Search Results (2,088)

Moving target detection is one of the most important tasks of radar systems. The clutter echo received by radar is usually strong and heterogeneous when the radar works in a complex terrain environment, resulting in performance degradation in moving target detection. Utilizing prior knowledge of the clutter distribution in the space–time domain, this paper proposes a novel moving target detection network based on small-sample transfer learning and attention mechanism. The proposed network first utilizes offline data to train the feature extraction network and reduce the online training time. Meanwhile, the attention mechanism used for feature extraction is applied in the beam-Doppler domain to improve classification accuracy of targets. Then, a small amount of real-time data are applied to a small-sample transfer network to fine-tune the feature extraction network. Finally, the target detection can be realized by the fine-tuned network. Simulation experiments show that the proposed network can eliminate the influence of heterogeneous clutter on moving target detection, and the attention mechanism can improve clutter suppression under a low signal-to-noise ratio regime. The proposed network has a lower computational load compared to conventional neural networks, enabling its use in real-time applications on space-borne/airborne radars. Full article

Reclamation is an effective strategy for alleviating land scarcity in coastal areas, thereby providing additional arable land and opportunities for marine ranching. Monitoring the safety of artificial reclamation embankments is crucial for protecting these reclaimed areas. This study employed synthetic aperture radar interferometry (InSAR) using 224 Sentinel-1A data, spanning from 9 January 2016 to 8 April 2024, to investigate the deformation characteristics of the coastal reclamation embankment in Funing Bay, China. We optimized the phase-unwrapping network by employing ambiguity-detection and redundant-observation methods to facilitate the multitemporal InSAR phase-unwrapping process. The deformation results indicated that the maximum observed land subsidence rate exceeded 50 mm per year. The Funing Bay embankment exhibited a higher level of internal deformation than areas closer to the sea. Time-series analysis revealed a gradual deceleration in the deformation rate. Furthermore, a geotechnical model was utilized to predict future deformation trends. Understanding the spatial dynamics of deformation characteristics in the Funing Bay reclamation embankment will be beneficial for ensuring the safe operation of future coastal reclamation projects. Full article

Recurring polarimetric radar signatures in supercells include deep and persistent differential reflectivity (Z_DR) columns, hail inferred in low-level scans, and the Z_DR arc signature. Prior investigations of supercell polarimetric signatures reveal positive correlations between the Z_DR column depth and cross-sectional area and quantitative characteristics of the radar reflectivity field. This study expands upon prior work by examining temporal associations between supercell polarimetric radar signatures, incorporating a dataset of relatively discrete, right-moving supercells from the continental United States observed by the Weather Surveillance Radar 1988-Doppler (WSR-88D) network. Cross-correlation coefficients were calculated between the Z_DR column area and depth and the base-scan hail area, Z_DR arc area, and mean Z_DR arc value. These correlation values were computed with a positive and negative lag time of up to 45 min. Results of the lag correlation analysis are consistent with prior observations indicative of storm cycling, including temporal associations between Z_DR columns and inferred hail signatures/Z_DR arcs in both tornadic and nontornadic supercells, but were most pronounced in tornadic storms. Full article

The contamination of marine ecosystems by oil spills poses a significant threat to the marine environment, necessitating the prompt and effective implementation of measures to mitigate the associated damage. Satellites offer a spatial and temporal advantage over aircraft and unmanned aerial vehicles (UAVs) in oil spill detection due to their wide-area monitoring capabilities. While oil spill detection has traditionally relied on synthetic aperture radar (SAR) images, the combined use of optical satellite sensors alongside SAR can significantly enhance monitoring capabilities, providing improved spatial and temporal coverage. The advent of deep learning methodologies, particularly convolutional neural networks (CNNs) and Transformer models, has generated considerable interest in their potential for oil spill detection. In this study, we conducted a comprehensive and objective comparison to evaluate the suitability of CNN and Transformer models for marine oil spill detection. High-resolution optical satellite images were used to optimize DeepLabV3+, a widely utilized CNN model; Swin-UPerNet, a representative Transformer model; and Mask2Former, which employs a Transformer-based architecture for both encoding and decoding. The results of cross-validation demonstrate a mean Intersection over Union (mIoU) of 0.740, 0.840 and 0.804 for all the models, respectively, indicating their potential for detecting oil spills in the ocean. Additionally, we performed a histogram analysis on the predicted oil spill pixels, which allowed us to classify the types of oil. These findings highlight the considerable promise of the Swin Transformer models for oil spill detection in the context of future marine disaster monitoring. Full article

Synthetic Aperture Radar (SAR) imaging plays a vital role in maritime surveillance, yet the detection of small vessels poses a significant challenge when employing conventional Constant False Alarm Rate (CFAR) techniques, primarily due to the limitations in resolution and the presence of clutter. Deep learning (DL) offers a promising alternative, yet it still struggles with identifying small targets in complex SAR backgrounds because of feature ambiguity and noise. To address these challenges, our team has developed the AFSC network, which combines anti-aliasing techniques with fully shared convolutional layers to improve the detection of small targets in SAR imagery. The network is composed of three key components: the Backbone Feature Extraction Module (BFEM) for initial feature extraction, the Neck Feature Fusion Module (NFFM) for consolidating features, and the Head Detection Module (HDM) for final object detection. The BFEM serves as the principal feature extraction technique, with a primary emphasis on extracting features of small targets, The NFFM integrates an anti-aliasing element and is designed to accentuate the feature details of diminutive objects throughout the fusion procedure, HDM is the detection head module and adopts a new fully shared convolution strategy to make the model more lightweight. Our approach has shown better performance in terms of speed and accuracy for detecting small targets in SAR imagery, surpassing other leading methods on the SSDD dataset. It attained a mean Average Precision ($AP$) of 69.3% and a specific $AP$ for small targets ($A{P}_S$) of 66.5%. Furthermore, the network’s robustness was confirmed using the HRSID dataset. Full article

Electromagnetic technology is widely applied in numerous fields, and precise electromagnetic characteristic fitting technology has become a crucial part for enhancing system performance and optimizing design. However, it faces challenges such as high computational complexity and the difficulty in balancing the accuracy and generalization ability of the model. For example, the Radar Cross Section (RCS) distribution characteristics of a single corner reflector model or Luneberg lens provide a relatively stable RCS value within a certain airspace range, which to some extent reduces the difficulty of radar target detection and fails to truly evaluate the radar performance. This paper aims to propose an innovative multi-parameter optimization method for electromagnetic characteristic fitting based on deep learning. By selecting common targets such as reflectors and Luneberg lens reflectors as optimization variables, a deep neural network model is constructed and trained with a large amount of electromagnetic data to achieve high-precision fitting of the target electromagnetic characteristics. Meanwhile, an advanced genetic optimization algorithm is introduced to optimize the multiple parameters of the model to meet the error index requirements of radar target detection. In this paper, by combining specific optimization variables such as corner reflectors and Luneberg lenses with the deep learning model and genetic algorithm, the deficiencies of traditional methods in handling electromagnetic characteristic fitting are effectively addressed. The experimental results show that the 60° corner reflector successfully realizes the simulation of multiple peak characteristics of the target, and the Luneberg lens reflector achieves the simulation of a relatively small RCS average value with certain fluctuations in a large space range, which strongly proves that this method has significant advantages in improving the fitting accuracy and optimization efficiency, opening up new avenues for research and application in the electromagnetic field. Full article

Deep neural networks (DNNs) have achieved great success in various computer vision tasks. However, they are susceptible to artificially designed adversarial perturbations, which limit their deployment in security-critical applications. In this paper, we propose a gradual adversarial training (GAT) method for remote sensing image segmentation. Our method incorporates a domain-adaptive mechanism that dynamically modulates input data, effectively reducing adversarial perturbations. GAT not only improves segmentation accuracy on clean images but also significantly enhances robustness against adversarial attacks, all without necessitating changes to the network architecture. The experimental results demonstrate that GAT consistently outperforms conventional standard adversarial training (SAT), showing increased resilience to adversarial attacks of varying intensities on both optical and Synthetic Aperture Radar (SAR) images. Compared to the SAT defense method, GAT achieves a notable defense performance improvement of 1% to 12%. Full article

Speckle noise is a granular interference that degrades image quality in coherent imaging systems, including underwater sonar, Synthetic Aperture Radar (SAR), and medical ultrasound. This study aims to enhance speckle noise reduction through advanced deep learning techniques. We introduce the Deep Gradient-Guidance Network (DGGNet), which features an architecture comprising one encoder and two decoders—one dedicated to image recovery and the other to gradient preservation. Our approach integrates a gradient map and fractional-order total variation into the loss function to guide training. The gradient map provides structural guidance for edge preservation and directs the denoising branch to focus on sharp regions, thereby preventing over-smoothing. The fractional-order total variation mitigates detail ambiguity and excessive smoothing, ensuring rich textures and detailed information are retained. Extensive experiments yield an average Peak Signal-to-Noise Ratio (PSNR) of 31.52 dB and a Structural Similarity Index (SSIM) of 0.863 across various benchmark datasets, including McMaster, Kodak24, BSD68, Set12, and Urban100. DGGNet outperforms existing methods, such as RIDNet, which achieved a PSNR of 31.42 dB and an SSIM of 0.853, thereby establishing new benchmarks in speckle noise reduction. Full article

In response to the shortcomings of current spatiotemporal prediction models, which frequently encounter difficulties in temporal feature extraction and the forecasting of medium to high echo intensity regions over extended sequences, this study presents a novel model for radar echo extrapolation that combines a translator encoder-decoder architecture with a spatiotemporal dual-discriminator conditional generative adversarial network (STD-TranslatorNet). Initially, an image reconstruction network is established as the generator, employing a combination of a temporal attention unit (TAU) and an encoder–decoder framework. Within this architecture, both intra-frame static attention and inter-frame dynamic attention mechanisms are utilized to derive attention weights across image channels, thereby effectively capturing the temporal evolution of time series images. This approach enhances the network’s capacity to comprehend local spatial features alongside global temporal dynamics. The encoder–decoder configuration further bolsters the network’s proficiency in feature extraction through image reconstruction. Subsequently, the spatiotemporal dual discriminator is crafted to encapsulate both temporal correlations and spatial attributes within the generated image sequences. This design serves to effectively steer the generator’s output, thereby augmenting the realism of the produced images. Lastly, a composite multi-loss function is proposed to enhance the network’s capability to model intricate spatiotemporal evolving radar echo data, facilitating a more comprehensive assessment of the quality of the generated images, which in turn fortifies the network’s robustness. Experimental findings derived from the standard radar echo dataset (SRAD) reveal that the proposed radar echo extrapolation technique exhibits superior performance, with average critical success index (CSI) and probability of detection (POD) metrics per frame increasing by 6.9% and 7.6%, respectively, in comparison to prior methodologies. Full article

Reliable environmental perception capabilities are a prerequisite for achieving autonomous driving. Cameras and LiDAR are sensitive to illumination and weather conditions, while millimeter-wave radar avoids these issues. Existing models rely heavily on image-based approaches, which may not be able to fully characterize radar sensor data or efficiently further utilize them for perception tasks. This paper rethinks the approach to modeling radar signals and proposes a novel U-shaped multilayer perceptron network (U-MLPNet) that aims to enhance the learning of omni-dimensional spatio-temporal dependencies. Our method involves innovative signal processing techniques, including a 3D CNN for spatio-temporal feature extraction and an encoder–decoder framework with cross-shaped receptive fields specifically designed to capture the sparse and non-uniform characteristics of radar signals. We conducted extensive experiments using a diverse dataset of urban driving scenarios to characterize the sensor’s performance in multi-view semantic segmentation and object detection tasks. Experiments showed that U-MLPNet achieves competitive performance against state-of-the-art (SOTA) methods, improving the mAP by 3.0% and mDice by 2.7% in RD segmentation and AR and AP by 1.77% and 2.03%, respectively, in object detection. These improvements signify an advancement in radar-based perception for autonomous vehicles, potentially enhancing their reliability and safety across diverse driving conditions. Full article

Linear frequency modulation (LFM) signals are pivotal in radar systems, enabling high-resolution measurements and target detection. However, these signals are often degraded by noise, significantly impacting their processing and interpretation. Traditional denoising methods, including wavelet-based techniques, have been extensively used to address this issue, yet they often fall short in terms of optimizing performance due to fixed parameter settings. This paper introduces an innovative approach by combining wavelet denoising with long short-term memory (LSTM) networks specifically tailored for LFM signals in radar systems. By generating a dataset of LFM signals at various signal-to-noise Ratios (SNR) to ensure diversity, we systematically identified the optimal wavelet parameters for each noisy instance. These parameters served as training labels for the proposed LSTM-based architecture, which learned to predict the most effective denoising parameters for a given noisy LFM signal. Our findings reveal a significant enhancement in denoising performance, attributed to the optimized wavelet parameters derived from the LSTM predictions. This advancement not only demonstrates a superior denoising capability but also suggests a substantial improvement in radar signal processing, potentially leading to more accurate and reliable radar detections and measurements. The implications of this paper extend beyond modern radar applications, offering a framework for integrating deep learning techniques with traditional signal processing methods to optimize performance across various noise-dominated domains. Full article

Soil piping erosion is an underground soil erosion process that is significantly underestimated or overlooked. It can lead to intense soil erosion and trigger surface processes such as landslides, collapses, and channel erosion. Conducting susceptibility mapping is a vital way to identify the potential for soil piping erosion, which is of enormous significance for soil and water conservation as well as geological disaster prevention. This study utilized airborne radar drones to survey and map 1194 sinkholes in Sunjiacha basin, Huining County, on the Loess Plateau in Northwest China. We identified seventeen key hydrogeomorphological factors that influence sinkhole susceptibility and used six machine learning models—support vector machine (SVM), logistic regression (LR), Convolutional Neural Network (CNN), K-Nearest Neighbors (KNN), random forest (RF), and gradient boosting decision tree (GBDT)—for the susceptibility assessment and mapping of loess sinkholes. We then evaluated and validated the prediction results of various models using the area under curve (AUC) of the Receiver Operating Characteristic Curve (ROC). The results showed that all six of these machine learning algorithms had an AUC of more than 0.85. The GBDT model had the best predictive accuracy (AUC = 0.94) and model migration performance (AUC = 0.93), and it could find sinkholes with high and very high susceptibility levels in loess areas. This suggests that the GBDT model is well suited for the fine-scale susceptibility mapping of sinkholes in loess regions. Full article

Synthetic aperture radar (SAR) is often affected by other high-power electromagnetic devices during ground observation, which causes unintentional radio frequency interference (RFI) with the acquired echo, bringing adverse effects into data processing and image interpretation. When faced with the task of screening massive SAR data, there is an urgent need for the global perception and detection of interference. The existing RFI detection method usually only uses a single type of data for detection, ignoring the information association between the data at all levels of the real SAR product, resulting in some computational redundancy. Meanwhile, current deep learning-based algorithms are often unable to locate the range of RFI coverage in the azimuth direction. Therefore, a novel RFI processing framework from quick-looks to single-look complex (SLC) data and then to raw echo is proposed. We take the data of Sentinel-1 terrain observation with progressive scan (TOPS) mode as an example. By combining the statistics-assisted network with the sliding-window algorithm and the error-tolerant training strategy, it is possible to accurately detect and locate RFI in the quick looks of an SLC product. Then, through the analysis of the TOPSAR imaging principle, the position of the RFI in the SLC image is preliminarily confirmed. The possible distribution of the RFI in the corresponding raw echo is further inferred, which is one of the first attempts to use spaceborne SAR data to elucidate the RFI location mapping relationship between image data and raw echo. Compared with directly detecting all of the SLC data, the time for the proposed framework to determine the RFI distribution in the SLC data can be shortened by 53.526%. All the research in this paper is conducted on Sentinel-1 real data, which verify the feasibility and effectiveness of the proposed framework for radio frequency signals monitoring in advanced spaceborne SAR systems. Full article

The application of joint sensing and communications (JSACs) technology in air–ground networks, which include unmanned aerial vehicles (UAVs), offers unique opportunities for improving both sensing and communication performances. However, this type of network is also sensitive to the peculiar characteristics of the aerial communications environment, which include shadowing and scattering caused by man-made structures. This paper investigates an aerial JSAC network and proposes a UAV-selection strategy that is shown to improve the communication performance. We first derive analytical expressions for the received signal-to-interference ratio for both communication and sensing functions. These expressions are then used to analyze the outage and coverage probability of the communication part, as well as the ergodic radar estimation information rate and the detection probability of the sensing part. Moreover, a performance trade-off is investigated under the assumption of a total bandwidth constraint. Various numerical evaluated results have been presented complemented by equivalent simulated ones. These results reveal the applicability of the proposed analysis, as well as the impact of shadowing and multipath fading severity, and interference on the system’s performance. Full article

Axial estimation is an important task for detecting non-cooperative space targets in orbit, with inverse synthetic aperture radar (ISAR) imaging serving as a fundamental approach to facilitate this process. However, most of the existing axial estimation methods usually rely on manually extracting and matching features of key corner points or linear structures in the images, which may result in a degradation in estimation accuracy. To address these issues, this paper proposes an axial estimation method for spaceborne targets via ISAR image sequences based on a regression network. Firstly, taking the ALOS satellite as an example, its Computer-Aided Design (CAD) model is constructed through a prior analysis of its structural features. Subsequently, target echoes are generated using electromagnetic simulation software, followed by imaging processing, analysis of imaging characteristics, and the determination of axial labels. Finally, in contrast to traditional classification approaches, this study introduces a straightforward yet effective regression network specifically designed for ISAR image sequences. This network transforms the classification loss into a loss function constrained by the minimum mean square error, which can be utilized to adaptively perform the feature extraction and estimation of axial parameters. The effectiveness of the proposed method is validated through both electromagnetic simulations and experimental data. Full article