Search Results (215)

Biodiversity monitoring is essential for evaluating mine rehabilitation success. Traditionally, assessments have relied on ground-based plot measurements, but advances in remote sensing offer opportunities to complement or replace plot-based surveys with spatially continuous monitoring approaches. We evaluated drone-derived multispectral imagery, the Soil Adjusted Vegetation Index (SAVI), and canopy height models (CHM) for mapping plant species used in mine rehabilitation in central Queensland, Australia. Ten classification models tested four combinations of spectral and structural data. Incorporating CHM improved overall accuracy by up to 10%, with notable gains for vegetation classes containing Eucalyptus and Acacia species. Species-level accuracy ranged from 79% to 100% for Eucalyptus and 74% to 100% for Acacia species. Misclassification was greatest among closely related red gums (Eucalyptus tereticornis Sm. and Eucalyptus camaldulensis Dehnh.) and Corymbia citriodora (Hook.) K.D.Hill & L.A.S.Johnson. These results demonstrate that structural information substantially improves species discrimination and has the potential to enhance biodiversity monitoring across plot (500 m²), block (1–100 ha), and landscape (100–1000 ha) scales. Full article

Coarse root systems govern tree anchorage, yet remain among the least documented components of tree architecture: excavation is irreversible, and established 3D methods rely on specialist scanners and lengthy post-processing. We evaluated whether a consumer smartphone records exposed coarse root architecture metrically, and which traits agree most closely with manual measurement. Four fully exposed Scots pine (Pinus sylvestris L.) root systems in northwestern Poland were scanned with an iPhone 17 Pro running Scaniverse, at about 30 min of acquisition and 5 h of processing per tree. Clouds were registered, cleaned and oriented to magnetic north in CloudCompare; of eight architectural metrics, four were validated against manual references at 95 cross-sections on 44 roots, and four were exploratory. Visible root length (root-mean-square error, RMSE, 22.2 cm, 8.4%), azimuth (RMSE 3.58°, mean absolute error 2.47°) and depth (RMSE 3.18 cm, 14.9%) agreed most closely with the reference; 70 of 77 first-order roots were detected with no false positives. Diameter was the weakest metric and the only one dependent on the operator (RMSE 0.46 and 0.29 cm for two operators on the same clouds). Smartphone LiDAR thus turns an irreversible excavation into a permanent, measurable record of the traits relevant to anchorage, provided that centimetre-level diameters are not required. Full article

Reliable unmanned surface vehicle (USV) recovery requires near-field maritime remote sensing outputs that remain stable during the final approach. Planar fiducial geometry provides metric pose estimates, but its depth channel is sensitive to corner-localization noise, apparent marker shrinkage, glare, reflection, and vessel vibration. We present VARE (Visual-Adaptive Ranging and Estimation), a geometry-anchored perception pipeline that combines ArUco-based Perspective-n-Point pose recovery, dual-path bearing fusion, MiDaS-assisted range stabilization, depth-consistency confidence weighting, and innovation-adaptive temporal filtering. VARE is a system-level integration rather than a new neural architecture, PnP solver, or end-to-end docking controller. The pipeline explicitly separates image-centroid bearing, translation-vector bearing, marker-normal heading, camera-frame horizontal approach range, and lateral offset. Independent RTK-synchronized external references, with measured lever-arm corrections between the RTK antenna, camera optical center, and marker reference point, are used for pool and near-shore evaluation. In controlled land tests, VARE reduced independent-reference angular RMSE by 34.0–49.3% relative to the pixel-only baseline and by 22.0–36.4% relative to a static-filter PnP variant. Across 15 pool-based approach trials, the full vision-only configuration achieved a horizontal bearing RMSE of 0.46 degrees, a range MAE of 0.82 m, and a range RMSE of 0.90 m. Relative to the matched IPPE-square geometry baseline with One-Euro filtering, the corresponding descriptive reductions were 14.8%, 4.7%, and 5.3%; the modest range differences are not presented as universally significant. Trial-level summaries, confidence intervals, and data-availability provisions are added to support reproducibility. The results support VARE as a candidate perception module for RTK-referenced USV recovery guidance, while full six-degree-of-freedom validation, session-level dropout survival, and closed-loop capture success remain future work. Full article

Terrestrial laser scanning (TLS), also referred to as terrestrial LiDAR, has become an essential close-range remote sensing technique for high-precision engineering surveying, deformation monitoring, industrial inspection, and cultural heritage documentation. The geometric reliability of TLS point clouds strongly depends on the effective compensation of instrumental systematic errors through in situ self-calibration. However, conventional target-based self-calibration often suffers from strong coupling between calibration parameters and exterior orientation parameters, whereas recently developed coplanarity-constrained formulations generally require highly redundant target networks, limiting their field efficiency. To address this limitation, this study proposes a variance inflation factor (VIF)-driven minimal network design strategy for efficient in situ geometric self-calibration of TLS systems. Unlike the commonly used geometric dilution of precision, VIF provides a dimensionless statistical alternative that effectively resolves the dimensional inconsistency inherent in traditional GDOP when handling mixed angular and distance parameters. A differential evolution algorithm is employed to search for hybrid calibration networks that minimize parameter coupling while preserving the physical interpretability of the National Institute of Standards and Technology (NIST) 10-parameter instrumental error model. Five digital twin simulation experiments and a physical validation experiment using a Faro Focus 350 scanner were conducted to evaluate the proposed method. The results show that the optimized network substantially reduces the number of required targets while maintaining high calibration accuracy. The final configuration, which combines VIF-optimized target placement with a dual-station height-difference constraint, reduces the condition number of the normal equations to below 60 and yields a mean system VIF close to 10. The maximum parameter correlation coefficient among the key calibration parameters is constrained to approximately 0.75, indicating near-optimal parameter decoupling under the limited field-of-view geometry of the instrument. These findings demonstrate that the proposed VIF-driven network design provides a highly effective strategy for field-efficient TLS self-calibration and improves the geometric reliability of terrestrial LiDAR point clouds in high-precision remote sensing applications. Full article

Wildfires are a major environmental hazard with severe consequences for ecosystems, air quality, infrastructure, and public safety. The rising incidence and severity of wildfire events worldwide have increased the need for reliable early detection and monitoring systems. Remote sensing technologies, such as satellite and unmanned aerial vehicle (UAV) imagery, along with ground-based Closed-Circuit Television (CCTV) cameras, provide valuable geospatial data for large-scale wildfire monitoring. Recent advances in deep learning, particularly Convolutional Neural Networks (CNNs) and Transformer-based architectures, have significantly improved the accuracy of wildfire detection systems. Despite these advances, balancing local feature representation with global contextual modeling remains challenging. CNNs effectively capture local spatial features but have limited receptive fields, whereas Vision Transformers (ViTs) model long-range dependencies but often overlook fine-grained local details and require substantial computational resources. Consequently, accurately detecting small, occluded, and visually ambiguous fire regions remains difficult, particularly for real-time deployment on resource-constrained edge devices. To address these challenges, this study proposes EdgeNeXt-Attn, an enhanced EdgeNeXt-based framework that effectively integrates local feature learning and global contextual modeling through channel and spatial attention mechanisms. The proposed model improves the detection of small, occluded, and visually ambiguous fire regions while maintaining the computational efficiency required for real-time edge deployment. The proposed framework is evaluated on four multi-platform benchmarks spanning ground-based CCTV (DFAN, Complex-Fire), aerial drone (FLAME), and mixed drone–satellite (ADSF) imagery, achieving 92.09%, 95.16%, 96.65%, and 87.81% accuracy, respectively, and outperforming recent state-of-the-art baselines. With only 5.3M parameters, the model achieves real-time inference at 85.9, 27.3, and 8.4 FPS on GPU, CPU, and Raspberry Pi, respectively. Furthermore, ablation studies and Grad-CAM analysis validate its effectiveness and accurate fire localization. These results demonstrate an accurate and computationally efficient framework for real-time wildfire monitoring using multi-platform remote sensing and ground-based imaging systems. Full article

The concentrations of DIN and DIP are important indicators in an offshore ecosystem; although they do not have optical activity, their concentrations are affected by optically active substances, such as sediment, chlorophyll, and dissolved organic matter, an association that is especially close in coastal waters. This study aimed to identify this relationship to provide a theoretical basis for using remote sensing to monitor DIN/DIP concentrations. This study first used correlation analysis to analyze the relationship between water quality indicators and the field-measured spectrum in the Sheyang estuary. The results show a strong positive correlation between the DIN and DIP concentrations and spectrum in near-infrared range, similar to that between the suspended sediment concentrations and spectrum; this indicates a close relationship between DIN/DIP concentrations and sediment concentration in this sea area. Traditional regression models for DIN and DIP concentrations were constructed using the sensitive bank factors of a Hyperion image. By comparing the physical meaning of the factors and the precision and stability of the models, the quadratic model established by the ratio factor of 45th and 10th bands was selected as the DIN concentration inversion model, the quadratic model established by the ratio factor of the 45th and 9th bands was selected as the DIP inversion model, and the inversion results of the image conformed to the actual distribution pattern of DIN and DIP concentrations. In order to fully utilize the spectral information of the Hyperion data, the model coupled using partial least squares (PLS) and support vector machine (SVM) was used to construct regression models of DIN and DIP concentrations. By comparing the standardized coefficients of PLS regression, the 8~16th bands and 37~57th bands of the Hyperion image were selected; all these bands were extracted as two orthogonal components to construct the SVM regression model. Finally, the parameter combinations of radial basis model with C = 10, γ = 0.05, and ε = 0.1 and C = 1, γ = 0.1, and ε = 0.001 were determined as the inversion models for DIN and DIP concentrations, respectively. The prediction accuracy of the models was significantly improved compared to the traditional regression models, and the inversion results were superior to those of the traditional regression models, demonstrating the potential of this algorithm in hyperspectral image modeling. Full article

Light detection and ranging (LiDAR) is widely used in robotics, autonomous vehicles, remote sensing, and object tracking, and a large number of commercial 3D LiDAR sensors with diverse specifications are now available. However, these sensors are typically sold with fixed specifications: their measuring range, field of view (FoV), angular resolution, number of scan points, and number of scan layers are all determined at the point of manufacture and cannot be adapted to the application. This rigidity forces the surrounding platform to absorb the cost of excess data, higher computation, larger post-processing storage, and false feature detections even when only a narrow region of interest is needed. To address these limitations, this paper presents 3D Customizable LiDAR (3D CS LiDAR), a novel reconfigurable 3D LiDAR architecture that exposes sensor specifications as run-time parameters. The paper describes the mechanical, electrical, and software subsystems of the developed sensor and evaluates its object-detection performance against a commercial 32-channel LiDAR under two experimental setups. Within the scope of the indoor evaluation reported here (1–3 m range, three geometric targets), the proposed reconfigurable 3D LiDAR provides denser on-target sampling and lower false negative rates than the commercial reference sensor in every tested configuration, indicating its potential for close-range indoor perception tasks such as robotic inspection and short-range obstacle detection. This work contributes to LiDAR technology by introducing a run-time-reconfigurable approach that addresses the specification rigidity of existing sensors and outlines the initial progress towards a full-fledged reconfigurable 3D LiDAR system, with outdoor operation and long-range characterisation identified as future work. Full article

Stratospheric solar-powered unmanned aerial vehicles (UAVs), commonly operated as High-Altitude Pseudo-Satellites (HAPS), promise satellite-like persistence for Earth observation, communications and remote sensing, but their feasibility is governed by a tight coupling between solar energy availability and onboard energy demand. This study presents an energy-balance simulation framework that predicts the diurnal charge–discharge behaviour and endurance of solar-powered UAVs. The framework couples a physics-based environmental irradiance model—astronomical solar position, an air-mass and pressure-scaled broadband atmospheric transmission and an eccentricity-corrected extraterrestrial irradiance—with a wing-geometry photovoltaic collection model that reduces the airfoil camber, planform, dihedral and cell layout of a real wing to three scalar coefficients, replacing the flat-plate assumption common in solar-UAV sizing. The closed-form collection coefficient captures the full dependence of collected power on sun position and aircraft heading and admits an exact orbit-averaging result for circular loiter. The model is implemented as a reproducible, modular tool with single-day, annual and global analysis modes. It is validated against a ground-based photovoltaic charging campaign conducted on the as-built Aurora solar UAV demonstrator (5.6 m span, 8 kg) over three clear-sky days spanning a 90-day seasonal range: predicted and measured wing-collected power agree with a Pearson correlation of 0.998, a coefficient of determination of 0.993, an RMS error of 6.0% and a daily-energy agreement within 3.5%. A structured residual identifies an unmodelled photovoltaic temperature effect bounded at the 6% level. The framework provides HAPS designers and operators with a transparent, validated tool for feasibility screening, component selection and mission planning across latitude and season. Full article

Grassland foliar functional traits are closely linked to ecosystem functioning, biodiversity, and plant responses to environmental change. Hyperspectral remote sensing provides an efficient and non-destructive approach for mapping foliar traits, yet direct comparisons between UAV-based and airborne imaging spectroscopy remain limited. In this study, we evaluated the performance of UAV-based Nano and airborne Hyspex hyperspectral imagery for predicting ten foliar functional traits across experimental grassland plots at the Cedar Creek Ecosystem Science Reserve, USA. We further assessed the contributions of visible-to-near-infrared (VNIR) and shortwave infrared (SWIR) spectral regions, as well as the effects of spectral preprocessing approaches for minimizing confounding effects from canopy structure, illumination/viewing geometry, and soil background. Random Forest regression models were developed using plot-level average spectra derived from Nano and Hyspex imagery. Both UAV- and airborne-based imaging spectroscopy achieved moderate to high prediction accuracies for most foliar traits. High accuracies were obtained for non-structural carbohydrates (NSC), carotenoids, β-carotene, hemicellulose, and cellulose (R² = 0.66–0.82; NRMSE = 6–10%), while moderate accuracies were achieved for nitrogen, chlorophyll, and xanthophylls (R² = 0.51–0.74; NRMSE = 8–12%). In contrast, carbon and lignin consistently exhibited lower predictive performance (R² = 0.32–0.59; NRMSE = 9–15%). Despite covering only the VNIR spectral range, the UAV-based Nano imagery achieved accuracies comparable to those obtained using the airborne full-spectrum Hyspex imagery, indicating that high spatial resolution can partially compensate for limited spectral coverage by reducing soil background effects. The VNIR spectral region alone provided trait estimation accuracies comparable to those obtained using the full visible-to-shortwave infrared (VSWIR) spectrum, whereas SWIR wavelengths contributed only marginal improvements for a subset of structural traits. Among preprocessing approaches, vector normalization generally improved prediction performance by reducing the confounding effects of canopy structure and illumination/viewing geometry, whereas NIR_v-adjusted spectra provided limited benefits. Our findings demonstrate that UAV-based VNIR imaging spectroscopy can provide accurate and cost-effective estimation of grassland foliar functional traits. The results also highlight important trade-offs between spectral and spatial resolution in hyperspectral remote sensing and provide practical guidance for selecting imaging spectroscopy platforms and preprocessing approaches for grassland ecosystem monitoring. Full article

Rapid and reliable flood segmentation utilizing optical remote-sensing imagery is critical for effective flood disaster response and risk assessment. Nevertheless, current models frequently struggle with imprecise boundary delineation and fragmented predictions in complex environments, especially where floodwater displays high spectral variability and closely resembles shadows, dark pavements, or wet soil. To overcome these challenges, we introduce FloodSeg, an innovative Mamba-CNN encoder–decoder network incorporating two lightweight yet highly effective components: a Shift module and a sequence-shuffle module. The spatial Shift module leverages spatially shifted feature aggregation to fortify boundary-aware representations, thereby ensuring the continuity of inundation contours even under varying illumination and cluttered backgrounds. Meanwhile, the sequence-shuffle module reorganizes multi-scale features via sequence-wise mixing and cross-regional interaction, significantly enhancing long-range dependency modeling. This facilitates the generation of globally consistent flood masks while mitigating local overfitting to dataset-specific textures. Evaluated on the Kaggle and FloodNet benchmark datasets, FloodSeg achieves outstanding mIoU scores of 81.85% and 91.21%, respectively. By outperforming various state-of-the-art CNN-, Transformer-, and Mamba-based baselines, our model demonstrates a superior accuracy-efficiency trade-off. These results substantiate that FloodSeg significantly advances boundary recognition and overall segmentation completeness, establishing it as a robust and practical solution for real-world remote-sensing flood mapping applications. Full article

This study presents the results from a comparison of measurement quantification methods of methane emissions from two onshore liquefied natural gas (LNG) export terminals, comparing site-level measurements, made using an in situ airborne technique, and estimates based on emission factors (EFs) derived from measurements using a remote sensing, ground-based, differential absorption LIDAR (DIAL) technique. The methane emissions from each site were quantified at an approximately one-year interval for each of the two techniques. DIAL was used to measure emissions at the sub-site, functional element (FE) level and calculate EFs for each FE using the specific FE activity data (AD). The total site methane emissions during the airborne measurements were estimated for each site using these EFs and the AD at the time. The results show the estimated methane emissions and the airborne measurements are close to agreement when considering the average of all the flight curtains (down to a 7% difference between uncertainty limits), whilst individual curtains were potentially significantly different. These results highlight the importance of fully characterising the methodology and uncertainty of both approaches. Using up-to-date, site-specific EFs or comparing over a statistically large sample size should improve agreement by reducing unknown emission uncertainties associated with site changes affecting the emission profile. Understanding each FE emission profile across a range of AD is critical to address potential differences due to non-linearity. It is important that accurate, specific and up-to-date AD is obtained to give a reliable estimate of emissions. The potential of the concept to estimate methane emissions from the FE EFs is demonstrated. Full article

Microwave-based remote sensing possesses the capability to penetrate through atmospheric obstructions such as cloud layers and fog, making it extensively utilized for estimating parameters including soil water content, atmospheric moisture levels, and terrestrial surface temperatures. Extended temporal datasets serve as fundamental requirements for climatological investigations; however, individual satellite operational lifespans remain constrained and prove inadequate for establishing multi-decade temporal sequences. Consequently, conducting comparative analyses and implementing cross-calibration procedures across measurements obtained from distinct sensors exhibiting comparable operational features becomes imperative. The FengYun (FY)-3G spacecraft, deployed into orbit during April 2023, hosts China’s most recent orbiting microwave radiometric instrument, designated as the Microwave Radiation Imager–Rainfall Mission (MWRI-RM). The FY-3G satellite’s unique drifting equator crossing time orbit plays a critical role in the calibration behavior of the MWRI-RM instrument, representing a key novelty of this study. The reliability of its brightness temperature (TB) observations has attracted considerable attention. Within this investigation, we conduct comparative assessments of orbital TB observations acquired from FY-3G/MWRI-RM against corresponding measurements obtained from the Advanced Microwave Scanning Radiometer 2 (AMSR2) installed on the Global Change Observation Mission–Water 1 (GCOM-W1) platform, and establish a straightforward linear inter-calibration methodology. Both sensing systems show strong consistency, with correlation coefficients exceeding 0.9 for all corresponding channels and systematic biases ranging from −1.40 K to −0.14 K. FY-3G/MWRI-RM generally reports lower TB values than GCOM-W1/AMSR2. The inter-sensor differences vary with frequency, land cover type, and TB range. Larger negative biases are mainly observed at 23.8 GHz and over water bodies, whereas the biases at 89 GHz are generally close to zero for most surface types. Latitude-dependent TB biases are most evident at 10.65 and 18.7 GHz, especially for vertical polarization at high latitudes, while orbit-dependent differences are more pronounced for vertically polarized low- and mid-frequency channels. After applying an inter-calibration procedure using AMSR2 as the reference, the agreement between FY-3G/MWRI-RM and GCOM-W1/AMSR2 is improved substantially, with mean biases below 0.25 K and RMSE values below 2 K for all channels. Validation using independent datasets further supports the stability of the calibration. The calibrated FY-3G/MWRI-RM TB data provide a basis for constructing long-term passive microwave brightness temperature records and for retrieving land and atmospheric parameters. Full article

Accurate tree counting from remote sensing data is essential for forest inventory, biomass estimation, carbon accounting, and ecological monitoring. However, existing approaches predominantly rely on airborne RGB imagery and often struggle in complex forest scenes where neighboring crowns exhibit highly similar textures and colors and where overlapping crown boundaries become ambiguous. To address this limitation, the LiDAR-derived Canopy Height Model (CHM) is introduced as a complementary modality that provides explicit cues on canopy height variation and vertical structure to support RGB-based analysis. Building on this, we propose BCAR-Net, a broker-guided RGB and depth (RGB-D) multimodal framework that couples bidirectional cross-modal interaction, adaptive tri-branch fusion, and auxiliary reconstruction within a two-stage optimization scheme. Specifically, a bidirectional cross-attention U-Net generates an intermediate broker RGB-D representation from paired RGB images and depth maps through symmetric bidirectional cross-attention between the two modalities and direction-aware gating. The original RGB image, depth map, and broker representation are then jointly encoded by three weight-sharing branches and adaptively aggregated by a spatial fusion gate for density-map regression. To regularize the fused latent feature, a multi-scale cross-attention reconstruction decoder provides auxiliary RGB and depth reconstruction supervision by querying multi-scale BCA-UNet encoder features through 2D cross-attention, and a reconstruction-oriented first stage replaces externally generated fused-image supervision, yielding a task-consistent optimization scheme. Experiments on the NEONTreeEvaluation benchmark show that BCAR-Net consistently outperforms single-modality settings and direct RGB-D concatenation multimodal baseline. Additional experiments on a public UAV RGB–LiDAR dataset provide a small-scale supplementary evaluation under a different acquisition setting, where BCAR-Net achieves modest but consistent improvements over RGB-only and depth-only baselines. These results demonstrate that the proposed framework offers an effective but computationally cautious solution for tree counting in complex forest environments. Full article

Object detection in optical remote sensing imagery faces persistent challenges from severe instance overlap, extreme spatial density, and motion or atmospheric blur. These degradations cause conventional detectors to over-mix neighboring instance features and fail to separate closely packed objects. To address these limitations, we propose SARC-DETR, a detection framework that augments the RT-DETR architecture with two complementary plug-in modules: Similarity Adaptive Convolution (SAC) and Receptive Field Cross Convolution (RCC). SAC introduces a reproducing-kernel-Hilbert-space (RKHS) motivated similarity gate that selectively suppresses responses inconsistent with local feature prototypes, thereby reducing cross-instance interference in overlapped and blurred regions. RCC constructs a large directional receptive field through orthogonal strip-based aggregation and content-adaptive fusion, enabling efficient long-range context capture without quadratic complexity overhead. Both modules can be integrated into existing DETR-style detectors without modifying the detection head or training protocol. On VisDrone2019-DET, SARC-DETR improves ${\mathbf{AP}}^{\mathbf{val}}$ from 29.7 to 34.8, ${\mathbf{AP}}_{50}^{\mathbf{val}}$ from 49.5 to 56.2, and ${\mathbf{AP}}_S^{\mathbf{val}}$ from 19.2 to 24.8. On DIOR, AP rises from 57.9 to 68.4, and on NWPU VHR-10, from 44.4 to 66.5, demonstrating robust cross-dataset generalization. After structural reparameterization, the additional overhead is less than 0.75 M parameters and 0.36 G FLOPs, confirming deployment suitability for UAV and satellite-based remote sensing applications. Full article

Satellite-based assessment of power tower damage is essential for rapid disaster response but is challenged by the scarcity of damage samples and the cross-scale mismatch between close-range UAV imagery and satellite imagery. Existing data augmentation methods, including copy-based strategies and diffusion-based generation, often fail to produce reliable samples due to their dependence on the training data distribution and the lack of explicit control over object scale and domain discrepancy. To address these issues, we propose a scale-constrained and frequency-adaptive diffusion-based data construction framework that explicitly models the scale distribution prior of power towers in the remote sensing domain and incorporates frequency-domain adaptation before image generation. Specifically, scale-aware instance embedding is used to construct training samples that conform to satellite-scale statistics, while frequency-domain adaptation is introduced to reduce spectral and texture discrepancies between UAV-derived damaged references and satellite imagery. A diffusion-based inpainting model is then trained on the constructed dataset to reconstruct damage at original tower locations. The experimental results, including feature statistical analysis and downstream change detection validation, demonstrate that the proposed method achieves better alignment with real satellite-scale distributions, reduces geometric and spectral–textural inconsistencies, and improves boundary continuity and structural realism under cross-resolution conditions. Full article