Synthetic Aperture Radar Images Research Articles

Ship Detection in Synthetic Aperture Radar Images Based on BiLevel Spatial Attention and Deep Poly Kernel Network

Synthetic aperture radar (SAR) is a technique widely used in the field of ship detection. However, due to the high ship density, fore-ground-background imbalance, and varying target sizes, achieving lightweight and high-precision multiscale ship object detection remains a significant challenge. In response to these challenges, this research presents YOLO-MSD, a multiscale SAR ship detection method. Firstly, we propose a Deep Poly Kernel Backbone Network (DPK-Net) that utilizes the Optimized Convolution (OC) Module to reduce data redundancy and the Poly Kernel (PK) Module to improve the feature extraction capability and scale adaptability. Secondly, we design a BiLevel Spatial Attention Module (BSAM), which consists of the BiLevel Routing Attention (BRA) and the Spatial Attention Module. The BRA is first utilized to capture global information. Then, the Spatial Attention Module is used to improve the network’s ability to localize the target and capture high-quality detailed information. Finally, we adopt a Powerful-IoU (P-IoU) loss function, which can adjust to the ship size adaptively, effectively guiding the anchor box to achieve faster and more accurate detection. Using HRSID and SSDD as experimental datasets, mAP of 90.2% and 98.8% are achieved, respectively, outperforming the baseline by 5.9% and 6.2% with a model size of 12.3 M. Furthermore, the network exhibits excellent performance across various ship scales.

Automatic Estimation of Tropical Cyclone Centers from Wide-Swath Synthetic-Aperture Radar Images of Miniaturized Satellites

Automatic Estimation of Tropical Cyclone Centers from Wide-Swath Synthetic-Aperture Radar Images of Miniaturized Satellites

SAR images change detection using proposed lamina attention-based noise-resistant UNet advance network (LANRUNet++)

In the past few years, change detection techniques using Convolutional Neural Networks (CNNs) and conventional methods have garnered considerable attention in satellite image analysis. However, both categories of existing approaches have their respective shortcomings. For instance, methods based on CNNs tend to overlook the interactions amongst multilayer convolutions, while traditional methods may contain errors in the initial classification stage that limit the optimization of network. To address these limitations, we propose a new attentionbased, noise-resistant advanced UNet model named as Lamina Attention-Based Noise-Resistant UNet Advance Network (LANRUNet++)for detecting changes in satellite imagery. UNet++ is a unique neural network structure composed of an encoder and decoder, that are linked by a sequence of dense convolutional blocks nested within each other. A core principle underlying the proposed LANRUNet++ is to effectively bridge the semantic disparity between the encoder and decoder feature maps prior to their fusion. We present a lamina attention mechanism within UNet++, which dynamically assigns weights to features extracted from various convolutional layers. This facilitates improved incorporation of spatial context information. Moreover, we added a loss function that is robust to noise and can effectively minimize the influence of inaccurate annotations. As a result, our model becomes less susceptible to errors in initial classification outcomes. Furthermore, we added a Pixel to Density Ratio Parameter that further reduces noisy labels, improving the robustness of the model.We conducted a comprehensive performance assessment of LANRUNet++ on SAR images and conducted a comparative analysis against a range of cutting-edge techniques currently available. The results of our experiments demonstrate that our proposed approach surpasses other existing methods in its ability to detect changes, achieving a higher level of accuracy with various metrics.

Complex-Valued 2D-3D Hybrid Convolutional Neural Network with Attention Mechanism for PolSAR Image Classification

The recently introduced complex-valued convolutional neural network (CV-CNN) has shown considerable advancements for polarimetric synthetic aperture radar (PolSAR) image classification by effectively incorporating both magnitude and phase information. However, a solitary 2D or 3D CNN encounters challenges such as insufficiently extracting scattering channel dimension features or excessive computational parameters. Moreover, these networks’ default is that all information is equally important, consuming vast resources for processing useless information. To address these issues, this study presents a new hybrid CV-CNN with the attention mechanism (CV-2D/3D-CNN-AM) to classify PolSAR ground objects, possessing both excellent computational efficiency and feature extraction capability. In the proposed framework, multi-level discriminative features are extracted from preprocessed data through hybrid networks in the complex domain, along with a special attention block to filter the feature importance from both spatial and channel dimensions. Experimental results performed on three PolSAR datasets demonstrate our present approach’s superiority over other existing ones. Furthermore, ablation experiments confirm the validity of each module, highlighting our model’s robustness and effectiveness.

Detailed detection and extraction of estuarine tidal channels with multispectral and full‐polarised SAR remote sensing

AbstractEstuarine tidal channels are active geomorphic units in tidal flats. However, accurate information on the spatiotemporal changes in tidal channel systems remains scarce. The width of the tidal channels may vary from several kilometres to tens of centimetres. Monitoring tidal channel evolution is complicated because of periodic tidal scouring, anthropogenic activities and sea level rise. In this study, we propose a synergetic classification method to detect and extract morphological information of estuarine tidal channels with a spatial resolution of up to 3 m by fusing PlanetScope multispectral data with C‐band GaoFen‐3 fully polarised Synthetic Aperture Radar (SAR) data and machine learning algorithms. Considering the Yellow River Estuary as an example, the spectral features, vegetation and water index, polarisation and texture features derived from the multispectral and SAR images were selected as input data for classifiers according to feature importance ranking. Comparison to the maximum likelihood, and support vector machine classifiers, the synergetic classification with random forest showed the best performance, with an overall accuracy of 99.6%. Based on these results, the total number of tidal channels in the Yellow River Estuary reached 872, with a total length of 348.8 km. The spatiotemporal changes in the central axis over the last 4 years (2019–2022) suggest that the evolution of tidal channels was mainly controlled by ocean dynamics and anthropogenic activities. This method provides a cost‐effective alternative to accurately map tidal channel systems in global estuarine and coastal zones and helps to quantitatively describe their morphological evolution, stability and drivers.

Geometric calibration of large-scale SAR images using wind turbines as ground control points

ABSTRACT The geometric positioning accuracy of synthetic aperture radar images is a key factor impacting their application, necessitating geometric calibration for improved accuracy. Traditional geometric calibration methods rely on ground calibration fields and supportive equipment such as corner reflectors, which often fall short in meeting both domestic and international geometric calibration demands. To enable convenient, swift, and large-scale or even global SAR calibration, we proposed a method that employs wind turbines as ground control points for SAR geometric calibration, and have constructed a wind turbine database for China. This database allows for precise positioning of wind turbine targets in SAR images. In this study, we applied the wind turbine geometric calibration model for the first time to four imaging modes of Gaofen-3 images. The results indicate that the positioning accuracy post-calibration ranges from 2.70 m to 8.72 m. The mean square error of positioning for the multi-scene calibration of 12 images spanning six provinces is less than 9 m, validating the method's applicability for large-scale calibration. Our proposed method presents a cost-effective solution for large-scale geometric calibration and can notably enhance the positioning accuracy of Gaofen-3 images, thereby increasing their application potential in remote sensing mapping, environmental monitoring, and resource management.

Constraints on the 2013 Saravan intraslab earthquake using permanent GNSS, InSAR and seismic data

SUMMARY On 16 April 2013, an Mw = 7.7 earthquake struck the border of Iran and Pakistan in the central part of the Makran subduction zone with a reported depth of 80 km by USGS. This rare event in this poorly instrumented region helps to shed light on the kinematics of the subducting slab. We investigate source parameters of the Saravan intraslab normal earthquake using RADARSAT-2 SAR images in three ascending tracks, nine permanent GNSS sites and teleseismic data. The maximum coseismic displacement occurred at the SRVN GNSS station with 54.1 mm southeast horizontal and 42.7 mm upward vertical displacements. The coseismic ascending InSAR displacement maps illustrate a continuous and smooth NE-trending elliptical shape deformation pattern with a maximum of ∼29 cm of displacement away from the satellite. We use 25 broad-band teleseismic P-waveforms to estimate the focal mechanism of the main shock. A joint uniform inversion of InSAR, GNSS and teleseismic data reveals a NW-dipping SW-striking fault and a primarily normal-faulting earthquake with a minor right-lateral strike-slip component. The static slip distribution of the InSAR coseismic maps localizes variable slip at depths between 50 and 81 km with a maximum amplitude >3 m at 60–75.5 km depth, rupturing the oceanic crust of the subducted slab. The kinematic slip distribution exhibits a well-constrained slip pattern with a nucleation depth of 65 km. The source time function indicates that the earthquake reaches its maximum moment tensor release at ∼8 and ∼16 s. The NE-trend of the Saravan earthquake slip pattern, the orientation of the volcanic arc, and the distribution of the intraslab intermediate-depth normal earthquakes provide new insights into slab geometry in the central Makran subduction zone. We suggest that the slab bending at the hinge of subducting Arabian Plate is oblique along a NE–SW direction parallel to the volcanic arc rather than the shoreline or deformation front, and it is likely to be the reason for an oblique volcanic arc in the Makran subduction zone. These new constraints on the Makran slab geometry will help further studies in establishing realistic coupling maps for seismic hazard assessment.

Application of Digital Twin Technology in Synthetic Aperture Radar Ground Moving Target Intelligent Detection System

In recent years, the detection performance of SAR-GMTI (synthetic aperture radar-ground moving target indication) algorithm based on deep learning has always been limited by insufficient measured data due to the heavy operation complexity and high cost of real SAR systems. To solve this problem, this paper proposes an overall DT-based implementation framework for SAR ground moving target intelligent detection tasks. In particular, by virtue of a SAR imaging algorithm, a high-fidelity twin replica of SAR moving targets is established in digital space through parameter traversal based on the prior target characteristics of the obtained measured datasets. Then, the constructed SAR twin datasets is fed into the neural network model to train an intelligent detector by fully learning features of the moving targets and preset the SAR scene in the twin space, which can realize the robust detection of ground moving targets in related practical scenarios with no need for multiple and complex field experiments. Moreover, the effectiveness of the proposed framework is verified on the MiniSAR measured system, and a comparison with traditional CFAR detection method is given simultaneously.

BP-YOLOv8: rotating target detection in synthetic aperture radar ship images based on improved YOLOv8

BP-YOLOv8: rotating target detection in synthetic aperture radar ship images based on improved YOLOv8

Attribute Feature Perturbation-Based Augmentation of SAR Target Data.

Large-scale, diverse, and high-quality data are the basis and key to achieving a good generalization of target detection and recognition algorithms based on deep learning. However, the existing methods for the intelligent augmentation of synthetic aperture radar (SAR) images are confronted with several issues, including training instability, inferior image quality, lack of physical interpretability, etc. To solve the above problems, this paper proposes a feature-level SAR target-data augmentation method. First, an enhanced capsule neural network (CapsNet) is proposed and employed for feature extraction, decoupling the attribute information of input data. Moreover, an attention mechanism-based attribute decoupling framework is used, which is beneficial for achieving a more effective representation of features. After that, the decoupled attribute feature, including amplitude, elevation angle, azimuth angle, and shape, can be perturbed to increase the diversity of features. On this basis, the augmentation of SAR target images is realized by reconstructing the perturbed features. In contrast to the augmentation methods using random noise as input, the proposed method realizes the mapping from the input of known distribution to the change in unknown distribution. This mapping method reduces the correlation distance between the input signal and the augmented data, therefore diminishing the demand for training data. In addition, we combine pixel loss and perceptual loss in the reconstruction process, which improves the quality of the augmented SAR data. The evaluation of the real and augmented images is conducted using four assessment metrics. The images generated by this method achieve a peak signal-to-noise ratio (PSNR) of 21.6845, radiometric resolution (RL) of 3.7114, and dynamic range (DR) of 24.0654. The experimental results demonstrate the superior performance of the proposed method.

A Fast Inverse Synthetic Aperture Radar Imaging Scheme Combining GPU-Accelerated Shooting and Bouncing Ray and Back Projection Algorithm under Wide Bandwidths and Angles

A Fast Inverse Synthetic Aperture Radar Imaging Scheme Combining GPU-Accelerated Shooting and Bouncing Ray and Back Projection Algorithm under Wide Bandwidths and Angles

Novel Method for Extraction of Ship Target with Overlaps in SAR Image via EM Algorithm

Novel Method for Extraction of Ship Target with Overlaps in SAR Image via EM Algorithm

More mass wasting activities reported in Sedongpu gully of Tibetan Plateau, China

Although the increase in the frequency of mass wasting events in the Sedongpu gully in recent years indicates that the Sedongpu gully has entered an intense mass wasting period, the current literature focuses only on ice‒rock avalanche events and lacks comprehensive knowledge of Sedongpu gully activity. To clarify the spatiotemporal distribution and scales of mass wasting events, we analysed multiple images from 1969 to present (including optical images and synthetic aperture radar (SAR) images) and topography data from 2013 to present. Since 1969, there have been at least 19 obvious mass wasting events that can be divided into 3 subpatterns: ice‒rock avalanches (IRAs, 8 events), ice‒moraine avalanches (IMAs, 2 events), and glacier debris flows (GDFs, 9 events). Since 2017, the Sedongpu gully has entered the most active period, i.e. more than 68% of events occurred after 2017, and approximately 530 Mm3 and 185 Mm3 of materials were removed from mixtures of glacial and moraine (MGM) and glacial source areas (GSAs). Recent continuous warning states that the temperature of the Sedongpu gully area exceeded 0 °C from April to July 2012, and the 2017 Mw 6.4 Nyingchi earthquake was critical in the current intense erosion state.

Area extraction and growth monitoring of sugarcane from multi-source remote sensing images under a polarimetric SAR data compensation based on buildings

ABSTRACT Aiming at the issue of low accuracy in crop mapping and growth monitoring caused by imprecise calibration of radar time-series data, this paper proposed a Synthetic Aperture Radar (SAR) spatio-temporal error compensation method. By constructing a compensation reference image using the buildings with stable backscattering coefficients in the study area, the error correction of time-series SAR data was realized based on the compensation model. The compensated SAR data were used to establish the Sugarcane Growth Index (SGI) according to the growth curve of sugarcane. The sugarcane area was extracted after combining the compensated SGI and optical image, and the accuracy of F1 on sugarcane distribution extraction was 92.12%. There was an improvement of 4.11% compared with no compensation method. On this basis, the newly planted and ratoon sugarcane were further classified by the expectation maximization algorithm based on the compensated SAR image at the seedling stage. The newly planted sugarcane and the ratoon sugarcane could be accurately distinguished with area extraction accuracy of 82.06% and 80.59%, respectively. Moreover, the compensated SAR data of time series during the tillering to maturity stages were used to estimate the sugarcane height, yielding an R 2 value of 0.717 using a quadratic polynomial model. The Spatio-temporal error compensation method for distributed targets proposed in this study can reduce the loss of SAR data across various times and regions, and achieve accurate results of sugarcane distribution extraction and plant height estimation.

Exploring Distributed Scatterers Interferometric Synthetic Aperture Radar Attributes for Synthetic Aperture Radar Image Classification

Land cover classification of Synthetic Aperture Radar (SAR) imagery is a significant research direction in SAR image interpretation. However, due to the unique imaging methodology of SAR, interpreting SAR images presents numerous challenges, and land cover classification using SAR imagery often lacks innovative features. Distributed scatterers interferometric synthetic aperture radar (DS-InSAR), a common technique for deformation extraction, generates several intermediate parameters during its processing, which have a close relationship with land features. Therefore, this paper utilizes the coherence matrix, the number of statistically homogeneous pixels (SHPs), and ensemble coherence, which are involved in DS-InSAR as classification features, combined with the backscatter intensity of multi-temporal SAR imagery, to explore the impact of these features on the discernibility of land objects in SAR images. The results indicate that the adopted features improve the accuracy of land cover classification. SHPs and ensemble coherence demonstrate significant importance in distinguishing land features, proving that these proposed features can serve as new attributes for land cover classification in SAR imagery.

Mitigation of Suppressive Interference in AMPC SAR Based on Digital Beamforming

Multichannel Synthetic Aperture Radar (MC-SAR) systems, such as Azimuth Multi-Phase Centre (AMPC) SAR, provide an effective solution for achieving high-resolution wide-swath (HRWS) imaging by reducing the pulse repetition frequency (PRF) to increase the swath width. However, in an Electronic Countermeasures (ECM) environment, the image quality of multichannel SAR systems can be significantly degraded by electromagnetic interference. Previous research into interference and counter-interference techniques has predominantly focused on single-channel SAR systems, with relatively few studies addressing the specific challenges faced by MC-SAR systems. This paper uses the classical spatial filtering technique of adaptive digital beamforming (DBF). Considering the Doppler ambiguity present in the echoes, two schemes—Interference Reconstruction And Cancellation (IRC) and Channel Grouping Nulling (CGN)—are designed to effectively eliminate suppressive interference. The IRC method eliminates the effects of interference without losing spatial degrees of freedom, ensuring effective suppression of Doppler ambiguity in subsequent processing. This method shows significant advantages under conditions of strong Doppler ambiguity and low jammer-to-signal ratio. Conversely, the CGN method mitigates the effect of interference on multichannel imaging at the expense of degrees of freedom redundant to Doppler ambiguity suppression. It shows remarkable interference suppression performance under weak-Doppler-ambiguity conditions, allowing for better image recovery. Simulations performed on point and distributed targets have validated that the proposed methods can effectively remove interfering signals and achieve high-resolution wide-swath (HRWS) SAR images.

A change detection algorithm for the SAR images based on DWT and DE optimization

ABSTRACT In this paper, a novel change detection algorithm is proposed for the remote sensing Synthetic Aperture Radar (SAR) images. Change detection in SAR images is one of the critical tasks in the field of remote sensing as the images contain significant speckle noise and illumination variations. In order to address these issues, a novel change detection algorithm is proposed using Discrete Wavelet Transform (DTW) and Differential Evaluation (DE). At first, the DWT is utilized to remove the speckle noise from the images. Then, a DE optimization-based Support Vector Machine (SVM) algorithm is proposed to detect the changes in SAR images. The proposed method can give comparatively better correct classification values, and lesser false alarm as well as total error values than the recently developed change detection methods.

High-resolution wide-swath SAR imaging with multifrequency pulse diversity mode in azimuth multichannel system

ABSTRACT High-resolution wide-swath (HRWS) imaging has emerged as a focal point in synthetic aperture radar (SAR) research. However, conventional SAR systems face challenges in achieving both high azimuth resolution and wide swath simultaneously due to the minimum antenna area constraint. In this paper, we propose a HRWS imaging method based on multifrequency pulse diversity (MFPD) and azimuth multichannel (AMC) technique, capable of resolving range and Doppler ambiguities concurrently. In MFPD mode, range ambiguous echoes can be separated by matched filters in the range frequency domain, as multifrequency pulses are transmitted by a single channel in the transmitter. To further enhance the ambiguity resolution ability of the system and address azimuth incoherence, a novel scheme applying the MFPD to AMC system is proposed, categorized into two distinct scenarios. 1) Uniform Sampling: This scenario satisfies the displaced phase centre antenna condition. Under this condition, high range resolution imaging can be achieved through spectrum splicing in range frequency domain, simultaneously resolving Doppler ambiguity. 2) Non-uniform Sampling: In this scenario, the ambiguous echoes are processed by spatial digital beamforming and spectrum splicing in two-dimensional frequency domain. Finally, the HRWS imaging can be obtained by performing the traditional SAR algorithm. Furthermore, the proposed method can synthesize a wideband signal from multifrequency signals, thereby enhancing the feasibility of super-high-resolution imaging. Simulation results demonstrate the effectiveness of the proposed method.

Large-scale building damage assessment based on recurrent neural networks using SAR coherence time series: A case study of 2023 Turkey–Syria earthquake

The Turkey–Syria earthquakes that occurred on February 6, 2023, have caused significant human casualties and economic damage. Emergency services require quick and accurate assessments of widespread building damage in affected areas. This can be facilitated by using remote sensing methods, specifically all-day and all-weather Synthetic Aperture Radar (SAR). In this study, we aimed to improve the detection of building anomalies in earthquake-affected areas using SAR images. To achieve this, we employed Recurrent Neural Network (RNN) to train coherence time series and predict co-seismic coherence. This approach allowed us to generate a Damage Proxy Map (DPM) for building damage assessment. The results of our study indicated that the estimated proportion of building damage in Kahramanmaras was approximately 24.08%. These findings were consistent with the actual damage observed in the field. Moreover, when utilizing the mean and standard deviation of coherence time series, our method achieved higher accuracy (0.761) and a lower false alarm rate (0.136) compared to directly using coherence with only two views of SAR data. Overall, our study demonstrates that this method provides an accurate and reliable approach for post-earthquake building damage assessment.

Parcel-Based Sugarcane Mapping Using Smoothed Sentinel-1 Time Series Data

The timely and accurate mapping of sugarcane cultivation is significant to ensure the sustainability of the sugarcane industry, including sugarcane production, rural society, sugar futures, and crop insurance. Synthetic aperture radar (SAR), due to its all-weather and all-time imaging capability, plays an important role in mapping sugarcane cultivation in cloudy areas. However, the inherent speckle noise of SAR data worsens the “salt and pepper” effect in the sugarcane map. Therefore, in previous studies, an additional land cover map or optical image was still required. This study proposes a new application paradigm of time series SAR data for sugarcane mapping to tackle this limitation. First, the locally estimated scatterplot smoothing (LOESS) smoothing technique was exploited to reconstruct time series SAR data and reduce SAR noise in the time domain. Second, temporal importance was evaluated using RF MDA ranking, and basic parcel units were obtained only based on multi-temporal SAR images with high importance values. Lastly, the parcel-based classification method, combining time series smoothing SAR data, RF classifier, and basic parcel units, was used to generate a sugarcane extent map without unreasonable sugarcane spots. The proposed paradigm was applied to map sugarcane cultivation in Suixi County, China. Results showed that the proposed paradigm was able to produce an accurate sugarcane cultivation map with an overall accuracy of 96.09% and a Kappa coefficient of 0.91. Compared with the pixel-based classification result with original time series SAR data, the new paradigm performed much better in reducing the “salt and pepper” spots and improving the completeness of the sugarcane plots. In particular, the unreasonable non-vegetation spots in the sugarcane map were eliminated. The results demonstrated the efficacy of the new paradigm for mapping sugarcane cultivation. Unlike traditional methods that rely on optical remote sensing data, the new paradigm offers a high level of practicality for mapping sugarcane in large regions. This is particularly beneficial in cloudy areas where optical remote sensing data is frequently unavailable.