Search Results (455)

The integration of large models and multimodal foundation models into the low-altitude economy is driving a transformative shift, enabling intelligent, autonomous, and efficient operations for low-altitude vehicles (LAVs). This article provides a comprehensive analysis of the role these large models play within the smart integrated lower airspace system (SILAS), focusing on their applications across the four fundamental networks: facility, information, air route, and service. Our analysis yields several key findings, which pave the way for enhancing the application of large models in the low-altitude economy. By leveraging advanced capabilities in perception, reasoning, and interaction, large models are demonstrated to enhance critical functions such as high-precision remote sensing interpretation, robust meteorological forecasting, reliable visual localization, intelligent path planning, and collaborative multi-agent decision-making. Furthermore, we find that the integration of these models with key enabling technologies, including edge computing, sixth-generation (6G) communication networks, and integrated sensing and communication (ISAC), effectively addresses challenges related to real-time processing, resource constraints, and dynamic operational environments. Significant challenges, including sustainable operation under severe resource limitations, data security, network resilience, and system interoperability, are examined alongside potential solutions. Based on our survey, we discuss future research directions, such as the development of specialized low-altitude models, high-efficiency deployment paradigms, advanced multimodal fusion, and the establishment of trustworthy distributed intelligence frameworks. This survey offers a forward-looking perspective on this rapidly evolving field and underscores the pivotal role of large models in unlocking the full potential of the next-generation low-altitude economy. Full article

Wild ginkgo, as an endangered species, holds significant value for genetic resource conservation, yet its practical applications face numerous challenges. Traditional field surveys are inefficient in mountainous mixed forests, while satellite remote sensing is limited by spatial resolution. Current deep learning approaches relying on single-source data or merely simple multi-source fusion fail to fully exploit information, leading to suboptimal recognition performance. This study presents a multimodal ginkgo crown dataset, comprising RGB and multispectral images acquired by an UAV platform. To achieve precise crown segmentation with this data, we propose a novel dual-branch dynamic weighting fusion network, termed dual-branch cross-modal attention-enhanced UNet (DCA-UNet). We design a dual-branch encoder (DBE) with a two-stream architecture for independent feature extraction from each modality. We further develop a cross-modal interaction fusion module (CIF), employing cross-modal attention and learnable dynamic weights to boost multi-source information fusion. Additionally, we introduce an attention-enhanced decoder (AED) that combines progressive upsampling with a hybrid channel-spatial attention mechanism, thereby effectively utilizing multi-scale features and enhancing boundary semantic consistency. Evaluation on the ginkgo dataset demonstrates that DCA-UNet achieves a segmentation performance of 93.42% IoU (Intersection over Union), 96.82% PA (Pixel Accuracy), 96.38% Precision, and 96.60% F1-score. These results outperform differential feature attention fusion network (DFAFNet) by 12.19%, 6.37%, 4.62%, and 6.95%, respectively, and surpasses the single-modality baselines (RGB or multispectral) in all metrics. Superior performance on cross-flight-altitude data further validates the model’s strong generalization capability and robustness in complex scenarios. These results demonstrate the superiority of DCA-UNet in UAV-based multimodal ginkgo crown recognition, offering a reliable and efficient solution for monitoring wild endangered tree species. Full article

Shipborne UAV-assisted dock is an important way to recover unmanned systems for remote water surface low-altitude detection. The lack of resisting deck disturbances capability for UAV autonomous landing in dynamic dock stations has led to the inability of traditional hovering recovery methods for single UAV guidance and flight attitude control systems to meet the growing demand for landing assistance. In this work, we present a shipborne manipulator arm designed to grasp drones that use low-altitude visual servo technology for landing on the water surface. The shipborne manipulator arm is fabricated as a key component of a seaplane drone dock comprising a ship-type embedded drone storage, a packaged helistop for power transfer and UAV recovery, and a multi-degree-of-freedom arm integrated with multi-source information sensors for the treatment of air-to-water-related airplane crashes. Dynamic model tests have demonstrated that the end-effector of the shipborne manipulator arm stabilizes and performs optimally for water surface disturbances. A down-to-top grasp docking paradigm for a UAV-assisted perching on a shipborne helistop that enables the charging components of the station system to be equipped automatically to ensure that the drone performs its mission in the best condition is also presented. The surface grasp experiments have verified the efficacy of this grasp paradigm when compared to the traditional autonomous landing method. Full article

In view of the complex flight scenarios existing in UAV path planning, it is necessary to model the UAV flight trajectory. When constructing the model, cost factors such as the minimum flight path of the UAV, obstacle avoidance, flight altitude, and trajectory smoothness are fully taken into account. To reduce the overall flight cost, a novel secretary bird optimization algorithm (NSBOA) is proposed in this paper, which effectively addresses the limitations of traditional algorithms in handling UAV path planning tasks. First of all, the Singer chaotic map is adopted to initialize the population instead of the conventional random initialization method. This improvement increases population diversity, enables the initial population to be more evenly distributed in the search space, and further accelerates the algorithm’s convergence speed in the subsequent optimization process. Second, an adaptive adjustment mechanism is integrated with the Levy flight mechanism to optimize the core logic of the algorithm, with a specific focus on improving the exploitation stage. By introducing appropriate perturbations near the current optimal solution, the algorithm is guided to jump out of local optimal traps, thereby enhancing its global optimization capability and avoiding premature convergence caused by insufficient population diversity. By comparing and analyzing NSBOA with SBOA, WOA, PSO, POA, NGO, and HHO algorithms in 12 common evaluation functions and CEC 2017 test functions, and applying NSBOA to the UAV path optimization problem, the simulation results show the effectiveness and superiority of the proposed scheme. Full article

This study proposes a lightweight framework for transferring pretrained land cover classification architectures without additional training. The system utilizes French IGN imagery and Korean UAV and aerial imagery. It employs FLAIR U-Net models with ResNet34 and MiTB5 backbones, along with the AI-HUB U-Net. The implementation consists of four sequential stages. First, we perform class mapping between heterogeneous schemes and unify coordinate systems. Second, a quadratic polynomial regression equation is constructed. This formula uses multispectral band statistics as hyperparameters and class-wise IoU as the dependent variable. Third, optimal parameters are identified using the stationary point condition of Response Surface Methodology (RSM). Fourth, the final land cover map is generated by fusing class-wise optimal results at the pixel level. Experimental results show that optimization is typically completed within 60 inferences. This procedure achieves IoU improvements of up to 67.86 percentage points compared to the baseline. For automated application, these optimized values from a source domain are successfully transferred to target areas. This includes transfers between high-altitude mountainous and low-lying coastal territories via proportional mapping. This capability demonstrates cross-regional and cross-platform generalization between ResNet34 and MiTB5. Statistical validation confirmed that the performance surface followed a systematic quadratic response. Adjusted R² values ranged from 0.706 to 0.999, with all p-values below 0.001. Consequently, the performance function is universally applicable across diverse geographic zones, spectral distributions, spatial resolutions, sensors, neural networks, and land cover classes. This approach achieves more than a 4000-fold reduction in computational resources compared to full model training, using only 32 to 150 tiles. Furthermore, the proposed technique demonstrates 10–74× superior resource efficiency (resource consumption per unit error reduction) over prior transfer learning schemes. Finally, this study presents a practical solution for inference and performance optimization of land cover semantic segmentation on standard commodity CPUs, while maintaining equivalent or superior IoU. Full article

For UAVs, the industry currently relies on expensive sensors for obstacle avoidance. A significant challenge arises from the scarcity of high-quality depth estimation datasets tailored for low-altitude environments, which hinders the advancement of self-supervised learning methods in these settings. Furthermore, mainstream depth estimation models capable of achieving obstacle avoidance through image recognition are built upon convolutional neural networks or hybrid Transformers. Their high computational costs make deployment on resource-constrained edge devices challenging. While existing lightweight convolutional networks reduce parameter counts, they struggle to simultaneously capture essential features and fine details in complex scenes. In this work, we introduce LFP-Mono as a lightweight self-supervised monocular depth estimation network. In the paper, we will detail the Pooling Convolution Downsampling (PCD) module, Continuously Dilated and Weighted Convolution (CDWC) module, and Cross-level Feature Integration (CFI) module. All results show that LFP-Mono outperforms existing lightweight methods on the KITTI benchmark, and by evaluating with the Make3D dataset, show that our method generalizes outdoors. Finally, by training and testing on the Syndrone dataset, baseline work shows that LFP-Mono exceeds state-of-the-art methods for low-altitude drone performance. Full article

Low-altitude Unmanned Aerial Vehicle (UAV) detection using LiDAR range images faces persistent challenges. These include sparse features for long-range targets, large scale variations caused by viewpoint changes, and severe interference from complex backgrounds. To address these issues, we propose an improved detection framework based on YOLOv10. First, we design a Swin-Conv hybrid module that combines sparse attention with deformable convolution. This module enables the network to focus on informative regions and adapt to target geometry. These capabilities jointly strengthen feature extraction for sparse, long-range targets. Second, we introduce Attentional Feature Fusion (AFF) in the neck to replace naïve feature concatenation. AFF employs multi-scale channel attention to softly select and adaptively weight features from different levels, improving robustness to multi-scale targets. In addition, we systematically study how the viewpoint distribution in the training set affects performance. The results show that moderately increasing the proportion of low-elevation-view samples significantly improves detection accuracy. Experiments on a self-built simulated LiDAR range-image dataset demonstrate that our method achieves 88.96% mAP at 54.2 FPS, which is 4.78 percentage points higher than the baseline. Deployment on the Jetson Orin Nano edge device further validates the model’s potential for real-time applications. The proposed method remains robust under noise and complex backgrounds. The proposed approach achieves an effective balance between detection accuracy and computational efficiency, providing a reliable solution for real-time target detection in complex low-altitude environments. Full article

Due to emerging strategic demands, this article presents a comprehensive conceptual design investigation into enhancing the MQ-9A Uncrewed Aerial Vehicle (UAV). Motivated by the need for persistent long-range protection and surveillance capabilities, the research study proposes three primary modifications to create an aircraft titled the MQ-9X Raven. First, the existing turboprop engine was replaced with the widely used Williams FJ44-4A turbofan for reduced fuel consumption and excess power at 50,000 ft, with a range of approximately 8000 nm. Second, the wing design was updated with a 79 ft wing for a greater aspect ratio and a new LRN1015 airfoil to enable high-altitude, long-endurance standoff of around 24 h. Third and finally, the conceptual redesign included integration of a releasable store for maritime interdiction (AGM-184). The project follows a rigorous methodology beginning with a redefinition of mission requirements, aerodynamic, thrust, and stability analysis, and then verification with flight simulation, computational fluid dynamics, and wind tunnel experiments. Our analysis shows the MQ-9X Raven is highly suitable for the task of pervasive high-altitude standoff maritime protection. Full article

In January 2025, multiple wildfires erupted across the Los Angeles region, fueled by prolonged dry conditions and intense Santa Ana winds. Southern California has faced increasingly frequent and severe wildfires in recent years, driven by prolonged drought, high temperatures, and the expanding wildland–urban interface. These fires have caused major loss of life, extensive property damage, mass evacuations, and severe air-quality decline in this densely populated, high-risk region. This study integrates passive and active satellite observations to characterize the spatiotemporal and vertical distribution of wildfire emissions and assesses their impact on air quality. TROPOMI (Sentinel-5P) and the recently launched TEMPO geostationary instrument provide hourly high temporal-resolution mapping of trace gases, including nitrogen dioxide (NO₂), carbon monoxide (CO), formaldehyde (HCHO), and aerosols. Vertical column densities of NO₂ and HCHO reached 40 and 25 Pmolec/cm², respectively, representing more than a 250% increase compared to background climatological levels in fire-affected zones. TEMPO’s unique high-frequency observations captured strong diurnal variability and secondary photochemical production, offering unprecedented insights into plume evolution on sub-daily scales. ATLID (EarthCARE) lidar profiling identified smoke layers concentrated between 1 and 3 km altitude, with optical properties characteristic of fresh biomass burning and depolarization ratios indicating mixed particle morphology. Vertical profiling capability was critical for distinguishing transported smoke from boundary-layer pollution and assessing radiative impacts. These findings highlight the value of combined passive–active satellite measurements in capturing wildfire plumes and the need for integrated monitoring as wildfire risk grows under climate change. Full article

Vehicle detection from unmanned aerial vehicles (UAVs) has gained increasing attention due to the growing availability and accessibility of these platforms. UAV-captured videos have proven valuable in a variety of applications, including agriculture, security, and search and rescue operations. To support research in UAV-based vehicle detection, this paper introduces UTUAV: Urban Traffic Unmanned Aerial Vehicle, a dataset composed of traffic video images collected over the streets of Medellín, Colombia. The images are recorded from a semi-static position at two different altitudes (100 and 120 m) and include three manually annotated vehicle types: cars, motorcycles, and large vehicles. The analysis focuses on the main characteristics and challenges presented in the dataset. In particular, data leakage occurs when a single video is used to construct the training, validation, and evaluation sets. An inadequate data split can result in highly similar samples leaking into the evaluation set, leading to inflated performance metrics that do not reflect a model’s true generalization ability. Additionally, baseline results from recent state-of-the-art object detection models based on CNNs and Transformers (YOLOv8, YOLOv11, YOLOv12 and RT-DETR) are presented. The experiments highlight several challenges, including the difficulty of detecting small-scale objects, especially motorcycles, and limited generalization capabilities under altitude changes, a phenomenon commonly referred to as domain shift. Full article

Unique skin microbial communities have been shaped by the harsh climatic conditions in high-altitude areas, such as intense ultraviolet radiation and low oxygen concentration. However, it is unknown whether high altitude contributes to shaping common microbiota inhabiting the skin across different mammals. The skin microbial communities of humans and horses living in high-altitude (Tibetan) and low-altitude areas were analyzed using full-length 16S rRNA sequencing technology. Alpha diversity differed between high- and low-altitude groups (p < 0.01). Skin microbial community composition also differed between high- and low-altitude areas (p < 0.05). Some of the common taxa present in the skin of humans and horses in high-altitude areas were identified as extreme microorganisms capable of adapting to the harsh high-altitude environment. Five bacterial taxa, including the genera Sphingomonas, Brevundimonas, and Kocuria, as well as the species Acinetobacter guillouiae and Arboricoccus pini, were significantly enriched (p < 0.01) on the skin of both humans and horses in high-altitude areas. Meanwhile, some taxa enriched on the skin surface at the same altitude showed preferences for mammalian species. Acinetobacter johnsonii, Anaerococcus nagyae, and Anaerococcus octavius were significantly enriched (p < 0.05) in the skin of humans at both high and low altitudes, whereas Acinetobacter pseudolwoffii and Armatimonas rosea, Archangium gephyra and Acinetobacter lwoffii were significantly enriched (p < 0.05) in the skin of horses at both high and low altitudes. In the network analyses, a positive correlation (p < 0.01) was shown between the skin taxa enriched in high-altitude areas and each other, while a negative correlation (p < 0.01) was found between the skin microorganisms enriched in high-altitude areas and those enriched in low-altitude areas. Overall, our findings indicate that high-altitude extreme environments drive convergent evolution of skin microbiota across mammals, reflecting the joint effects of environmental selection and host-related filtering on community assembly. This cross-species comparison provides a framework for understanding skin microbiome responses to extreme environments in plateau mammals. Full article

The integration of terrestrial and aerial components in future wireless networks is a key enabler for achieving wide-area coverage and providing ubiquitous services. In this context, and with the goal of enhancing spectral efficiency through opportunistic spectrum reuse, this paper investigates a cooperative spectrum sensing approach in which cognitive UAVs equipped with full-duplex (FD) MIMO technology operate as aerial base stations (ABS). Each UAV performs local detection using the sphericity test, then a push–sum consensus protocol is employed to fuse local test statistics without relying on a fusion center. Unlike conventional unweighted consensus or centralized hard-decision fusion, the proposed approach accounts for the heterogeneity introduced by residual self-interference in FD transceivers. Specifically, multipath in the self-interference channel induces temporal correlation, increasing the variance of the local test statistic and, consequently, the false-alarm probability. To mitigate this effect, we design variance-aware consensus weights proportional to the inverse of the sphericity test variance enhancing robustness to RSI-induced variability. Numerical results demonstrate that the proposed scheme outperforms both unweighted consensus and centralized OR-rule fusion in user capacity, while maintaining negligible communication overhead. Moreover, the operational altitude of the UAVs is evaluated to balance the coverage provided to users and the primary signal detection capability. Full article

Due to the recent improvement in the additive manufacturing field, aerospike engines have been reconsidered as a possible alternative to the traditional bell-shaped nozzles. The former offer higher thrust and specific impulse during the launcher ascension phase because they are theoretically able to adapt the gas expansion ratio, reaching the optimal condition for a wide range of ambient pressure values, while bell-shaped nozzles can achieve the optimal expansion condition only at the design altitude. This capability has been proved for full-length plug nozzles, which, however, have some drawbacks, like a low thrust-to-weight ratio and challenging design of the cooling system at the spike tip. Therefore, research is moving towards truncated spike geometries, which allow the previously mentioned issues to be overcome. The aim of this work is to verify the expansion adaptation ability of a specific truncated aerospike geometry at different ambient pressures and to develop a simplified theory to estimate the upper bound of the base thrust coefficient. The analysis has been addressed by running numerical fluid dynamics simulations performed with an OpenFOAM solver. Full article

Land surface temperature (LST) is an important indicator of ecosystem sustainability and climate change resilience, particularly in highland watersheds characterized by fast land use and land cover (LULC) changes. In this research, the LST dynamics of the Laut Tawar Sub-watershed, Central Aceh, Indonesia, were investigated, based on Landsat 9 OLI/TIRS 2024 imagery. Supervised classification identified eight land cover categories, and their thermal contrasts were evident: built-up and plantation zones exhibited the highest LST values (25–32 °C), while water bodies and forests acted as natural coolers (9.5–17 °C), with elevation further modulating these patterns by creating cooler microclimates at higher altitudes (>2000 m), highlighting the impact of topography in generating microclimatic diversity. Intermediate values were shown for the moderate and sparse forest areas, which thus worked as transition zones with low cooling capabilities. Natural land covers contributed to thermal regulation, whereas built-up and agricultural expansion exacerbated surface heat and possible urban heat island (UHI) effects. This research highlights the importance of protecting forests and water bodies, controlling land conversion, and applying targeted green infrastructure informed by the thermal disparities and land cover dynamics observed. Full article

Detecting low-altitude, slow-speed, small (LSS) UAVs is especially challenging in low-visibility scenes (low light, haze, motion blur), where inherent uncertainties in sensor data and object appearance dominate. We propose GAME-YOLO, a novel detector that integrates a Bayesian-inspired probabilistic reasoning framework with Global Attention and Multi-Scale Enhancement to improve small-object perception and sub-pixel-level localization. Built on YOLOv11, our framework comprises: (i) a visibility restoration front-end that probabilistically infers and enhances latent image clarity; (ii) a global-attention-augmented backbone that performs context-aware feature selection; (iii) an adaptive multi-scale fusion neck that dynamically weights feature contributions; (iv) a sub-pixel-aware small-object detection head (SOH) that leverages high-resolution feature grids to model sub-pixel offsets; and (v) a novel Shape-Aware IoU loss combined with focal loss. Extensive experiments on the LSS2025-DET dataset demonstrate that GAME-YOLO achieves state-of-the-art performance, with an AP@50 of 52.0% and AP@[0.50:0.95] of 32.0%, significantly outperforming strong baselines such as LEAF-YOLO (48.3% AP@50) and YOLOv11 (36.2% AP@50). The model maintains high efficiency, operating at 48 FPS with only 7.6 M parameters and 19.6 GFLOPs. Ablation studies confirm the complementary gains from our probabilistic design choices, including a +10.5 pp improvement in AP@50 over the baseline. Cross-dataset evaluation on VisDrone-DET2021 further validates its generalization capability, achieving 39.2% AP@50. These results indicate that GAME-YOLO offers a practical and reliable solution for vision-based UAV surveillance by effectively marrying the efficiency of deterministic detectors with the robustness principles of Bayesian inference. Full article