Search Results (1,740)

Icebergs pose significant risks to shipping, offshore oil exploration, and underwater pipelines. Detecting and monitoring icebergs in the North Atlantic Ocean, where darkness and cloud cover are frequent, is particularly challenging. Synthetic aperture radar (SAR) serves as a powerful tool to overcome these difficulties. In this paper, we propose a method for automatically detecting and classifying icebergs in various sea conditions using C-band dual-polarimetric images from the RADARSAT Constellation Mission (RCM) collected throughout 2022 and 2023 across different seasons from the east coast of Canada. This method classifies SAR imagery into four distinct classes: open water (OW), which represents areas of water free of icebergs; open water with target (OWT), where icebergs are present within open water; sea ice (SI), consisting of ice-covered regions without any icebergs; and sea ice with target (SIT), where icebergs are embedded within sea ice. Our approach integrates statistical features capturing subtle patterns in RCM imagery with high-dimensional features extracted using a pre-trained Vision Transformer (ViT), further augmented by climate parameters. These features are classified using XGBoost to achieve precise differentiation between these classes. The proposed method achieves a low false positive rate of 1% for each class and a missed detection rate ranging from 0.02% for OWT to 0.04% for SI and SIT, along with an overall accuracy of 96.5% and an area under curve (AUC) value close to 1. Additionally, when the classes were merged for target detection (combining SI with OW and SIT with OWT), the model demonstrated an even higher accuracy of 98.9%. These results highlight the robustness and reliability of our method for large-scale iceberg detection along the east coast of Canada. Full article

The quick and effective detection of humans trapped under debris is crucial in search and rescue operations. This study explores the use of antennas operating within the 150–650 MHz frequency range to identify human respiration and movement under building wreckage. A debris model consisting of construction materials was generated at the laboratory, and attenuation characteristics were observed to set ideal operating frequencies. Time-dependent transmission coefficient data were collected over 20 s and processed using short-time Fourier transform, wavelet transform, and empirical mode decomposition for time-frequency analysis. To enhance signal clarity, denoising techniques were applied before the radar signals were categorized into three classes: empty debris, human respiration, and human movement. Generative adversarial networks augmented environmental noise data to enrich training datasets comprising nine subsets. Deep learning models, including temporal convolutional networks, long short-term memory, and convolutional neural networks, were employed for classification. Hyperparameter optimization via random search further refined model performance. Results indicate that the convolutional neural networks using short-time Fourier transform data consistently achieved the highest classification accuracy across subsets. These findings demonstrate the potential of combining radar with deep learning for reliable human detection under debris, advancing rescue efforts in disaster scenarios. Full article

Aboveground biomass (AGB) serves as an important indicator for assessing the productivity of forest ecosystems and exploring the global carbon cycle. However, accurate estimation of forest AGB remains a significant challenge, especially when integrating multi-source remote sensing data, and the effects of different feature combinations for AGB estimation results are unclear. In this study, we proposed a method for estimating forest AGB by combining Gao Fen 7 (GF-7) stereo imagery with data from Sentinel-1 (S1), Sentinel-2 (S2), and the Advanced Land Observing Satellite digital elevation model (ALOS DEM), and field survey data. The continuous tree height (TH) feature was derived using GF-7 stereo imagery and the ALOS DEM. Spectral features were extracted from S1 and S2, and topographic features were extracted from the ALOS DEM. Using these features, 15 feature combinations were constructed. The recursive feature elimination (RFE) method was used to optimize each feature combination, which was then input into the extreme gradient boosting (XGBoost) model for AGB estimation. Different combinations of features used to estimate forest AGB were compared. The best model was selected for mapping AGB distribution at 30 m resolution. The outcomes showed that the forest AGB model was composed of 13 features, including TH, topographic, and spectral features extracted from S1 and S2 data. This model achieved the best prediction performance, with a determination coefficient (R²) of 0.71 and a root mean square error (RMSE) of 18.11 Mg/ha. TH was found to be the most important predictive feature, followed by S2 optical features, topographic features, and S1 radar features. Full article

Multiple-Input Multiple-Output (MIMO) radar enjoys the advantages of a high degree of freedom and relatively large virtual aperture, so it has various forms of applications in several aspects such as remote sensing, autonomous driving and radar imaging. Among all multiplexing schemes, Time-Division Multiplexing (TDM)-MIMO radar gains a wide range of interests, as it has a simple and low-cost hardware system which is easy to implement. However, the time-division nature of TDM-MIMO leads to the dilemma between the lower Pulse Repetition Interval (PRI) and more transmitters, as the PRI of a TDM-MIMO system is proportional to the number of transmitters while the number of transmitters significantly affects the resolution of MIMO radar. Moreover, a high PRI is often needed to obtain unambiguous imaging results for MIMO-SAR 3D imaging applications on a fast-moving platform such as a car or an aircraft. Therefore, it is of vital importance to develop an algorithm which can achieve unambiguous TDM-MIMO-SAR 3D imaging even when the PRI is low. Inspired by the motion compensation problem associated with TDM-MIMO radar imaging, this paper proposes a novel imaging algorithm which can utilize the phase shift induced by the time-division nature of TDM-MIMO radar to achieve unambiguous MIMO-SAR 3D imaging. A 2D-Compressed Sensing (CS)-based method is employed and the proposed method, which is called HPC-2D-FISTA, is verified by simulation data. Finally, a real-world experiment is conducted to show the unambiguous imaging ability of the proposed method compared with the ordinary matched-filter-based method. The effect of velocity error is also analyzed with simulation results. Full article

Rapid and accurate leaf area index (LAI) determination is important for monitoring daylily growth, yield estimation, and field management. Because of low estimation accuracy of empirical models based on single-source data, we proposed a machine-learning algorithm combining optical and microwave remote-sensing data as well as the random forest regression (RFR) importance score to select features. A high-precision LAI estimation model for daylilies was constructed by optimizing feature combinations. The RFR importance score screened the top five important features, including vegetation indices land surface water index (LSWI), generalized difference vegetation index (GDVI), normalized difference yellowness index (NDYI), and backscatter coefficients VV and VH. Vegetation index features characterized canopy moisture and the color of daylilies, and the backscatter coefficient reflected dielectric properties and geometric structure. The selected features were sensitive to daylily LAI. The RFR algorithm had good anti-noise performance and strong fitting ability; thus, its accuracy was better than the partial least squares regression and artificial neural network models. Synergistic optical and microwave data more comprehensively reflected the physical and chemical properties of daylilies, making the RFR-VI-BC05 model after feature selection better than the others ( r = 0.711, RMSE = 0.498, and NRMSE = 9.10%). This study expanded methods for estimating daylily LAI by combining optical and radar data, providing technical support for daylily management. Full article

Flood events are among the most destructive natural catastrophes worldwide and pose serious threats to socioeconomic systems, ecological environments, and the safety of human life and property. With the advancement of remote sensing technology, synthetic aperture radar (SAR) has provided new means for flood monitoring. However, traditional methods have limitations when dealing with high noise levels and complex terrain backgrounds. To address this issue, in this study, we adopt an improved U-Net model incorporating the Kolmogorov–Arnold Network (KAN), referred to as UKAN, for the efficient extraction of flood inundation extents from multisource remote sensing data. UKAN integrates the efficient nonlinear mapping capabilities of KAN layers with the multiscale feature fusion mechanism of U-Net, enabling better capturing of complex nonlinear relationships and global features. Experiments were conducted on the C2S-MS Floods and MMFlood datasets, and the results indicate that the UKAN model outperforms traditional models in terms of metrics such as the intersection over union (IoU), precision, recall, and F1 score. On the C2S-MS Floods dataset and the MMFlood dataset, UKAN achieves IoUs of 87.95% and 78.31%, respectively, representing improvements of approximately 3.5 and three percentage points, respectively, over those of the traditional U-Net. Moreover, the model has significant advantages in terms of parameter efficiency and computational efficiency. These findings suggest that the UKAN model possesses greater accuracy and robustness in flood inundation area extraction tasks, which is highly important for increasing the monitoring and early warning capabilities of flood disasters. Full article

Erosion is a critical geological process that degrades soil and poses significant risks to human settlements and natural habitats. As climate change intensifies, effective coastal erosion management and prevention have become essential for our society and the health of our planet. Given the vast extent of coastal areas, erosion management efforts must prioritize the most vulnerable and critical regions. Identifying and prioritizing these areas is a complex task that requires the accurate monitoring and forecasting of erosion and its potential impacts. Various tools and techniques have been proposed to assess the risks, impacts and rates of coastal erosion. Specialized methods, such as the Coastal Vulnerability Index, have been specifically designed to evaluate the susceptibility of coastal areas to erosion. Coastal boundaries, a critical factor in coastal erosion monitoring, are typically extracted from remote sensing images. Due to the extensive scale of coastal areas and the complexity of the data, manually extracting coastal boundaries is challenging. Recently, artificial intelligence, particularly deep learning, has emerged as a promising and essential tool for this task. This review provides an in-depth analysis of remote sensing and deep learning for extracting coastal boundaries to assist in erosion monitoring. Various remote sensing imaging modalities (optical, thermal, radar), platforms (satellites, drones) and datasets are first presented to provide the context for this field. Artificial intelligence and its associated metrics are then discussed, followed by an exploration of deep learning algorithms for extracting coastal boundaries. The presented algorithms range from basic convolutional networks to encoder–decoder architectures and attention mechanisms. An overview of how these extracted boundaries and other deep learning algorithms can be utilized for monitoring coastal erosion is also provided. Finally, the current gaps, limitations and potential future directions in this field are identified. This review aims to offer critical insights into the future of erosion monitoring and management through deep learning-based boundary extraction. Full article

The Aburrá Valley, located in the northwestern region of Colombia, has undergone significant land cover changes and urban expansion in recent decades, driven by rapid population growth and infrastructure development. This region, known for its steep topography and dense urbanization, faces considerable environmental challenges. Monitoring these transformations is essential for informed territorial planning and sustainable development. This study leverages Synthetic Aperture Radar (SAR) imagery from the Sentinel-1 mission, covering 2017–2024, to propose a methodology for the multitemporal analysis of land cover dynamics and urban expansion in the valley. The novel proposed methodology comprises several steps: first, monthly SAR images were acquired for every year under study from 2017 to 2024, ensuring the capture of surface changes. These images were properly calibrated, rescaled, and co-registered. Then, various multitemporal fusions using statistics operations were proposed to detect and find different phenomena related to land cover and urban expansion. The methodology also involved statistical fusion techniques—median, mean, and standard deviation—to capture urbanization dynamics. The kurtosis calculations highlighted areas where infrequent but significant changes occurred, such as large-scale construction projects or sudden shifts in land use, providing a statistical measure of surface variability throughout the study period. An advanced clustering technique segmented images into distinctive classes, utilizing fuzzy logic and a kernel-based method, enhancing the analysis of changes. Additionally, Pearson correlation coefficients were calculated to explore the relationships between identified land cover change classes and their spatial distribution across nine distinct geographic zones in the Aburrá Valley. The results highlight a marked increase in urbanization, particularly along the valley’s periphery, where previously vegetated areas have been replaced by built environments. Additionally, the visual inspection analysis revealed areas of high variability near river courses and industrial zones, indicating ongoing infrastructure and construction projects. These findings emphasize the rapid and often unplanned nature of urban growth in the region, posing challenges to both natural resource management and environmental conservation efforts. The study underscores the need for the continuous monitoring of land cover changes using advanced remote sensing techniques like SAR, which can overcome the limitations posed by cloud cover and rugged terrain. The conclusions drawn suggest that SAR-based multitemporal analysis is a robust tool for detecting and understanding urbanization’s spatial and temporal dynamics in regions like the Aburrá Valley, providing vital data for policymakers and planners to promote sustainable urban development and mitigate environmental degradation. Full article

The study is dedicated to the statistical optimization of radar imaging of surfaces with the synthetic aperture radar (SAR) technique, assuming a static surface area and applying the ability to move a sensor along a nonlinear trajectory via developing a new method and validating its operability for remote sensing and non-destructive testing. The developed models address the sensing geometry for signals reflected from a surface along with the observation signal–noise equation, including correlation properties. Moreover, the optimal procedures for coherent radar imaging of surfaces with the static SAR technology are synthesized according to the maximum likelihood estimation (MLE). The features of the synthesized algorithm are the decoherence of the received oscillations, the matched filtering of the received signals, and the possibility of using continuous signal coherence. Furthermore, the developed optimal and quasi-optimal algorithms derived from the proposed MLE have been investigated. The novel framework for radio imaging has demonstrated good overall operability and efficiency during simulation modeling (using the MATLAB environment) for real sensing scenes. The developed algorithms of spatio–temporal signal processing in systems with a synthesized antenna with nonlinear carrier trajectories open a promising direction for creating new methods of high-precision radio imaging from UAVs and helicopters. Full article

Distributed radar networks have emerged as a key technology in remote sensing and surveillance due to their high transmission power and robustness against node failures. When performing coherent beamforming with multiple radars, frequency and phase deviations introduced by independent oscillators lead to a decrease in transmission power. This paper proposes an optimized diffuse Kalman filter (ODKF) for the frequency and phase synchronization. Specifically, each radar locally estimates its frequency and phase, then shares this information with neighboring nodes, which are used for incremental update and diffusion update to adjust local estimates. To further reduce synchronization errors, we incorporate a self-feedback strategy in the diffusion step, in which each node balances its own estimate with neighbor information by optimizing the diagonal weights in the diffusion matrix. Numerical simulations demonstrate the superior performance of the proposed method in terms of mean squared deviation (MSD) and convergence speed. Full article

Speckle reduction in Synthetic Aperture Radar (SAR) images is a crucial challenge for effective image analysis and interpretation in remote sensing applications. This study proposes a novel deep learning-based approach using autoencoder architectures for SAR image despeckling, incorporating analysis of variance (ANOVA) for hyperparameter optimization. The research addresses significant gaps in existing methods, such as the lack of rigorous model evaluation and the absence of systematic optimization techniques for deep learning models in SAR image processing. The methodology involves training 240 autoencoder models on real-world SAR data, with performance metrics evaluated using Mean Squared Error (MSE), Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Equivalent Number of Looks (ENL). By employing Pareto frontier optimization, the study identifies models that effectively balance denoising performance with the preservation of image fidelity. The results demonstrate substantial improvements in speckle reduction and image quality, validating the effectiveness of the proposed approach. This work advances the application of deep learning in SAR image denoising, offering a comprehensive framework for model evaluation and optimization. Full article

The exchange of water, sediment, and nutrients in wetlands occurs through a complex network of channels and overbank flow. Although optical sensors can map channels at high resolution, they fail to identify narrow intermittent channels colonized by vegetation. Here we demonstrate an innovative application of rapid-repeat interferometric synthetic aperture radar (InSAR) to study hydrologic connectivity and tidal influences in Louisiana’s coastal wetlands, which can provide valuable insights into water flow dynamics, particularly in vegetation-covered and narrow channels where traditional optical methods struggle. Data used were from the airborne UAVSAR L-band sensor acquired for the Delta-X mission. We applied interferometric techniques to rapid-repeat (~30 min) SAR imagery of the southern Atchafalaya basin acquired during two flights encompassing rising-to-high tides and ebbing-to-low tides. InSAR coherence is used to identify and differentiate permanent open water channels from intermittent channels in which flow occurs underneath the vegetation canopy. The channel networks at rising and ebbing tides show significant differences in the extent of flow, with vegetation-filled small channels more clearly identified at rising-to-high tide. The InSAR phase change is used to identify locations on channel banks where overbank flow occurs, which is a critical component for modeling wetland hydrodynamics. This is the first study to use rapid-repeat InSAR to monitor tidal impacts on water flow dynamics in wetlands. The results show that the InSAR method outperforms traditional optical remote sensing methods in monitoring water flow in vegetation-covered wetlands, providing high-resolution data to support hydrodynamic models and critical support for wetland protection and management. Full article

This paper provides an overview of the three-year effort to design and implement a prototypical sense-and-avoid (SAA) system based on a multisensory architecture leveraging data fusion between optical and radar sensors. The work was carried out within the context of the Italian research project named TERSA (electrical and radar technologies for remotely piloted aircraft systems) undertaken by the University of Pisa in collaboration with its industrial partners, aimed at the design and development of a series of innovative technologies for remotely piloted aircraft systems of small scale (MTOW < 25 Kgf). The system leverages advanced computer vision algorithms and an extended Kalman filter to enhance obstacle detection and tracking capabilities. The “Sense” module processes environmental data through a radar and an electro-optical sensor, while the “Avoid” module utilizes efficient geometric algorithms for collision prediction and evasive maneuver computation. A novel hardware-in-the-loop (HIL) simulation environment was developed and used for validation, enabling the evaluation of closed-loop real-time interaction between the “Sense” and “Avoid” subsystems. Extensive numerical simulations and a flight test campaign demonstrate the system’s effectiveness in real-time detection and the avoidance of non-cooperative obstacles, ensuring compliance with UAV aero mechanical and safety constraints in terms of minimum separation requirements. The novelty of this research lies in (1) the design of an innovative and efficient visual processing pipeline tailored for SWaP-constrained mini-UAVs, (2) the formulation an EKF-based data fusion strategy integrating optical data with a custom-built Doppler radar, and (3) the development of a unique HIL simulation environment with realistic scenery generation for comprehensive system evaluation. The findings underscore the potential for deploying such advanced SAA systems in tactical UAV operations, significantly contributing to the safety of flight in non-segregated airspaces Full article

An innovative and efficient hybrid technique, which combines the Method of Moments (MoM) with Volume Meshed Shooting and Bouncing Ray (VSBR), is presented to analyze the scattering of metallic–dielectric mixed multi-scale structures in urban scenes. Additionally, the technique can rapidly generate radar images at different angles, which is useful for the video remote sensing community. By dividing the mixed multi-scale targets into sub-regions, different solvers are employed to compute the scattering contributions based on their varying electrical sizes. For large-scale sub-regions, the VSBR method is employed on both the medium and metal parts, leading to a multilevel electromagnetic field including both the direct induced field and the multi-reflection field. This field contributes to the integral equation in the MoM sub-regions. Additionally, interactions from the MoM region are considered within the VSBR region, followed by a surface current integration to compute the scattered field. When addressing mixed multi-scale electromagnetic problems, this technique proves to be more efficient and easier to implement in general-purpose computer codes. Furthermore, this method is accelerated using the local coupling (LC) theory and fast multipole method (FMM). Using this fast computational method, efficient simulation results of radar images at different angles for the scenes can be obtained and the numerical results demonstrate the efficiency and accuracy of the proposed method. Full article

Synthetic Aperture Radar (SAR) is a crucial remote sensing technology with significant advantages. Ship detection in SAR imagery has garnered significant attention. However, existing ship detection methods often overlook feature extraction, and the unique imaging mechanisms of SAR images hinder the direct application of conventional natural image feature extraction techniques. Moreover, oriented bounding box-based detection methods often prioritize accuracy excessively, leading to increased parameters and computational costs, which in turn elevate computational load and model complexity. To address these issues, we propose a novel two-stage detector, Burgs-rooted vertex offset encoding scheme (BurgsVO), for detecting rotated ships in SAR images. BurgsVO consists of two key modules: the Burgs equation heuristics module, which facilitates feature extraction, and the average diagonal vertex offset (ADVO) encoding scheme, which significantly reduces computational costs. Specifically, the Burgs equation module integrates temporal information with spatial data for effective feature aggregation, establishing a strong foundation for subsequent object detection. The ADVO encoding scheme reduces parameters through anchor transformation, leveraging geometric similarities between quadrilaterals and triangles to further reduce computational costs. Experimental results on the RSSDD and RSDD benchmarks demonstrate that the proposed BurgsVO outperforms the state-of-the-art detectors in both accuracy and efficiency. Full article