Search Results (239)

Polarimetric reflectance can be described using the Stokes parameters with S₀ representing the total intensity of the light beam reflected from a material, S₁ representing the intensity difference between the horizontally {0°, 180°} and vertically {90°, 270°} linearly polarized components, S₂ representing the intensity difference between the +45° and −45° (or 135°) linearly polarized components, and the Degree of Linear Polarization (DoLP) representing the fraction of light that is linearly polarized. Spectral analyses often fail to distinguish between materials that may be spectrally similar, while polarimetric analyses may be able to enhance the distinction. Prior research has demonstrated the utility of polarization for target detection; however, existing studies rarely compare controlled laboratory polarimetric signatures directly with real-world aerial-field measurements. Furthermore, there is a gap in systematically evaluating how both material physical properties, such as metallic versus dielectric structures, and collection geometries affect polarimetric signatures across multiple wavebands. The objective of this research is to test an approach to measure material, object, and land cover separability in visible (VIS), shortwave infrared (SWIR), and longwave infrared (LWIR) polarimetric laboratory and aerial imagery through complementary laboratory and aerial-field experiments, which may aid in differentiating between spectrally similar man-made materials, objects, and land covers. In this study, sensors measure unpolarized and polarized reflectance responses from man-made materials, objects, and land covers in VIS, SWIR, and LWIR bands in laboratory and aerial field imagery at varying collection geometries. The relationship between laboratory samples and aerial-field-collected imagery of man-made materials, objects, and land covers for S₀, S₁, S₂, and DoLP responses was explored. Results show statistically significant separability by material and collection geometry across Stokes parameters and wavelengths. Post hoc pairwise comparisons showed which materials, objects, and land covers were separable and which collection geometries were separable from each other; however, separability differed between the laboratory and field measurements. Ultimately, this research provides a foundational understanding that can assist with spectropolarimetric data collection planning by demonstrating that overall collection geometry is a critical factor for optimizing material, object, and land cover separability. Future work should focus on isolating the effects of individual collection geometry parameters, such as camera angle, flight direction, and time of day, to develop more targeted collection strategies. Full article

Unmanned aerial vehicle (UAV) imagery supports intelligent surveillance, environmental monitoring, traffic management, and infrastructure inspection. Yet aerial detection is difficult when objects are small, crowded, and observed at markedly different scales. Background clutter and illumination changes further weaken target cues and impair localization. We therefore propose HD-YOLO, a lightweight multiscale detector for small objects in UAV imagery. Its Multi-Dilation Shared Convolution Kernel (DSCK) extracts local texture and contextual information with shared dilated kernels. The Hybrid Dilated Bidirectional Feature Pyramid Network (HDFPN) reconstructs global and local cues before bidirectional aggregation, enabling high-resolution evidence to reach the prediction layers. The Efficient and Slim Head (ES-Head) combines shared operations with differential convolution to reduce cost and strengthen boundary-sensitive features. A joint ShapeIoU and Normalized Wasserstein Distance loss improves regression for small, irregular objects. Together, these components reduce missed detections in dense, cluttered scenes without relying on large model capacity. On VisDrone2019, HD-YOLO improves precision, recall, mAP50, and mAP50:95 over YOLOv8n by 6.9%, 7.2%, 8.2%, and 5.2%, respectively, while reducing parameters from 3.0 M to 0.9 M. Evaluations on TinyPerson and HIT-UAV also support its utility for tiny pedestrians and infrared aerial targets. HD-YOLO therefore improves small-object detection with a compact parameter footprint, while direct hardware benchmarks remain necessary to establish deployment efficiency. Full article

Unmanned aerial vehicle (UAV)-based multispectral imaging enables flexible, non-destructive crop monitoring. Although UAV imagery offers much higher spatial resolution than satellite platforms, its effective spatial detail at typical operational flight altitudes can still be insufficient for plant-level interpretation and fine canopy structure, which can reduce vegetation-index reliability. Most super-resolution (SR) research targets RGB or satellite imagery and emphasizes perceptual or pixel-wise quality, leaving the spectral fidelity of reconstructed UAV multispectral imagery under-examined. This study benchmarked an SR evaluation framework for UAV-based five-band crop imagery (Blue, Green, Red, Red-edge, and near-infrared) using the open-source AI Hub cabbage dataset, with low-resolution inputs generated by controlled downsampling at ×2, ×3, and ×4. Nine methods (bicubic, SRCNN, EDSR, RCAN, SwinIR-based, ESRGAN-based, HAT-based, DAT-based, and DRCT-based SR) were compared under joint five-channel and band-wise reconstruction on 2170 test scenes using image-quality, spectral-angle, vegetation-index (NDVI, GNDVI, NDRE), band-wise, and efficiency metrics. EDSR and RCAN gave the most balanced performance. At ×4, band-wise reconstruction was strongest for per-band spatial fidelity, where EDSR reduced RMSE by 12.6%, and RCAN lowered near-infrared RMSE by about 21% relative to bicubic, whereas joint reconstruction with its spectral-angle and vegetation-index losses best preserved spectral relationships (spectral angle and vegetation-index errors). Learning-based gains were clearest at ×4. The recently proposed HAT-based, DAT-based, and DRCT-based attention models achieved the strongest pixel-wise RMSE and PSNR but did not surpass EDSR or RCAN on spectral angle or vegetation-index preservation under the equalized training budget. These results indicate that UAV multispectral SR should be assessed by spatial fidelity together with spectral consistency and agricultural index reliability. Full article

The accurate estimation of forest aboveground biomass (AGB) typically relies on extensive field surveys, which are highly time-consuming and cost-prohibitive. While unmanned aerial vehicle (UAV) Light Detection and Ranging (LiDAR) provides ultra-high point densities capable of reliable individual-tree analysis, its limited flight coverage restricts large-scale applications. Conversely, regional airborne laser scanning (ALS) offers broad spatial coverage, but its relatively low point cloud density makes individual-tree level analysis unreliable. To bridge this scale and data gap, this study develops a scale-consistent framework that integrates UAV-LiDAR, three-dimensional simulation, multisource remote sensing, and machine learning for Chinese fir (Cunninghamia lanceolata) plantation AGB estimation. High-density UAV-LiDAR data were first used to construct individual-tree AGB models, and the predicted tree-level biomass was aggregated to generate spatially representative “agent plots” for stand-scale modeling. A three-dimensional (3D) radiative transfer simulation framework was further employed to reproduce airborne LiDAR observations under different point densities, enabling the evaluation of structural information loss caused by LiDAR sparsity. Structural features derived from simulated LiDAR and spectral information from Sentinel-2 imagery were integrated using the Tabular Prior-data Fitted Network (TabPFN). Model reliability was assessed through 10-fold spatial block cross-validation and Monte Carlo simulations, which quantified spatial generalization and uncertainty propagation from individual-tree estimation to stand-level prediction. Feature interpretation using SHapley Additive exPlanations (SHAP) revealed that the LiDAR-derived vertical canopy structure provided the primary constraints for biomass estimation, whereas Sentinel-2 shortwave infrared features supplied complementary information related to canopy conditions. The optimal TabPFN model achieved a stand-level accuracy of R² = 0.88 and RMSE = 9.23 Mg·ha⁻¹ using LiDAR combined with Sentinel-2 data. Uncertainty analysis further demonstrated the robustness of the proposed framework under propagated errors, highlighting its potential for scalable and reliable forest biomass estimation in data-limited subtropical ecosystems. Full article

Nitrogen (N) is one of the most important nutrients influencing wheat growth, plant nutrition, and grain production. Appropriate timing of nitrogen application is essential to synchronize nutrient availability with crop demand. This study evaluated seven nitrogen management treatments, including a control (N0) and six split nitrogen application schedules (N1–N6), in durum wheat under Mediterranean conditions using an integrated approach combining ground-based hyperspectral sensing and unmanned aerial vehicle (UAV)-based multispectral imagery. Plant nutrient concentrations (N, P, K, Ca, and Mg), spectral reflectance, vegetation indices, plant height, and grain yield were evaluated at different phenological stages. Split nitrogen application significantly affected plant nutrient concentrations, spectral reflectance, vegetation indices, plant height, and grain yield. Plant nutrient concentrations generally declined with crop development, whereas spectral reflectance increased across the visible and near-infrared regions of the spectrum. Vegetation indices derived from both hyperspectral and UAV multispectral data successfully differentiated phenological stages and nitrogen treatments. UAV-derived plant height showed strong agreement with field measurements, confirming the reliability of photogrammetric measurements for monitoring crop development. Among the nitrogen treatments, the N3 split application schedule produced the most favorable overall crop response, with higher plant nitrogen concentration, stronger spectral responses, and the highest grain yield. In addition, UAV-derived NDVI measured at the booting stage showed the strongest relationship with grain yield (r = 0.717, p < 0.01). These findings demonstrate that integrating ground-based hyperspectral sensing with UAV multispectral imagery provides complementary information for evaluating crop development and plant nutritional responses under different split nitrogen application schedules. Full article

Small object detection (SOD) is a crucial research area in the field of computer vision. It poses significant challenges due to variations in scale, dense objects, limited target resolution, and a complex background. To achieve real-time detection, existing methods typically focus on local feature extraction and employ downsampling to reduce computation. However, this approach lowers the feature map resolution and loses the fine-grained details during downsampling. Meanwhile, frequency, global, and surrounding information play a significant role in small object detection. To address multi-scale dense targets in RGB and thermal infrared imagery with limited spatial, contextual, and frequency information, we propose a novel architecture that leverages Wavelet Transform Fusion (WTF) and Context-Guided Downsampling (CGD) in the real-time detection transformer (RT-DETR) for small object detection. WTF performs multi-frequency feature decomposition and fusion to preserve both high-frequency details and low-frequency semantic information, thereby improving the representation of small targets while reducing computational complexity. CGD incorporates local, surrounding, and global contextual information during downsampling to mitigate spatial information loss and strengthen feature representation for precise object localization. CGD is a downsampling technique that efficiently captures and preserves the contextual spatial information of local and global features using a local feature extractor and a joint feature extractor. It takes into account the surrounding information of the object, thereby reducing the loss of spatial details during downsampling. This spatial information helps in the precise detection of small objects in RGB and thermal infrared aerial images. Our proposed model is evaluated independently on the RGB aerial dataset NWPU-VHR-10 and the thermal infrared dataset HIT-UAV. Evaluations on the NWPU-VHR-10 and HIT-UAV datasets demonstrate that CGWT-DETR improves the mAP@0.50 to 89.9% and 86.5%, respectively, while boosting the strict localization metric mAP@0.50:0.95 to 60.3% and 58.8%. Furthermore, these accuracy gains are achieved alongside a 14.29% reduction in model parameters and a 29.8% decrease in GFLOPs. Experimental results demonstrate that CGWT-DETR outperforms the RT-DETR baseline in both detection accuracy and computational efficiency. Full article

Reliable target detection and geographic localization are critical for unmanned aerial vehicle (UAV)-assisted search and rescue (SAR) yet remain challenging in complex outdoor environments. Small targets in UAV Red–Green–Blue–Infrared (RGB–IR) imagery suffer from background clutter, occlusion, low illumination, and infrared thermal diffusion, while localization is vulnerable to unstable viewpoints and terrain-induced ray uncertainty. This study presents an integrated UAV-SAR framework coupling lightweight multispectral detection with Digital Elevation Model (DEM)-constrained geographic localization. For detection, the Asymmetric Fusion and Context-aware Detection (AFC-Det) network leverages asymmetric dual-stream encoding, cross-modal mutual prompting, and high-resolution anchored aggregation to enhance small-target representation from RGB–IR pairs. For localization, the Global Context-Regularized Huber Ray Consistency Optimization (GCR-HRCO) improves geolocation via global ray aggregation, multi-ray geometric consistency, Huber robust optimization, and DEM-based terrain constraints. Experimental results demonstrate AFC-Det achieves 45.4% average precision (AP) and 44.7% AP for small objects (APs) on the VTSaR dataset, with 1.7 million parameters, 8.0 GFLOPs, and 107.2 FPS, generalizing well to M3FD (54.6% AP). On SAR-DAG_raycast, GCR-HRCO reduces mean horizontal error from 6.85 m to 3.31 m and RMSE from 8.16 m to 4.33 m. Collectively, these results demonstrate the effectiveness of the proposed detection and localization components. Full article

Visual geo-localization is a predominant approach for unmanned aerial vehicles (UAVs) operating in Global Navigation Satellite System (GNSS)-denied environments, typically achieved by matching UAV-captured visible optical images with satellite base maps. However, under low-light conditions, visible cameras struggle to capture distinct features. While infrared sensors can capture clear features in such scenarios, the significant modality gap between thermal infrared images and optical satellite base maps makes accurate matching highly challenging. In this paper, we propose a novel cross-modal super-resolution matching and geo-localization method constrained by geographic consistency. First, a geographic consistency normalization module is introduced to narrow the modality gap between satellite optical images and thermal infrared images, thereby enhancing cross-modal matchability. Subsequently, a thermal infrared super-resolution enhancement module is employed to improve the spatial resolution and detail representation of the images, effectively increasing feature discriminability in low-texture regions. Finally, an end-to-end dense matching module is utilized to strengthen the stability of cross-modal correspondence estimation, ultimately improving geo-localization accuracy in low-light environments. Extensive experiments conducted on both a self-constructed network dataset and a real-world flight dataset demonstrate that the proposed method outperforms current competitive approaches. The proposed framework is not a simple combination of existing enhancement and matching modules, but a task-driven design that jointly addresses cross-modal discrepancy, low-resolution thermal imagery, and robust correspondence estimation. Experiments on self-constructed and public datasets demonstrate its robustness and superiority, achieving average geo-localization errors of 1.31 m and 8.04 m, respectively. Full article

Robust object detection for autonomous driving requires perception models that remain reliable when visible imagery is degraded by darkness, glare, rain, fog, motion blur, or long-range small targets. Visible and thermal infrared cameras provide complementary evidence, yet many RGB–thermal detectors fuse modalities, mainly as aligned tensors, and may underuse relational structure in channel responses, spatial layouts, semantic scales, and modality-specific uncertainty. This paper presents TopoGraph-Fusion, a hierarchical graph-guided dual-modal object detector that formulates fusion as topology-aware reasoning rather than direct feature concatenation. The proposed framework builds a dual-stream backbone for RGB and thermal images, constructs channel-wise topology through a channel-topology graph aggregation module, derives relation-aware spatial and channel global attention from affinity graphs, and replaces fixed feature-pyramid communication with a Graph-Guided Feature-Pyramid Network. A topology-regularized detection objective further encourages stable cross-modal correspondence while suppressing noisy all-to-all connections. Experiments on M3FD, FLIR, RGBTDronePerson, and VEDAI512 cover road scenes, adverse illumination, drone–person perception, and aerial vehicle detection. Within this validation scope, the results and visual analyses indicate that topology-guided fusion improves small-object recall, cross-modal consistency, and robustness under modality imbalance. Full article

Multimodal object detection leveraging RGB and infrared imagery has become essential for robust all-weather perception in unmanned aerial vehicle (UAV) applications. However, existing methods still struggle with effective cross-modal feature fusion, spatial misalignment between modalities, and scale variation of objects in aerial views. In this paper, we propose CMGFDet, a Cross-Modal Gated Fusion Network with Multi-Receptive Field Aggregation designed for RGB–infrared aerial object detection. Our framework introduces three coordinated modules: (1) a Cross-Modal Feature Fusion Network (CMFFN) that employs a gated attention mechanism to selectively aggregate complementary information from both modalities during encoding; (2) a Global–Local Attention Module (GLAM) that performs hierarchical cross-modal feature alignment by jointly modelling global channel statistics and local spatial correlations in the decoder; and (3) a Multi-Receptive Field Aggregation Network (MRFAN) that captures multi-scale contextual information through parallel depthwise convolutions with diverse kernel sizes. Additionally, we incorporate a deep supervision strategy and a composite loss function to enhance training efficiency. Extensive experiments on four public benchmarks (DroneVehicle, RGBTDronePerson, VEDAI, and VTUAV) show that CMGFDet improves the previous best mAP@0.5 by 1.6%, 2.2%, 1.9%, and 2.2%, respectively. The implementation code will be released upon acceptance to support reproducibility. Full article

This study investigates automated detection of rooftop thermal anomalies using Unmanned Aerial Vehicle-Based Infrared Thermography (UAV-IRT) and deep learning object detection models. UAV thermal images are used to identify potential thermal bridges on building rooftops. The experiment is framed as a preliminary workflow validation performed on a subset of the Karlsruhe reference dataset. The study evaluates four YOLO models, including YOLOv9, YOLOv10, YOLOv11, and YOLOv12. The results indicate that all models can detect major thermal anomaly regions in UAV thermal imagery. YOLOv9 achieves slightly higher detection accuracy in the tested dataset. These results demonstrate the feasibility of the proposed workflow under reference-dataset conditions, while validation on a dedicated historic-building dataset remains necessary before claiming applicability to heritage or historic urban environments. Full article

Canopy temperature (T_c) is an important indicator for characterizing crop water status and serves as the core variable for constructing the Crop Water Stress Index (CWSI). Timely and accurate diagnosis of crop water stress is of great significance for precision irrigation and yield improvement. Owing to its non-contact and high-efficiency characteristics, unmanned aerial vehicle (UAV) remote sensing has become an effective approach for high-spatiotemporal-resolution monitoring of crop water conditions. However, variations in observation geometry can introduce thermal directional effects in canopy temperature, thereby reducing the stability and reliability of CWSI estimation. In this study, multi-angular thermal infrared imagery acquired by a UAV platform was utilized to investigate the directional characteristics of winter wheat canopy temperature. A kernel-driven model was employed to separate the directional components of canopy temperature and retrieve isotropic temperature parameters that more closely represent the actual thermal status of the crop canopy. Based on these temperature parameters, three CWSI models were constructed and evaluated for crop water stress diagnosis. The results demonstrated that (1) winter wheat canopy temperature exhibited pronounced directional characteristics, and the observed temperature generally decreased with increasing relative azimuth angle between the viewing direction and solar incident direction; (2) after angular correction, the isotropic canopy temperature simulated by the kernel-driven model showed an improved correlation with soil moisture content at a depth of 30 cm (R² = 0.54); and (3) when angular-corrected canopy temperature was used as the input variable for different CWSI models, the sensitivity of all models to crop water variation was substantially enhanced, resulting in improved discrimination among different irrigation treatments. Among the evaluated approaches, the empirical CWSI model achieved the best performance in diagnosing crop water stress variations (R² = 0.73, RMSE = 1.59%). These findings provide a theoretical basis for UAV-based thermal infrared remote sensing of crop water status and offer technical support for precision irrigation management. Full article

The survival probability of persons requiring rescue after large-scale earthquakes or landslides decreases rapidly with time, and nighttime search operations are constrained by limited visibility. Satellite remote sensing enables wide-area observation at night, but its limited spatial resolution restricts the identification of individual persons. This study develops an automated method for detecting persons in thermal infrared imagery captured by Unmanned Aerial Vehicles (UAVs) using the deep learning model Grounding DINO. To address the limited availability of Unmanned Aerial Vehicle (UAV)-based training data, thermal infrared imagery captured by fixed-point ground cameras was used for training. Spatial resizing and padding were applied to emulate UAV viewpoints and mitigate the ground-aerial domain gap. The proposed model outperformed the baseline on real-world datasets, with substantial Recall improvements in environments with low thermal contrast. An ablation study confirmed that spatial resizing, padding, and position-based augmentation each contribute progressively to detection performance. A comparison with the lightweight YOLOv8n and DETR-based RT-DETR detectors indicated that the Transformer architecture alone does not account for reliable detection in scenes with complex thermal noise. This robustness instead derives from the language-grounded semantic priors of Grounding DINO. An extended evaluation on nighttime imagery indicated that the proposed approach generalizes to nighttime acquisition. Full article

Wildfires in California increasingly threaten communities and ecosystems. However, comprehensive estimation of fire dynamics and fuel structure remains limited. Recent advances in Uncrewed Aerial Vehicle (UAV) technology and high-spatial-resolution mapping have provided increasingly important tools for estimating wildfire fuel-height loss across fuel types. This study used a one-year Uncrewed Aerial Vehicle (UAV) time series to quantify fuel-height loss and vegetation regrowth associated with a prescribed upslope canyon fire near Salinas, California, USA. Multispectral, infrared, and visible UAV imagery collected before, during, and after burning was used to generate orthomosaic, digital surface models (DSMs), fuel-type classifications, and surface-volume estimates. To enable reliable pre- and post-fire comparison, ground control points and tie points were used to train linear regression calibrations that corrected angular discrepancies and elevation offsets among time-series DSMs. Calibrated DSMs were then integrated with ecological field measurements to map fuel-height consumption and post-fire recovery at the individual-plant scale. UAV-derived fuel-height change was associated with in situ twig-diameter measurements, which provide field-based indicators of fire effects in chaparral vegetation, while the maximum recorded temperature explained only a small proportion of variation in fuel-height loss. This workflow can support integrated fire ecology and remote-sensing studies by providing repeatable measurements of post-fire changes in vegetation structure. Full article

Agricultural production in arid regions is strongly constrained by water stress, making timely evaluation of crop water conditions increasingly important. However, conventional measurements of plant moisture content (PMC) primarily rely on destructive oven-drying methods, which are not only labor-intensive and time-consuming but also constrained by limited sample size and spatial coverage. These shortcomings make it difficult to capture the spatial heterogeneity of crop water status across large agricultural regions, thereby restricting regional-scale water diagnosis and precision irrigation decision-making. Focusing on silage maize cultivated in the arid region of Gansu Province, China, this work develops a regional PMC estimation approach by combining multi-source remote sensing data. High-resolution unmanned aerial vehicle (UAV) observations were integrated with Sentinel-2 and Sentinel-3 imagery, while radiometric and temperature corrections were applied to improve data consistency. A set of spectral, textural, and thermal features was derived from multispectral, visible, and thermal infrared datasets. Feature selection based on Pearson correlation was then carried out, followed by the construction of three models, namely Random Forest (RF), Support Vector Machine (SVM), and Partial Least Squares Regression (PLSR). Among them, the RF model performed more reliably, achieving a validation R² of 0.92 with relatively low prediction error. In addition, calibration using UAV data led to a clear improvement in satellite-based estimates, with R² increasing from 0.52–0.62 to 0.71–0.74. The generated PMC maps captured both the temporal decline during the growing season and the spatial variability across the study area. Overall, the proposed approach offers a practical option for large-scale monitoring of crop water status and can support irrigation management in water-limited environments. Full article