in performance. However, precise target detection at each control step is imperative for effective flight path control. By integrating multiple algorithms, the developed system can effectively track UAVs with improved detection performance. Furthermore, this paper aims to establish a versatile Unmanned Aerial System (UAS) development platform constructed using open-source components and possessing the capability to adapt and evolve seamlessly throughout the development and post-production phases. Full article

The European Union’s developing rural development plan places digital and precision agriculture at the centre of agricultural modernisation and economic development. This article examines how agricultural practices in rural EU regions are being influenced by smart technology, such as drones, IoT sensors, satellite-based research, and AI-driven platforms, through an analysis of recent data from sources across the European Union. This study applies a mixed-methods approach, combining quantitative analysis of strategic policy documents and EU databases, to evaluate the ways in which precision agriculture reduces input consumption, increases productivity, reduces labour shortages and rural area depopulation, and improves sustainability. By investing in infrastructure, developing communities for data exchange, and organising training for farmers, European policies such as the Strategic Plans of the Common Agricultural Policy (CAP), the SmartAgriHubs initiative, and the AgData program actively encourage the transition to digital agriculture. Cyprus is analysed as a case study to show how targeted investments and initiatives supported by the EU can help smaller countries, with limited natural resources, to realise the benefits of digital transformation in agriculture. A special focus is placed on how solutions adapted to agro-climatic and socioeconomic conditions can contribute to strengthening the competitiveness of the agricultural sector, attracting young people to get involved in this field and opening up new economic opportunities. The results of previous research indicate that digital agriculture not only improves productivity but also proves to be a strategic mechanism for attracting and retaining young people in rural areas. Thus, this work additionally contributes to the broader goal of the European Union—the development of smart, inclusive, and sustainable rural areas, in which digital technologies are not only seen as tools for efficiency but also as key means for integrated and long-term rural development. Full article

Quantifying methane (CH₄) emissions is essential for climate change mitigation; however, current estimation methods often suffer from substantial uncertainties, particularly at the site level. This study introduces a drone-based approach for measuring CH₄ emissions using an open-path Tunable Diode Laser Absorption Spectroscopy (TDLAS) sensor mounted parallel to the ground, rather than in the traditional nadir-pointing configuration. Controlled CH₄ release experiments were conducted to evaluate the method’s accuracy, employing a modified mass-balance technique to estimate emission rates. Two wind data processing strategies were compared: a logarithmic wind profile (LW) and a constant scalar wind speed (SW). The LW approach yielded highly accurate results, with an average recovery rate of 98%, while the SW approach showed greater variability with increasing distance from the source, although it remained reliable in close proximity. The method demonstrated the ability to quantify emissions as low as 0.08 g s⁻¹ with approximately 4% error, given sufficient sampling. These findings suggest that the proposed UAV-based system is a promising, cost-effective tool for accurate CH₄ emission quantification in sectors, such as agriculture, energy, and waste management, where traditional monitoring techniques may be impractical or limited. Full article

Visual–Inertial Odometry (VIO) algorithms are widely adopted for autonomous drone navigation in GNSS-denied environments. However, conventional monocular and stereo VIO setups often lack robustness under challenging environmental conditions or during aggressive maneuvers, due to the sensitivity of visual information to lighting, texture, and motion blur. In this work, we enhance an existing open-source VIO algorithm to improve both the robustness and accuracy of the pose estimation. First, we integrate an IMU-based motion prediction module to improve feature tracking across frames, particularly during high-speed movements. Second, we extend the algorithm to support a multi-camera setup, which significantly improves tracking performance in low-texture environments. Finally, to reduce the computational complexity, we introduce an adaptive feature selection strategy that dynamically adjusts the detection thresholds according to the number of detected features. Experimental results validate the proposed approaches, demonstrating notable improvements in both accuracy and robustness across a range of challenging scenarios. Full article

Addressing the significant challenge of speech enhancement in ultra-low-Signal-to-Noise-Ratio (SNR) scenarios for Unmanned Aerial Vehicle (UAV) voice communication, particularly under edge deployment constraints, this study proposes the Edge-Deployed Band-Split Rotary Position Encoding Transformer (Edge-BS-RoFormer), a novel, lightweight band-split rotary position encoding transformer. While existing deep learning methods face limitations in dynamic UAV noise suppression under such constraints, including insufficient harmonic modeling and high computational complexity, the proposed Edge-BS-RoFormer distinctively synergizes a band-split strategy for fine-grained spectral processing, a dual-dimension Rotary Position Encoding ($\mathrm{RoPE}$) mechanism for superior joint time–frequency modeling, and $\mathrm{FlashAttention}$ to optimize computational efficiency, pivotal for its lightweight nature and robust ultra-low-SNR performance. Experiments on our self-constructed DroneNoise-LibriMix (DN-LM) dataset demonstrate Edge-BS-RoFormer’s superiority. Under a −15 dB SNR, it achieves Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) improvements of 2.2 dB over Deep Complex U-Net (DCUNet), 25.0 dB over the Dual-Path Transformer Network (DPTNet), and 2.3 dB over HTDemucs. Correspondingly, the Perceptual Evaluation of Speech Quality (PESQ) is enhanced by 0.11, 0.18, and 0.15, respectively. Crucially, its efficacy for edge deployment is substantiated by a minimal model storage of 8.534 MB, 11.617 GFLOPs (an 89.6% reduction vs. DCUNet), a runtime memory footprint of under 500MB, a Real-Time Factor (RTF) of 0.325 (latency: 330.830 ms), and a power consumption of 6.536 W on an NVIDIA Jetson AGX Xavier, fulfilling real-time processing demands. This study delivers a validated lightweight solution, exemplified by its minimal computational overhead and real-time edge inference capability, for effective speech enhancement in complex UAV acoustic scenarios, including dynamic noise conditions. Furthermore, the open-sourced dataset and model contribute to advancing research and establishing standardized evaluation frameworks in this domain. Full article