Radar Images Research Articles

Deep-Learning for Change Detection Using Multi-Modal Fusion of Remote Sensing Images: A Review

Remote sensing images provide a valuable way to observe the Earth’s surface and identify objects from a satellite or airborne perspective. Researchers can gain a more comprehensive understanding of the Earth’s surface by using a variety of heterogeneous data sources, including multispectral, hyperspectral, radar, and multitemporal imagery. This abundance of different information over a specified area offers an opportunity to significantly improve change detection tasks by merging or fusing these sources. This review explores the application of deep learning for change detection in remote sensing imagery, encompassing both homogeneous and heterogeneous scenes. It delves into publicly available datasets specifically designed for this task, analyzes selected deep learning models employed for change detection, and explores current challenges and trends in the field, concluding with a look towards potential future developments.

FV-DLV3+: a light-weight flooded vegetation extraction method with attention-based DeepLabv3+

ABSTRACT Climate change and human activities have led to a decline in wetland vegetation and sharp reduction of wetland area, which has caused considerable damage to the hydrological cycle and ecological functions of many wetlands. Flooded vegetation (FV) is an important wetland landscape, and strengthening the research on methods of the extracting FV using remote sensing or aerial photos plays an important role in monitoring changes to wetlands. This paper used optical satellite and synthetic aperture radar satellite images as data sources, construct a set of feature variable sets suitable for FV extraction; in addition, a deep learning method based on the semantic segmentation model DeepLabv3+, FV-DLV3+, is proposed for FV extraction. The method adopts the lightweight MobileNetV2 model as the backbone feature extraction network, introduces the SegFormer network to make up for the feature information loss caused by MobileNetV2, and further captures more effective features and suppresses the interference of the background through an attention mechanism to enhance the ability to extract feature boundaries, thereby improving the accuracy of FV extraction. Taking the wetland of Poyang Lake as the experimental area, Landsat 8 and Sentinel-1A satellite data were selected as the data sources to produce a deep learning dataset, and U-Net, DeepLabv3+, Swin-Unet, Swin Transformer, and CVTNet were selected for comparison when conducting model training and validating experiments. The results show that FV-DLV3+ has an excellent effect on FV extraction of the Poyang Lake wetland, which effectively reduces the computational complexity of the process while improving extraction accuracy; the mean intersection over union of this paper’s method was higher than the five above-mentioned methods, which was 12.93% and 5.85% higher than that of DeepLabv3+ and CVTNet, respectively.

Deep Learning-Based Approximated Observation Sparse SAR Imaging via Complex-Valued Convolutional Neural Network

Sparse synthetic aperture radar (SAR) imaging has demonstrated excellent potential in image quality improvement and data compression. However, conventional observation matrix-based methods suffer from high computational overhead, which is hard to use for real data processing. The approximated observation sparse SAR imaging method relieves the computation pressure, but it needs to manually set the parameters to solve the optimization problem. Thus, several deep learning (DL) SAR imaging methods have been used for scene recovery, but many of them employ dual-path networks. To better leverage the complex-valued characteristics of echo data, in this paper, we present a novel complex-valued convolutional neural network (CNN)-based approximated observation sparse SAR imaging method, which is a single-path DL network. Firstly, we present the approximated observation-based model via the chirp-scaling algorithm (CSA). Next, we map the process of the iterative soft thresholding (IST) algorithm into the deep network form, and design the symmetric complex-valued CNN block to achieve the sparse recovery of large-scale scenes. In comparison to matched filtering (MF), the approximated observation sparse imaging method, and the existing DL SAR imaging methods, our complex-valued network model shows excellent performance in image quality improvement especially when the used data are down-sampled.

Microwave Coincidence Imaging with Phase-Coded Stochastic Radiation Field

Microwave coincidence imaging (MCI) represents a novel forward-looking radar imaging method with high-resolution capabilities. Most MCI methods rely on random frequency modulation to generate stochastic radiation fields, which introduces the complexity of radar systems and imposes limitations on imaging quality under noisy conditions. In this paper, microwave coincidence imaging with phase-coded stochastic radiation fields is proposed, which generates spatio-temporally uncorrelated stochastic radiation fields with phase coding. Firstly, the radiation field characteristics are analyzed, and the coding sequences are designed. Then, pulse compression is applied to achieve a one-dimensional range image. Furthermore, an azimuthal imaging model is built, and a reference matrix is derived from the frequency domain. Finally, sparse Bayesian learning (SBL) and alternating direction method of multipliers (ADMM)-based total variation are implemented to reconstruct targets. The methods have better imaging performance at low signal-to-noise ratios (SNRs), as shown by the imaging results and mean square error (MSE) curves. In addition, compared with the SBL and ADMM-based total variation methods based on the direct frequency-domain solution, the proposed method’s computational complexity is reduced, giving it great potential in forward-looking high-resolution scenarios, such as autonomous obstacle avoidance with vehicle-mounted radar and terminal guidance.

Monitoring Crop Condition at Gield Scales and at a Daily Time Step Using Synthetic Aperture Radar (SAR)

Operations that rely on optically-based Normalized Difference Vegetation Index (NDVI) to track crop productivity, are negatively impacted by cloud cover. In this research, parameters from Synthetic Aperture Radar (SAR) imagery were calibrated to NDVI with the targeted outcome to integrate SAR into Canadian crop monitoring services. Data from fully polarimetric RADARSAT-2 and dual-polarization Sentinel-1B imagery were calibrated to Sentinel-2 NDVI. Random Forest Regression (RFR) and Least Squares Boosting (LSBoost) were tested to calibrate SAR to NDVI (SARcal-NDVI) for six crops (corn, canola, soybeans, wheat, oats and barley). RADARSAT-2 provided the best fit with R2 exceeding 0.84 for canola, 0.87 for wheat and 0.90 for corn and soybeans. Correlations were lower for oats (R2 of 0.72–0.77) and barley (R2 of 0.43–0.64) due to a limited number of fields. Although a global model yielded lower correlations (R2 of 0.80), this model would be easier to implement into operations. Total power, the first and second eigenvalues and VH backscatter were important in reducing model error. The SARcal-NDVI and Growing Degree Days were then integrated into a Crop Structure Dynamic Model to produce daily estimates of crop condition, at field scales. The next step is to test if these daily estimates of crop condition can improve crop yield forecasting for the Canadian agriculture sector.

Adaptive iterative thresholding segmentation method guided by optical prior water body information in extracting urban flood inundation areas of synthetic aperture radar images

Adaptive iterative thresholding segmentation method guided by optical prior water body information in extracting urban flood inundation areas of synthetic aperture radar images

Antarctic ice-shelf meltwater outflows in satellite radar imagery: ground-truthing and basal channel observations

Abstract Ice shelves regulate the flow of the Antarctic ice sheet toward the ocean and its contribution to sea-level rise. Accurately monitoring the basal and surface melting of ice shelves is therefore essential for predicting the ice sheet's response to climatic warming. In this study, we utilize Sentinel-1A synthetic aperture radar satellite imagery combined with shipboard measurements of water temperature and salinity to investigate the presence of surficial meltwater plumes along the Antarctic coastline. Our approach reveals a strong correlation between areas of pronounced low radar backscatter extending from ice shelves and significant decreases in water temperature and salinity, suggesting meltwater-enriched ocean waters. We propose that the low radar backscatter signature of meltwater outflows is caused by stable stratification of the upper water column, driven by density contrasts from buoyant, low-salinity meltwater and surface current shear that reduce Bragg scattering waves. The resulting smooth water surfaces were observed adjacent to the surface expression of deep basal channels, documented in a helicopter survey along part of the Bellingshausen Sea ice edge. We present high-temporal resolution satellite radar as a tool for identifying meltwater release from beneath ice shelves, capable of all-weather, day-and-night imaging.

Improving Alaska flood monitoring with synthetic aperture radar imagery (DOC)

Improving Alaska flood monitoring with synthetic aperture radar imagery (DOC)

Electromagnetic and Radon Earthquake Precursors

Earthquake forecasting is arguably one of the most challenging tasks in Earth sciences owing to the high complexity of the earthquake process. Over the past 40 years, there has been a plethora of work on finding credible, consistent and accurate earthquake precursors. This paper is a cumulative survey on earthquake precursor research, arranged into two broad categories: electromagnetic precursors and radon precursors. In the first category, methods related to measuring electromagnetic radiation in a wide frequency range, i.e., from a few Hz to several MHz, are presented. Precursors based on optical and radar imaging acquired by spaceborne sensors are also considered, in the broad sense, as electromagnetic. In the second category, concentration measurements of radon gas found in soil and air, or even in ground water after being dissolved, form the basis of radon activity precursors. Well-established mathematical techniques for analysing data derived from electromagnetic radiation and radon concentration measurements are also described with an emphasis on fractal methods. Finally, physical models of earthquake generation and propagation aiming at interpreting the foundation of the aforementioned seismic precursors, are investigated.

Research on Radar Target Detection Based on the Electromagnetic Scattering Imaging Algorithm and the YOLO Network

In this paper, the radar imaging technology based on the time-domain (TD) electromagnetic scattering algorithm is used to generate image datasets quickly and apply them to target detection research. Considering that radar images are different from optical images, this paper proposes an improved strategy for the traditional You Only Look Once (YOLO)v3 network to improve target detection accuracy on radar images. The speckle noise in radar images can cover the real information of a target image and increase the difficulty of target detection. The attention mechanisms are added to the traditional YOLOv3 network to strengthen the weight of the target region. By comparing the target detection accuracy under different attention mechanisms, an attention module with higher detection accuracy is obtained. The validity of the proposed detection network is verified on a simulation dataset, a measured real dataset, and a mixed dataset. This paper is about an interdisciplinary study of computational electromagnetics, remote sensing, and artificial intelligence. Experiments verify that the proposed composite network has better detection performance.

Development of a Storm-Tracking Algorithm for the Analysis of Radar Rainfall Patterns in Athens, Greece

This research work focuses on the development and application of a storm-tracking algorithm for identifying and tracking storm cells. The algorithm first identifies storm cells on the basis of reflectivity thresholds and then matches the cells in the tracking procedure on the basis of their geometrical characteristics and the distance within the weather radar image. A sensitivity analysis was performed to evaluate the preferable thresholds for each case and test the algorithm’s ability to perform in different time step resolutions. Following this, we applied the algorithm to 54 rainfall events recorded by the National Technical University X-Band weather radar, the rainscanner system, from 2018 to 2023 in the Attica region of Greece. Testing of the algorithm demonstrated its efficiency in tracking storm cells over various time intervals and reflecting changes such as merging or dissipation. The results reveal the predominant southwest-to-east storm directions in 40% of cases examined, followed by northwest-to-east and south-to-north patterns. Additionally, stratiform storms showed slower north-to-west trajectories, while convective storms exhibited faster west-to-east movement. These findings provide valuable insights into storm behavior in Athens and highlight the algorithm’s potential for integration into nowcasting systems, particularly for flood early warning systems.

Enhanced SAR Compression through Multi-Look Doppler Compensation and Auto-Focusing Technique.

This paper presents a simple and streamlined compensation technique for improving the quality of synthetic aperture radar (SAR) images based on the Range Doppler Algorithm (RDA). Incorrect Doppler estimation in the space orbit, caused by unexpected radar motion errors, orbit mismatches, and other factors, can significantly degrade SAR image quality. These inaccuracies result in mismatches between the azimuth-matched filter and the received Doppler chirp signal. To address this issue, we propose a Doppler estimation method that leverages the Fractional Fourier Transform (FrFT) and cross-correlation techniques. The received signals are compared with the azimuth-matched filter based on the rotation angle in the FrFT domain, and the Doppler centroid is adjusted to achieve the optimal alignment. This process ensures high correlation values and enhanced resolution in the final SAR image. The efficacy of the proposed technique is validated through experiments using real spaceborne SAR data from the practical satellite. The results demonstrate significant improvements in image quality and resolution compared to conventional algorithms, highlighting the advantages of our approach for various remote sensing applications.

PointNet + + Based Concealed Object Classification Utilizing an FMCW Millimeter-Wave Radar

In the field of millimeter-wave (MMW) imaging, the integration of artificial intelligence (AI) has emerged as a crucial solution for addressing automation challenges. In this study, concealed object classification was successfully achieved on point cloud data from MMW radar high-precision imaging using the PointNet + + deep learning method. The utilized dataset comprises point cloud data generated through the transformation of 3D models and reconstruction of physical objects with an accuracy of less than 1 mm via MMW radar scanning. Classification accuracy was significantly improved by introducing data enhancement techniques, including the generation of homologous data and optimization of sampling points. After several evaluations, 300 epochs of training were conducted using 8192 sampling points, the results showed an accuracy of 0.998 for the training dataset and 0.996 for the test dataset. Moreover, evaluations of samples not included in the original dataset as well as multi-surface scans of concealed objects within the cardboard both resulted in correct predictions, which further validates the effectiveness and reliability of the study and demonstrates the potential of AI applied to MMW imaging.

LiOSR-SAR: Lightweight Open-Set Recognizer for SAR Imageries

Open-set recognition (OSR) from synthetic aperture radar (SAR) imageries plays a crucial role in maritime and terrestrial monitoring. Nevertheless, numerous deep learning-based SAR classifiers struggle with unknown targets outside of the training dataset, leading to a dilemma, namely that a large model is difficult to deploy, while a smaller one sacrifices accuracy. To address this challenge, the novel “LiOSR-SAR” lightweight recognizer is proposed for OSR in SAR imageries. It incorporates the compact attribute focusing and open-prediction modules, which collectively optimize its lightweight structure and high accuracy. To validate LiOSR-SAR, “fast image simulation using bidirectional shooting and bouncing ray (FIS-BSBR)” is exploited to construct the corresponding dataset. It enhances the details of targets for more accurate recognition significantly. Extensive experiments show that LiOSR-SAR achieves remarkable recognition accuracies of 97.9% and 94.1% while maintaining a compact model size of 7.5 MB, demonstrating its practicality and efficiency.

Enhanced small target detection and color interpretation of synthetic aperture radar images

Enhanced small target detection and color interpretation of synthetic aperture radar images

Conditional diffusion model for arbitrary-size synthetic aperture radar image despeckling with multi-scale and dual attention mechanism

Conditional diffusion model for arbitrary-size synthetic aperture radar image despeckling with multi-scale and dual attention mechanism

Time-variant parity-time symmetry in frequency-scanning systems.

Parity-time (PT) symmetry is an active research area that provides a variety of new opportunities for different systems with novel functionalities. For instance, PT symmetry has been used in lasers and optoelectronic oscillators to achieve single-frequency lasing or oscillation. A single-frequency system is essentially a static PT-symmetric system, whose frequency is time-invariant. Here we investigate time-variant PT symmetry in frequency-scanning systems. Time-variant PT symmetry equations and eigenfrequencies for frequency-scanning systems are developed. We show that time-variant PT symmetry can dynamically narrow the instantaneous linewidth of frequency-scanning systems. The instantaneous linewidth of a produced frequency-modulated continuous-wave (FMCW) waveform is narrowed by a factor of 14 in the experiment. De-chirping and radar imaging results also show that the time-variant PT-symmetric system outperforms a conventional frequency-scanning one. Our study paves the way for a new class of time-variant PT-symmetric systems and shows great promise for applications including FMCW radar and lidar systems.

Algorithm for cloud removal in optical-synthetic aperture radar fusion images based on improved residual networks

Algorithm for cloud removal in optical-synthetic aperture radar fusion images based on improved residual networks

Combining Fusion-Based Thresholding and Non-Linear Diffusion for Improved Speckle Noise Mitigation in SAR Images

The primary concern of synthetic aperture radar (SAR) images is speckle noise, an inherent property. The creation of speckle noise is in a granular form and its nature is multiplicative. To reduce such noise from the radar images, the researchers’ primary motive is to suppress granular pattern while preserving the quality of the obtained images, thereby facilitating easier feature extraction and classification. Existing speckle-noise reduction methods often fail to preserve fine details such as edges and textures. This study proposes a fusion-based method that integrates non-linear transform-based thresholding with advanced noise reduction techniques. The proposed method is implemented on two simulated SAR images at noise variance levels of σ = from 5 to 40. The fundamental and most significant step is to analyze the effect of granular patterns in radar images before despeckling. Different performance metrics, classified into with-reference and without-reference indexes, are considered to investigate the effectiveness of the proposed despeckle method. The Signal-to-Noise Ratio (SNR) for SAR-1 at σ = 20 was observed at 16.22 dB, outperforming the next best result of 12.89 dB from the Log Compression filter. The Universal Image Quality Index (UIQI) reached 0.6987, indicating high visual quality retention across various noise levels. The proposed despeckling method demonstrated superior performance in comparison to different filters, achieving a Peak Signal-to-Noise Ratio (PSNR) improvement of up to 29.37 dB on SAR-2 at a noise variance of σ = 5, significantly higher than the best filter method’s 26.70 dB. Additionally, the method achieved a Structural Similarity Index Measure (SSIM) of 0.6538, indicating superior image quality preservation.

MAEE-Net: SAR ship target detection network based on multi-input attention and edge feature enhancement

Synthetic Aperture Radar (SAR) imagery has a wide range of applications in search and rescue ships lost contact and military reconnaissance. When detecting multi-scale targets, better determination of the target edge is conducive to improving the detection accuracy of the model, but most of the existing methods lack research on this aspect. To fix the problems mentioned earlier, this paper suggests using a SAR Ship target detection network called MAEE-Net. In this paper, a multi-input attention-based feature fusion module (MAFM) and an edge feature enhancement module (EFEM) are proposed. MAFM uses attention mechanism with multi-input and multiple-output to improve attention to shallow feature map target and suppress invalid information, so as to improve the information utilization rate of each layer. To make the network better at detecting the edges of ships, EFEM uses double-branched structure to carry out fine-grained information retention and edge feature extraction. PIoU v2 is introduced to enhance multi-target processing capability. Experiments were carried out on SSDD dataset and SAR-Ship-Dataset, the overall detection accuracy was as high as 98.6% and 94.7%. The detection accuracy was 93.5% and 99.3% on inshore and offshore sub-datasets of SSDD dataset. Experimental results on two datasets show that our model is impactful.