Search Results (14,713)

Cloud contamination obscures ground objects, interferes with surface reflectance, and disrupts spatial continuity. In thick-cloud regions, surface structures and spectral information are often extensively missing. CNN-based cloud removal methods can recover local textures, but they are less effective at modeling global structures and color consistency over large cloud-covered areas. Transformer-based methods capture long-range dependencies; however, standard self-attention introduces high computational and memory costs for high-resolution remote sensing images. Efficient attention reduces this cost but may weaken edge and texture discriminability. SAR imagery can penetrate clouds and provide surface structural information, yet repeated SAR injections may propagate speckle noise, cross-modal misalignment, and imaging discrepancies through deep restoration layers. To address these issues, this paper proposes DST-SARNet, a dual-stage SAR structural guidance network for optical remote sensing image cloud removal. In this framework, dual-stage refers to two explicit SAR-guidance positions: early structural skeleton guidance at the input side and late high-frequency modulation near the output. The Texture-Aware Asymmetric Retrieval module is placed between these two stages as a bottleneck memory retrieval operation rather than as a third dense SAR injection stage. With this design, SAR provides structural skeletons, readable texture memory, and terminal detail compensation, while the optical branch remains responsible for color, semantics, and spectral appearance recovery. Experiments on the SMILE-CR and SEN12MS-CR datasets show that DST-SARNet effectively restores cloud-contaminated imagery with a compact model scale, demonstrating its potential for efficient SAR-assisted optical cloud removal. Full article

Platform motion errors degrade SAR image quality in terms of severe defocusing and azimuth blurring. We propose a Range-aware Autofocus Network (RAFnet) by embedding a novel range-aware attention module into a progressive autofocus framework. The module exploits 1-D azimuth pooling to compress spatial features and extract high-SNR scattering components from the range dimension. Such features are further enriched via a light cross-channel interaction. To facilitate coarse-to-fine hierarchical learning, we develop a progressive multi-scale entropy loss which jointly optimizes the entire network. Experimental results on real SAR data show that the proposed approach captures high-level phase fluctuations accurately and effectively suppresses raw phase deviations and sidelobes. Quantitative results show that combining the attention module with multi-scale loss achieved a global spatial entropy of 9.8567 and contrast of 5.0091 in focused images. By extracting more accurate focus-oriented feature representations, we provide an effective solution for high-quality SAR auto-focusing. Full article

Rice cultivation is a major source of methane (CH₄) emission in the agricultural sector, with a significantly higher global warming potential than carbon dioxide. Accurate and scalable quantification of CH₄ from rice paddies is essential for carbon accounting. This study presents an automated framework for estimating rice CH₄ emissions from irrigated paddies in the central plain of Thailand, integrating multi-sensor Synthetic Aperture Radar (SAR) observations with the IPCC methodology. The framework combines Sentinel-1 C-band SAR time series for phenological detection, ALOS-2 PALSAR-2 L-band full-polarimetric SAR for water regime classification, and IPCC water-scaling factors corresponding to Continuous Flooding, Single Drainage, or Multiple Drainage regimes. Evaluated across five stratified holdout sets, the phenology detection algorithm achieved planting and harvesting date Mean Absolute Errors of 6.1 ± 1.4 and 8.3 ± 1.7 days, with a 97.0% ± 2.7% operational detection rate. Water regime classification employed rice growth stage-specific Support Vector Machine classifiers with Radial Basis Function kernels (SVM-RBF), achieving per-stage test Balanced Accuracy ranging from 0.59 to 0.89. End-to-end integration using a four-track counterfactual decomposition yielded a full-pipeline mean absolute error of 18.5 ± 4.5 $\mathrm{kg}{\mathrm{CH}}_4{\mathrm{ha}}^{-1}$ (21.4% of the mean ground-based CH₄ calculation) and a mean bias of 3.5 ± 5.8 $\mathrm{kg}{\mathrm{CH}}_4{\mathrm{ha}}^{-1}$. Water level classification was confirmed as the dominant algorithmic uncertainty source, while the IPCC Tier 1 emission factor structural range (−32% to +48% of the default) exceeded all algorithmic errors combined. The proposed framework provides a spatially explicit approach for integrating multi-frequency SAR data into IPCC-compliant methane estimation, supporting Monitoring, Reporting, and Verification applications. Full article

This paper presents a novel optimal control-based beamforming framework for phased antenna arrays, targeting advanced wireless communication and radar applications, including 5G systems. Unlike conventional beamforming techniques, such as Fourier-based methods and adaptive algorithms (e.g., LMS and RLS), the proposed approach formulates the beam synthesis problem as a discrete-time optimal control problem. The antenna array is modeled using a state-space representation, and a quadratic cost function is introduced to jointly minimize the deviation from a desired radiation pattern and the excitation power. The optimal excitation weights are derived using the Linear Quadratic Regulator (LQR) framework by solving the discrete-time algebraic Riccati equation. This formulation enables an effective trade-off between sidelobe suppression, main lobe accuracy, and power efficiency. Simulation results demonstrate that the proposed method achieves a well-focused main beam, significantly reduced sidelobe levels, and improved directivity compared to conventional approaches. Furthermore, the framework offers robustness and computational efficiency, making it a promising candidate for future FPGA and embedded implementations. Overall, the proposed optimal control-based beamforming approach provides a flexible, robust, and computationally efficient solution for next-generation antenna systems in 5G, beyond-5G (B5G), and radar applications. Full article

Direction of arrival (DoA) estimation is a fundamental problem in modern communication systems, such as 5G/6G cellular systems, V2X, and radar. Modern DoA estimation techniques enhance signal reception, mitigate interference, enhance communication efficiency, improve capacity, and improve spatial selectivity. In this paper, a two-channel residual neural network (ResNet) CNN is designed and trained based on the covariance matrix for a realistic electromagnetic antenna array model by expanding the steering vector obtained from the embedded element radiations. The regression DoA estimation is parameterized for three scenarios: regression using a trigonometric angle process, regression directly in degrees, and regression in radians. Then, the proposed network is compared with the modified conventional multiple signal classification (MUSIC), minimum variance distortion-less response (MVDR), and a two-channel deep CNN. A microstrip antenna array is designed, operating at 28 GHz, using Ansys Electronic Desktop to obtain the 3D embedded element radiation, for both co-polarized and cross-polarized components, considering mutual coupling among the antenna array elements, finite-element spacing, and array geometry. The proposed degree-based ResNet CNN achieves sub-degree azimuth and elevation RMSE for angular separations greater than 10° at an SNR of 0 dB in our simulations, clearly outperforming modified MUSIC, MVDR, and deep CNN learning-based 2D DoA methods that require significantly higher SNR to reach comparable accuracy. Moreover, the network operating directly on the real and imaginary parts of the covariance matrix and predicting angles in degrees consistently yields lower RMSE than variants trained to predict radians or sine–cosine representations, while avoiding the steering vector knowledge and postprocessing steps, spatial spectra, peak search, or root-finding, used in existing approaches. Full article

Autonomous Haulage Systems (AHS) have significantly transformed surface mining operations by improving safety, productivity, and operational consistency. Currently, AHS predominantly rely on vehicle-centric perception architectures. Onboard LiDAR, radar, cameras, and Global Navigation Satellite Systems (GNSS) perform sensing, interpretation, and decision-making within individual systems. These processes enable collision avoidance and path tracking. However, they are limited in their ability to consider the broader, dynamic mining environment characterized by dust, terrain degradation, geotechnical instability, heterogeneous traffic, and rapidly evolving operational conditions. This paper presents a systematic review of dynamic vision systems of AHS in surface mining. It critically analyzes the transition from autonomy to interconnected, ecosystem-aware intelligence. The review synthesizes literature from mining automation, robotics, intelligent transportation systems, and multi-agent perception. It assesses sensing technologies, perception algorithms, sensor fusion strategies, and environmental robustness techniques. Attention is focused on the limitations of egocentric perception models in complex surface mining ecosystems. Building on identified gaps, the paper proposes a conceptual framework for Ecosystem-Centric Dynamic Vision (ECDV). Perception is enhanced through integration with fleet communication networks, dispatch systems, digital twins, geotechnical monitoring platforms, and environmental sensing infrastructure. The framework outlines a multi-layer architecture enabling cooperative perception, predictive hazard modeling, and risk-aware decision support at the mine-wide level. The review concludes by outlining a research agenda to transition from vehicle autonomy to ecosystem intelligence in surface mining. It highlights opportunities in cooperative perception, adaptive sensor fusion under degraded visibility, and digital-twin-integrated predictive safety systems. Full article

Continuous full-domain vehicle trajectories are essential for smart highway monitoring, but single-sensor roadside perception is limited by physical coverage, occlusion, and environmental sensitivity. To address continuous trajectory tracking across multiple roadside-sensing domains, this study proposes a real-time, full-domain highway trajectory tracking framework based on radar–camera fusion, improved Deep-SORT, and inverse covariance intersection. At the local perception level, a two-stage object-level and decision-level fusion model is constructed, and Deep-SORT is improved using a CIoU matching strategy and an occluded target tracking controller to enhance local multi-object tracking continuity. At the cross-domain association level, a geometry-motion consistency stepwise calibration method is developed to unify adjacent sensing domains, and a CATS-ICI trajectory stitching strategy is introduced to improve trajectory association and state smoothness during sensor handover. The proposed framework was validated on a real highway test section with roadside radar, video, and drone-based ground-truth trajectories. Experimental results show that the full local method achieves an EMOTA of 92.35%, and the reconstructed full-domain trajectories achieve a successful trajectory matching rate of 98.4% under the 452 vehicles/10 min test condition. Additional ablation experiments further verify the contributions of radar–camera fusion, CIoU, OTTC, GMCSC, CATS, and ICI. These results demonstrate that the proposed framework can provide continuous and reliable full-domain vehicle trajectories for real-world highway monitoring. Full article

Post-disaster scenarios such as tsunamis require rapid terrain assessment that cannot wait for the next satellite synthetic aperture radar (SAR) revisit, yet a readily deployable system remains lacking. We present an off-the-shelf K-band drone-borne dual circular polarimetric (DCP) SAR and a processing pipeline for on-demand terrain classification. Compared with fully polarimetric (FP) SAR, DCP requires only a single transmit polarization and two receive channels, providing a wider swath than FP for the same acquisition, while still separating odd-bounce and even-bounce scattering mechanisms, which dual linear polarimetric modes with the same channel count provide with greater ambiguity due to their sensitivity to target orientation angle. To compensate for platform motion, we implemented RTK global navigation satellite system (GNSS) guided time-domain backprojection (TDBP) with phase gradient autofocus (PGA), yielding an 11.98 dB improvement in peak amplitude. We then applied single-target wire calibration to correct a measured 8.91 dB inter-channel complex gain difference between co-polarization and cross-polarization. As a result, H/α decomposition of the calibrated DCP data classifies canonical reflectors, artificial structures, gravel roads, vegetation, and a pond surface. These field experiments extend compact polarimetric H/α decomposition to drone-borne SAR data for terrain discrimination, establishing a practical pathway toward rapid post-disaster terrain assessment. Full article

Reliable and scalable landmine detection technologies are essential for humanitarian mine action (HMA), yet standardized benchmarks for Unmanned Aerial Vehicle (UAV)-based sensing in operationally relevant environments remain limited. This study presents a comprehensive evaluation of 34 multimodal datasets acquired over a standardized seeded test site for landmine and unexploded ordnance detection. Nine sensing modalities, including RGB, thermal, multispectral, hyperspectral, LiDAR, and Synthetic Aperture Radar (SAR), are evaluated using the Anomaly, Identifiable Anomaly, Unique Identifiable Anomaly (AIU) index to establish a unified framework for quantifying detection fidelity. Results indicate that RGB imagery achieves the highest surface detection rate (94.8%), with 45.4% of targets classified as uniquely identifiable, reducing false-positive risk. For sub-surface detection, handheld electromagnetic induction (EMI) and magnetometry exceed 95% detection for ferrous items but fall below 10% for plastic ordnance. Ground-penetrating radar (GPR) is the only modality capable of detecting buried plastic targets (55.6% for cart-based systems), whereas UAV-mounted GPR remains limited (18.2%) at current operational flight heights. Based on the comparative analysis, we discuss the gaps in current detection capabilities, compare false-positive rates across modalities, and perform a cost–benefit analysis fitting contamination scenarios with the most cost-effective detection method. All datasets are publicly released, along with an interactive web-map, to support reproducible benchmarking and cross-modality comparison in UAV-enabled explosive hazard detection. Full article

Accurate retrieval of cloud liquid water content (LWC) and ice water content (IWC) vertical profiles remains limited by strong vertical variability and nonlinear dependencies among observed variables. Ground-based cloud radar reflectivity and microwave radiometer-derived thermodynamic profiles provide complementary constraints, but their joint use requires consistent time–height matching and bias-controlled predictors. This study develops a vertically structured machine-learning framework that explicitly represents profile-level dependencies by constructing vertical-structure-enhanced features to encode local gradients and contextual information, integrating multiple tree-based learners with heterogeneous configurations through a profile-aware stacking strategy, and introducing a profile-level refinement step to suppress layer-to-layer inconsistencies. The framework is evaluated using year-round Cloudnet observations from the Lindenberg site, where IWC RMSE decreases from 0.0152 g m⁻³ to 0.0092 g m⁻³ with R² increasing from 0.412 to 0.784, and LWC RMSE decreases from 0.0786 g m⁻³ to 0.0591 g m⁻³ with R² increasing from 0.303 to 0.606. Additional boundary-region evaluation shows that the improvement is particularly evident near radar-derived cloud boundaries, where cloud structure and hydrometeor content may vary rapidly with height. These results indicate that treating cloud retrieval as a vertically structured learning problem reduces inconsistencies inherent in pointwise models and establishes a data-driven baseline for incorporating vertical constraints into atmospheric profile retrieval. Full article

Tracking highly maneuverable UAVs in complex maritime environments faces multiple challenges: dynamic sea surface interference and low-altitude occlusion make UAV motion trajectories difficult to predict; the strong maneuvering behavior of UAVs imposes high demands on tracking real-time performance and accuracy; and marine environmental noise and unstable shipborne sensor data lead to measurement incompleteness. These factors collectively limit the adaptability and robustness of existing maneuvering UAV tracking methods in complex maritime scenarios. In this context, accurate model recognition for UAVs becomes a key factor in improving tracking performance. Traditional interactive multiple model (IMM) methods rely on probabilistic weighting for model selection, suffering from response delays during UAV maneuvers, and fixed model sets cannot adapt to diverse maneuvering scenarios, resulting in degraded UAV velocity estimation accuracy. To address the above issues, this study proposes a dual long short-term memory (LSTM) cooperative network architecture, targeting the two key problems of incomplete measurements in shipborne radar measurements and inaccurate model probability estimation, and presents corresponding solutions. First, an online-trained LSTM-based incomplete-measurement compensation method is proposed, which achieves real-time fitting and restoration of historical measurement data, providing continuous and stable measurement inputs for shipborne platform UAV tracking in maritime environments. Second, building on this, an LSTM-based UAV model recognition method is developed to directly identify the UAV’s current motion model from multi-frame historical measurement information, effectively reducing maneuvering delays. Furthermore, GPS data is used to generate optimal model probabilities as training labels, thereby improving model reliability. Simulation results show that, under incomplete-measurement conditions, the proposed method can effectively reconstruct missing measurements and ensure measurement continuity. Under complete-measurement conditions, the proposed LSTM-based model recognition method significantly improves UAV model recognition accuracy and three-dimensional velocity estimation performance, demonstrating the effectiveness of deep learning for maneuvering UAV tracking from shipborne platforms in maritime environments. Full article

Global Navigation Satellite System Reflectometry Interferometric Synthetic Aperture Radar (GNSS-R InSAR) offers all-weather, all-day observation capabilities and high temporal resolution, enabling elevation deformation monitoring with a single satellite. However, in hazardous regions, such as tailings dam slopes, measuring the deformation of a greater number of target points is essential for a more accurate assessment of geological hazard risks. Since navigation satellite signals are not originally designed for imaging purposes, their inherent narrow bandwidths result in low spatial resolution and limited target recognition capabilities, rendering them inadequate for such scenarios. To address these limitations, this paper investigates a GNSS-R InSAR deformation measurement architecture utilizing dual-frequency BeiDou-3 (BDS-3) signal fusion. Specifically, a coherent spectrum fusion method is introduced to effectively expand the signal bandwidth, thereby significantly enhancing range resolution and target identification capabilities. Building upon this, deformation measurements are conducted to achieve more refined and detailed monitoring. Full article

Clouds frequently degrade optical satellite imagery, limiting the reliability of remote sensing models. However, in the literature, cloud-free analyses are often performed by excluding cloudy images from machine learning datasets and methods. This restricts their usefulness in time-critical scenarios such as disaster response, where waiting for cloud-free imagery is impractical. Cloud removal can mitigate this issue, but methods remain imperfect and may introduce visual artifacts. Therefore, it is desirable to develop cloud-robust methods by combining optical imagery with radar data, a modality unaffected by clouds. While datasets for machine learning combine optical and radar data, most researchers exclude cloudy images from training and evaluation. We identify this exclusion as a limitation that reduces applicability to cloudy scenarios and address it by introducing CloudyBigEarthNet (CBEN), a dataset of paired optical and radar images containing cloud occlusions for land-use and land-cover classification. Using average precision (AP), we show that state-of-the-art methods trained on clear-sky optical and radar data suffer performance drops of between 23.8 and 33.4 AP points when tested on cloudy imagery. We adapt these methods using cloudy images during training and improve AP on cloudy test cases by 17.2 to 28.7 AP points. Code and dataset have been published. Full article

High-altitude rock slides frequently occur in the high-mountain canyon regions of the eastern Tibetan Plateau, posing significant disaster risks. The Baige landslide catastrophically failed in October 2018, blocking the Jinsha River and forming a major landslide-dammed lake. However, quantitative understanding of the spatiotemporal evolution and environmental control mechanisms remains insufficient, particularly regarding stage-dependent driving mechanisms. This study investigates the Baige landslide using mall Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR), Seasonal-Trend decomposition based on Loess (STL) time-series decomposition, Principal Component Analysis–Independent Component Analysis (PCA-ICA) signal analysis, and slope-unit spatial statistics. Results indicate that: (1) deformation exhibited three stages separated by October 2018: slow pre-slide deformation, post-slide residual creep, and long-term sustained acceleration; (2) instability caused systematic restructuring of the deformation field, with valid pixels decreasing from 2766 to 560, deformation changing from slight positive line-of-sight (LOS) displacement to pronounced negative LOS displacement, and global standard deviation increasing from 21.40 mm to 40.55 mm, with stronger disturbances in the steep front zone; and (3) the driving mechanism shifted from short-term multi-factor control to a temperature-dominated long-term environmental control regime after failure, while gravity-driven creep and post-failure structural adjustment remained important background controls. Slope fragmentation and structural reorganization likely contributed to this transition. Full article

Aiming at core bottlenecks in weak and small target detection in radar range-Doppler (RD) spectra under low signal-to-noise ratio (SNR)—including severe performance degradation of traditional constant false alarm rate (CFAR) detectors and the inherent trade-off difficulty faced by existing deep learning methods in balancing detection accuracy, localization precision, and real-time performance—this paper proposes a progressive sub-pixel-level intelligent detection algorithm named F²DN-CCWL. The algorithm constructs a three-stage detection pipeline: global candidate screening, local fine discrimination, and weighted localization, and implements a full-stack customized design covering network architecture, soft-label training strategy, and post-processing modules. Simulation and field-measured results demonstrate that at −20 dB SNR, the proposed algorithm achieves a detection probability of 95.3%, a false alarm rate of 3.1%, an average localization error of 0.76 pixels, and a single-frame inference latency of 47.21 ms. This method offers a high-performance engineering solution for radar-based detection of low observable targets. Full article