Search Results (332)

Small object detection in remote sensing images provides significant value for urban monitoring, aerospace reconnaissance, and other fields. However, detection accuracy still faces multiple challenges including limited target information, weak feature representation, and complex backgrounds. This research aims to improve the performance of the YOLO11 model for small object detection in remote sensing imagery by addressing key issues in long-distance spatial dependency modeling, multi-scale feature adaptive fusion, and computational efficiency. We constructed a specialized Remote Sensing Airport-Plane Detection (RS-APD) dataset and used the public VisDrone2019 dataset for generalization verification. Based on the YOLO11 architecture, we proposed the DAE-YOLO model with three innovative modules: Dynamic Spatial Sequence Module (DSSM) for enhanced long-distance spatial dependency capture; Adaptive Multi-scale Feature Enhancement (AMFE) for multi-scale feature adaptive receptive field adjustment; and Efficient Dual-level Attention Mechanism (EDAM) to reduce computational complexity while maintaining feature expression capability. Experimental results demonstrate that compared to the baseline YOLO11, our proposed model improved mAP₅₀ and mAP_50:95 on the RS-APD dataset by 2.1% and 2.5%, respectively, with AP_s increasing by 2.8%. This research provides an efficient and reliable small object detection solution for remote sensing applications. Full article

This study presents a comparative analysis of two rare thundersnow events accompanied by snowfall that occurred on 11 November 2023 and 10 December 2023 in Shaanxi province, China. Multiple data sources were integrated, including MICAPS surface and upper-air conventional detection observations, hourly meteorological records from Yanliang Airport, lightning location data, and ERA5 reanalysis, to examine and contrast the synoptic conditions, moisture transport mechanisms, and convective characteristics underlying these two events. The results indicate that the large-scale circulation patterns were characterized by a “high in the west and low in the east” configuration and a “two troughs-one ridge” pattern for the November and December cases, respectively. In both episodes, Shaanxi Province was located on the rear side of a high-pressure ridge, where a strong pressure gradient induced pronounced northerly winds that advected cold air southward, forming a distinct near-surface cold pool. During the November event, the convective cloud system developed east of the Tibetan plateau, guided by a westerly flow, and propagated eastward while gradually weakening, with a minimum brightness temperature of −42 °C. Conversely, in December, the convective activity initiated over southwestern Shaanxi and moved northeastward under a southwesterly flow, reaching a lower minimum brightness temperature of −55 °C, indicative of stronger vertical development. In both events, the principal water vapor transport occurred near the 700 hPa height level and was primarily sourced from the Bay of Bengal via a southwesterly flow. The November event featured a stronger northwesterly cold-air intrusion, whereas the December case exhibited a broader moisture channel. The CAPE values peaked during the afternoon and nighttime periods in both cases. The cold-pool and inversion-layer thickness were approximately 2 km/45 hPa in November and 0.8 km/150 hPa in December. Full article

Accurate detection of concealed items in X-ray baggage images is critical for public safety in high-security environments such as airports and railway stations. However, small objects with low material contrast, such as plastic lighters, remain challenging to identify due to background clutter, overlapping contents, and weak edge features. In this paper, we propose a novel architecture called the Contrast-Enhanced Feature Pyramid Network (CE-FPN), designed to be integrated into the YOLO detection framework. CE-FPN introduces a contrast-guided multi-branch fusion module that enhances small-object representations by emphasizing texture boundaries and improving semantic consistency across feature levels. When incorporated into YOLO, the proposed CE-FPN significantly boosts detection accuracy on the HiXray dataset, achieving up to a +10.1% improvement in mAP@50 for the nonmetallic lighter class and an overall +1.6% gain, while maintaining low computational overhead. In addition, the model attains a mAP@50 of 84.0% under low-resolution settings and 87.1% under high-resolution settings, further demonstrating its robustness across different input qualities. These results demonstrate that CE-FPN effectively enhances YOLO’s capability in detecting small and concealed objects, making it a promising solution for real-world security inspection applications. Full article

The accurate extraction of damage information around airport runways is crucial for the rapid development of subsequent damage effect assessment work and the timely formulation of the ensuing operational plan. However, the presence of dark interference areas such as trees and shadows in the background, as well as the increased irregularity at the edge of the crater due to the proximity to the crater, pose challenges to the accurate extraction of the crater area in high entropy images. In this paper, we present a multi-feature fusion-based two-stage method for airport crater extraction from remote sensing images. In stage I, we designed an edge arc segment grouping and matching strategy based on the shape characteristics of craters for preliminary detection. In stage II, we established a crater model based on the regional distribution characteristics of craters and used the marked point processing method for crater detection. In addition, during the step of calculating the magnitude of the edge gradient, we proposed a near-region search strategy, which enhanced the ability of the proposed method to accurately extract craters with irregular shapes. In the test images, the proposed method accurately extracts craters located around and within the runways. Among them, the average recall R and precision P of the proposed method for extracting all craters around the airport runways reached 89% and 87%, respectively, and the average recall R and precision P of the proposed method for extracting craters inside the runways reached 94% and 92%, respectively. Meanwhile, the results of comparative tests showed that our method outperformed other representative algorithms in terms of both crater extraction recall and extraction precision. Full article

Detecting aircraft in Airport Surface Movement Radar (SMR) imagery presents a unique challenge rooted in the conflict between object symmetry and data asymmetry. While aircraft possess strong structural symmetry, their radar signatures are often sparse, incomplete, and highly asymmetric, leading to target loss and position jitter in traditional detection algorithms. To overcome this, we introduce SWCR-YOLO, a keypoint detection framework designed to learn and enforce the target’s implicit structural symmetry from its imperfect radar representation. Our model reconstructs a stable aircraft pose by localizing four keypoints (nose, tail, wingtips) that define its symmetric axes. Based on YOLOv11n, SWCR-YOLO incorporates a MultiScaleStem module and wavelet transforms to effectively extract features from the sparse, asymmetric scatter points, while a Multi-Scale Convolutional Attention (MSCA) module refines salient information. Crucially, training is guided by a Geometric Regularized Keypoint Loss (GRKLoss), which introduces a symmetry-based prior by imposing angular constraints on the keypoints to ensure physically plausible pose estimations. Our symmetry-aware approach, on a real-world SMR dataset, achieves an mAP50 of 88.2% and reduces the trajectory root mean square error by 51.8% compared to MTD-CFAR pipeline methods, from 8.235 m to 3.968 m, demonstrating its effectiveness in handling asymmetric data for robust object tracking. Full article

This work addresses computational inefficiency in ultra-wide-area remote sensing image (RSI) object detection. Traditional homogeneous tiling strategies enforce computational symmetry by processing all image regions uniformly, ignoring the intrinsic spatial asymmetry of target distribution where target-dense coexist with vast target-sparse areas (e.g., deserts, farmlands), thereby wasting computational resources. To overcome symmetry mismatch, we propose a heat-guided adaptive blocking and dual-model collaboration (HAB-DMC) framework. First, a lightweight EfficientNetV2 classifies initial 1024 × 1024 tiles into semantic scenes (e.g., airports, forests). A target-scene relevance metric converts scene probabilities into a heatmap, identifying high-attention regions (HARs, e.g., airports) and low-attention regions (LARs, e.g., forests). HARs undergo fine-grained tiling (640 × 640 with 20% overlap) to preserve small targets, while LARs use coarse tiling (1024 × 1024) to minimize processing. Crucially, a dual-model strategy deploys: (1) a high-precision LSK-RTDETR-base detector (with Large Selective Kernel backbone) for HARs to capture multi-scale features, and (2) a streamlined LSK-RTDETR-lite detector for LARs to accelerate inference. Experiments show 23.9% faster inference on 30k-pixel images and reduction in invalid computations by 72.8% (from 50% to 13.6%) versus traditional methods, while maintaining competitive mAP (74.2%). The key innovation lies in repurposing heatmaps from localization tools to dynamic computation schedulers, enabling system-level efficiency for Ultra-Wide-Area RSIs. Full article

The article proposes a concept for a mobile robot designed to detect hazardous and explosive materials in airport parking lots. The problem with operating such a robot is twofold. Firstly, it must move in a dynamic environment, between vehicles that are parked or also in motion, but without stopping vehicles that are in motion. The second problem is the detection of hazardous and explosive materials. For robot mobility solutions, an obstacle analysis system based on popular, low-cost LIDAR sensors and cameras was proposed. For the detection of hazardous and explosive materials, a dual vehicle monitoring system was proposed for airport parking lots. The first is based on vision techniques, where cameras and image recognition procedures are used to examine the undercarriages of parked vehicles. This system is designed to detect unusual objects mounted on vehicle undercarriages. The second is based on the analysis of volatile substances produced by explosives and hazardous materials found under or inside car chassis and gasoline and oils. The aim of the project is to develop a functional prototype of such a robot and describe its capabilities. The article describes the preliminary findings of the research. Full article

Soil biodiversity is crucial for maintaining biological soil resilience, understood as a temporal property and as the ability of soils to uphold or recover their ecological functions under stress thanks to the diversity and complementarity of their biological communities. To evaluate this property, we developed the Biological Soil Resilience Index (BSR), conceived as an evolution of the QBS-ar approach by integrating additional key bioindicators—entomopathogenic nematodes, entomopathogenic fungi, and earthworms—together with microarthropod eco-morphological adaptation scores. This multi-taxon framework provides a more comprehensive assessment of soil biological conditions than single-group indices and is specifically designed to be applied repeatedly over time to detect resilience trajectories. The Biodiversity Soil Resilience (BSR) Index was applied across nine sites subject to low, medium, and high anthropogenic disturbance, spanning urban, industrial, and airport environments. Results revealed not a resilience gradient but a clear disturbance gradient: low-impact sites achieved the highest BSR values (52–59), reflecting diverse and functionally complementary assemblages; medium-impact sites maintained moderate BSR value (27–42), but displayed imbalances among faunal groups; and high-impact sites showed the lowest values, including a critically low score at C_HI (17.86), where entomopathogens were absent and earthworm populations reduced. Entomopathogenic organisms proved particularly sensitive, disappearing entirely under severe disturbance. The BSR was sensitive to environmental gradients and effective in distinguishing ecologically meaningful differences among soil communities. Because it can be repeatedly applied over time, BSR provides the basis for monitoring long-term resilience dynamics, detecting early warning signals, and support timely mitigation or restoration measures. Overall, the study highlights the pivotal role of biodiversity in sustaining soil resilience and supports the BSR Index as a simple yet integrative tool for soil health assessment and for future resilience monitoring in disturbed landscapes. Full article

This paper presents a markerless augmented reality (AR) navigation system for guiding users across a university campus, independent of internet or wireless connectivity, integrating machine learning (ML) and deep learning techniques. The system employs computer vision to detect campus signage “Meeting Point” and “Directory”, and classifies them through a binary classifier (BC) and convolutional neural networks (CNNs). The BC distinguishes between the two types of signs using RGB values with algorithms such as Perceptron, Bayesian classification, and k-Nearest Neighbors (KNN), while the CNN identifies the specific sign ID to link it to a campus location. Navigation routes are generated with the Floyd–Warshall algorithm, which computes the shortest path between nodes on a digital campus map. Directional arrows are then overlaid in AR on the user’s device via ARCore, updated every 200 milliseconds using sensor data and direction vectors. The prototype, developed in Android Studio, achieved over 99.5% accuracy with CNNs and 100% accuracy with the BC, even when signs were worn or partially occluded. A usability study with 27 participants showed that 85.2% successfully reached their destinations, with more than half rating the system as easy or very easy to use. Users also expressed strong interest in extending the application to other environments, such as shopping malls or airports. Overall, the solution is lightweight, scalable, and sustainable, requiring no additional infrastructure beyond existing campus signage. Full article

This paper reports on the study of turbulence at various locations in Hong Kong during Typhoon Wipha in July 2025, including turbulence intensity based on Doppler Light Detection and Ranging (LIDAR) systems and radiosondes, observations by microclimate stations, and low-level windshear and turbulence at the Hong Kong International Airport (HKIA) by LIDAR, flight data, and pilot reports. Although the observation period was primarily limited to 20 July 2025, passage of a typhoon over a densely instrumented urban area is uncommon; these observations on turbulent flow associated with typhoons therefore can serve as valuable benchmarks for similar studies on turbulent flow associated with typhoons in other coastal areas, particularly for operational alerts in aviation. To assess the predictability of turbulence, the eddy dissipation rate (EDR) was derived from a high-resolution numerical weather prediction (NWP) model using diagnostic and reconstruction approaches. Compared with radiosonde data, both approaches performed similarly in the shear-dominated low-level atmosphere, while the diagnostic approach outperformed when buoyancy became important. This result highlights the importance of incorporating buoyancy effects in the reconstruction approach if the EDR diagnostic is not available. The high-resolution NWP was also used to provide time-varying boundary conditions for computational fluid dynamics simulations in urban areas, and its limitations were discussed. This study also demonstrated the difficulty of capturing low-level windshear encountered by departing aircraft in an operational environment and demonstrated that a trajectory-aware method for deriving headwind could align more closely with onboard measurements than the standard fixed-path product. Full article

Cities are major sources of anthropogenic carbon dioxide (CO₂) emissions, making the study of intra-urban CO₂ concentration patterns an emerging research priority. However, limited data availability and the complexity of urban environments have impeded detailed spatiotemporal analyses at the city scale. To address these challenges, an analysis supported by multi-source data and GeoAI methods is carried out to examine the spatial distribution, vertical variation, temporal dynamics, and driving factors of CO₂ concentrations in urban areas. We combined OCO-2 satellite-derived XCO₂ data (2014–2024) with ground-based measurements from the Shanghai Tower (August 2024 to March 2025), alongside meteorological and socioeconomic variables. The analysis employed spatial interpolation (inverse distance weighting), nonparametric testing (Mann–Whitney U test), time series decomposition, ordinary least squares (OLS) regression, and machine learning techniques including random forest and SHAP (SHapley Additive exPlanations) analysis. Results reveal that CO₂ concentrations are significantly higher in central urban districts compared to suburban areas, with notable spatial heterogeneity. Elevated levels were detected near ports and ferry routes, with airports and industrial emissions identified as principal contributors. Vertically, CO₂ concentrations decline with increasing altitude but exhibit a peak at mid-level heights. Temporally, a pronounced seasonal pattern was observed, characterized by higher concentrations in winter and lower levels in summer. Both OLS regression and machine learning models highlight proximity to emission sources, wind speed, and temperature as key determinants of spatial CO₂ variability, with these factors collectively explaining 67% of the variance in OLS models. This study demonstrates how multi-source data and advanced methods can capture the spatial, vertical, and seasonal dynamics and driving factors of urban CO₂ concentrations, offering insights for policy, planning, and mitigation. Full article

Airport pavement condition assessment plays a critical role in ensuring operational safety, surface functionality, and long-term infrastructure sustainability. Traditional visual inspection methods, although widely used, are increasingly challenged by limitations in accuracy, subjectivity, and scalability. In response, the field has seen a growing adoption of automated and intelligent inspection technologies, incorporating tools such as unmanned aerial vehicles (UAVs), Laser Crack Measurement Systems (LCMS), and machine learning algorithms. This systematic review aims to identify, categorize, and analyze the main technological approaches applied to functional pavement inspections, with a particular focus on surface distress detection. The study examines data collection techniques, processing methods, and validation procedures used in assessing both flexible and rigid airport pavements. Special emphasis is placed on the precision, applicability, and robustness of automated systems in comparison to traditional approaches. The reviewed literature reveals a consistent trend toward greater accuracy and efficiency in systems that integrate deep learning, photogrammetry, and predictive modeling. However, the absence of standardized validation protocols and statistically robust datasets continues to hinder comparability and broader implementation. By mapping existing technologies, identifying methodological gaps, and proposing strategic research directions, this review provides a comprehensive foundation for the development of scalable, data-driven airport pavement management systems. Full article

Unmanned aerial vehicle (UAV) intrusions cause flight delays and disrupt airport operations, so accurate monitoring is essential for safety. To address the scarcity and mismatch of real-world training data in small-target detection, an anti-UAV approach is proposed that integrates style transfer learning (STL) with deep learning. An airport monitoring platform is established to acquire a real UAV dataset, and a Cycle-Consistent Generative Adversarial Network (CycleGAN) is employed to synthesize multi-scene images that simulate diverse airport backgrounds, thereby enriching the training distribution. Using these simulated scenes, a controlled comparison of YOLOv5/YOLOv6/YOLOv7/YOLOv8 is conducted, in which YOLOv5 achieves the best predictive performance with AP values of 93.95%, 98.09%, and 97.07% across three scenarios. On public UAV datasets, the STL-enhanced model (YOLOv5_STL) is further compared with other small-object detectors and consistently exhibits superior performance, indicating strong cross-scene generalization. Overall, the proposed method provides an economical, real-time solution for airport UAV intrusion prevention while maintaining high accuracy and robustness. Full article

The wake vortex of an aircraft can be hazardous to aviation operations. Therefore, the International Civil Aviation Organization has established requirements regarding the separation of aircraft. In light of the current implementation of regulations, this systematic study was the first of its kind investigating wake vortices of aircraft at the new north runway of Hong Kong International Airport (HKIA). A short-range light detection and ranging (SR-LIDAR) system, previously installed by the Hong Kong Observatory at HKIA, performed range–height indicator scans at the recently commissioned north runway end to capture wake vortices of arriving aircraft. The lifetimes of the wake vortices were calculated, and the exit times of the vortices away from the runway were determined. Based on an analysis of data from a period of approximately eight weeks—mostly during summer with its prevailing southwestern monsoon—it was found that, as in a previous study, the displacement of vortices increased with the radial background velocity. Moreover, approximately 0.6% of aircraft may be susceptible to encountering the vortex left behind by the preceding aircraft. Analysis of data from a second period of approximately four weeks revealed that vortex lifetimes were negatively correlated with the magnitude of the turbulence intensity expressed in terms of the eddy dissipation rate. Correlations with various other meteorological and non-meteorological factors were not apparent. The results of the present study supplement previous work in Hong Kong with a site-specific dataset for the new commissioned north runway, provide validation of established principles with an initial assessment of operational risk of turbulence encounter, and pave the way for longer-term statistical analysis of the behaviour of aircraft wake vortices in the climate of Hong Kong. Full article

Using deep learning in automated pavement distress detection has shown huge improvements for transport infrastructure, but a noticeable challenge remains in distinguishing sealed cracks from active ones, which are more evident in high-resolution aerial imagery of airport pavements. Misclassifying sealed cracks, an indicator of maintenance intervention, as structural distress leads to false positives that cause overestimation in distress metrics and, ultimately, inaccurate Pavement Condition Index (PCI) scores. This study tries to address this limitation by investigating whether explicitly labeling sealed cracks as a separate class during training can improve model performance. In this regard, aerial orthophotos of taxiways from one selected airport, as a case study, were collected via Unmanned aerial vehicle (UAV) surveys, and three instance segmentation models based on YOLOv11 (version 11 from You Only Look Once family) were trained on different datasets: one excluding sealed cracks (including only longitudinal and transvers cracks), one including sealed cracks without explicit labeling, and one treating sealed cracks as a separate class. Validation against ground-truth field surveys revealed that the model trained with explicit sealed crack annotations achieved significantly lower error rates, with a 56.7% reduction for longitudinal cracks and a 75.2% reduction for transverse cracks with respect to traditional detection methods. This improvement led to fewer false positives and a more reliable quantification of both longitudinal and transverse cracking. The results demonstrate that tailored annotation strategies, which in this study means distinguishing sealed cracks, substantially improve the accuracy of deep learning models for real-world pavement condition assessment. Full article