Search

Flood susceptibility mapping plays a crucial role in flood risk assessment and management. Accurate identification of areas prone to flooding is essential for implementing effective mitigation measures and informing decision-making processes. In this regard, the present study used high-resolution remote sensing products, i.e., synthetic aperture radar (SAR) images for flood inventory preparation and integrated four machine learning models (Random Forest: RF, Classification and Regression Trees: CART, Support Vector Machine: SVM, and Extreme Gradient Boosting: XGBoost) to predict flood susceptibility in Metlili watershed, Morocco. Initially, 12 independent variables (elevation, slope angle, aspect, plan curvature, topographic wetness index, stream power index, distance from streams, distance from roads, lithology, rainfall, land use/land cover, and normalized vegetation index) were used as conditioning factors. The flood inventory dataset was divided into 70% and 30% for training and validation purposes using a popular library, scikit-learn (i.e., train_test_split) in Python programming language. Additionally, the area under the curve (AUC) was used to evaluate the performance of the models. The accuracy assessment results showed that RF, CART, SVM, and XGBoost models predicted flood susceptibility with AUC values of 0.807, 0.780, 0.756, and 0.727, respectively. However, the RF model performed better at flood susceptibility prediction compared to the other models applied. As per this model, 22.49%, 16.02%, 12.67%, 18.10%, and 31.70% areas of the watershed are estimated as being very low, low, moderate, high, and very highly susceptible to flooding, respectively. Therefore, this study showed that the integration of machine learning models with radar data could have promising results in predicting flood susceptibility in the study area and other similar environments. [ABSTRACT FROM AUTHOR]

The article presents the main considerations for determining the tangential velocity of high-speed vessels in the digital signal processing system of a space synthetic aperture radar with an amplitude-phase program discriminator in the azimuth channel. The article suggests a complex of algorithms for fast determination of the parameters of motion of high-speed vessels in the digital signal processing system of a space synthetic aperture radar. The article contains the results of semi-natural experiments that confirm the reliability of the algorithms and their effectiveness in solving the problem of observing the sea surface.

IntroductionRemote sensing is defined as data acquisition about an object or a phenomenon related to a geographic location without physical. The use of remote sensing data is expanding rapidly. Researchers have always been interested in accurately classifying land coverage phenomena using multispectral images. One of the factors that reduces the accuracy of the classification map is the existence of uneven surfaces and high-altitude areas. The presence of high-altitude points makes it difficult for the sensors to obtain accurate reflection information from the surface of the phenomena. Radar imagery used with the digital elevation model (DEM) is effective for identifying and determining altitude phenomena. Image fusion is a technique that uses two sensors with completely different specifications and takes advantage of both of the sensors' capabilities. In this study, the feasibility of employing the fusion technique to improve the overall accuracy of classifying land coverage phenomena using time series NDVI images of Sentinel 2 satellite imagery and PALSAR radar imagery of ALOS satellite was investigated. Additionally, the results of predicted and measured areas of fields under cultivation of wheat, barley, and canola were studied.Materials and MethodsThirteen Sentinel-2 multispectral satellite images with 10-meter spatial resolution from the Bajgah region in Fars province, Iran from Nov 2018 to June 2019 were downloaded at the Level-1C processing level to classify the cultivated lands and other phenomena. Ground truth data were collected through several field visits using handheld GPS to pinpoint different phenomena in the region of study. The seven classes of distinguished land coverage and phenomena include (1) Wheat, (2) Barley, (3) Canola, (4) Tree, (5) Residential regions, (6) Soil, and (7) others. After the preprocessing operations such as radiometric and atmospheric corrections using predefined built-in algorithms recommended by other researchers in ENVI 5.3, and cropping the region of interest (ROI) from the original image, the Normalized Difference Vegetation Index (NDVI) was calculated for each image. The DEM was obtained from the PALSAR sensor radar image with the 12.5-meter spatial resolution of the ALOS satellite. After preprocessing and cropping the ROI, a binary mask of radar images was created using threshold values of altitudes between 1764 and 1799 meters above the sea level in ENVI 5.3. The NDVI time series was then composed of all 13 images and integrated with radar images using the pixel-level integration method. The purpose of this process was to remove the high-altitude points in the study area that would reduce the accuracy of the classification map. The image fusion process was also performed using ENVI 5.3. The support Vector Machine (SVM) classification method was employed to train the classifier for both fused and unfused images as suggested by other researchers.To evaluate the effectiveness of image fusion, Commission and Omission errors, and the Overall accuracy were calculated using a Confusion matrix. To study the accuracy of the estimated area under cultivation of main crops in the region versus the actual measured values of the area, regression equation and percentage of difference were calculated.Results and DiscussionVisual inspection of classified output maps shows the difference between the fused and unfused images in classifying similar classes such as buildings and structures versus regions covered with bare soil and lands under cultivation versus natural vegetation in high altitude points. Statistical metrics verified these visual evaluations. The SVM algorithm in fusion mode resulted in 98.06% accuracy and 0.97 kappa coefficient, 7.5% higher accuracy than the unfused images.As stated earlier, the similarities between the soil class (stones and rocks in the mountains) and manmade buildings and infrastructures increase omission error and misclassification in unfused image classification. The same misclassification occurred for the visually similar croplands and shallow vegetation at high altitude points. These results were consistence with previous literature that reported the same misclassification in analogous classes. The predicted area under cultivation of wheat and barley were overestimated by 3 and 1.5 percent, respectively. However, for canola, the area was underestimated by 3.5 percent.ConclusionThe main focus of this study was employing the image fusion technique and improving the classification accuracy of satellite imagery. Integration of PALSAR sensor data from ALOS radar satellite with multi-spectral imagery of Sentinel 2 satellite enhanced the classification accuracy of output maps by eliminating the high-altitude points and biases due to rocks and natural vegetation at hills and mountains. Statistical metrics such as the overall accuracy, Kappa coefficient, and commission and omission errors confirmed the visual findings of the fused vs. unfused classification maps.

Breast cancer is one of the most common malignancies among women. In many cases, the mortality rate can be drastically lowered if the disease is detected early. Microwave breast imaging is considered a potential mammography replacement to ensure patient safety. This paper presents three active regions used to represent the damaged region. The protective cells may be contaminated with cancerous and healthy tissues and fibers. A different version of a Multi-Variate and Multi-Dimensional Constant False Alarm Rate (MVMD-CFAR) in Radar Image was developed and evaluated using an open-source experimental database derived from the (UM-BMID). The results demonstrate that it is superior in obtaining a high probability of detection ( P D ) by making some changes. For example, changing the size of the damaged and healthy areas in images by varying the number of pixels and mixing between the pixels that carry the information of damaged tissues and healthy tissues. When the probability of a false alarm is reduced, a higher threshold T is obtained. A more significant number of damaged pixels in the region under test performs better and achieves the highest probability of detection. [ABSTRACT FROM AUTHOR]

In high-traffic harbor waters, marine radar frequently encounters signal interference stemming from various obstructive elements, thereby presenting formidable obstacles in the precise identification of ships. To achieve precise pixel-level ship identification in the complex environments, a customized neural network-based ship segmentation algorithm named MrisNet is proposed. MrisNet employs a lightweight and efficient FasterYOLO network to extract features from radar images at different levels, capturing fine-grained edge information and deep semantic features of ship pixels. To address the limitation of deep features in the backbone network lacking detailed shape and structured information, an adaptive attention mechanism is introduced after the FasterYOLO network to enhance crucial ship features. To fully utilize the multi-dimensional feature outputs, MrisNet incorporates a Transformer structure to reconstruct the PANet feature fusion network, allowing for the fusion of contextual information and capturing more essential ship information and semantic correlations. In the prediction stage, MrisNet optimizes the target position loss using the EIoU function, enabling the algorithm to adapt to ship position deviations and size variations, thereby improving segmentation accuracy and convergence speed. Experimental results demonstrate MrisNet achieves high recall and precision rates of 94.8% and 95.2%, respectively, in ship instance segmentation, outperforming various YOLO and other single-stage algorithms. Moreover, MrisNet has a model parameter size of 13.8M and real-time computational cost of 23.5G, demonstrating notable advantages in terms of convolutional efficiency. In conclusion, MrisNet accurately segments ships with different spot features and under diverse environmental conditions in marine radar images. It exhibits outstanding performance, particularly in extreme scenarios and challenging interference conditions, showcasing robustness and applicability. [ABSTRACT FROM AUTHOR]

Introduction Remote sensing is defined as data acquisition about an object or a phenomenon related to a geographic location without physical. The use of remote sensing data is expanding rapidly. Researchers have always been interested in accurately classifying land coverage phenomena using multispectral images. One of the factors that reduces the accuracy of the classification map is the existence of uneven surfaces and high-altitude areas. The presence of high-altitude points makes it difficult for the sensors to obtain accurate reflection information from the surface of the phenomena. Radar imagery used with the digital elevation model (DEM) is effective for identifying and determining altitude phenomena. Image fusion is a technique that uses two sensors with completely different specifications and takes advantage of both of the sensors' capabilities. In this study, the feasibility of employing the fusion technique to improve the overall accuracy of classifying land coverage phenomena using time series NDVI images of Sentinel 2 satellite imagery and PALSAR radar imagery of ALOS satellite was investigated. Additionally, the results of predicted and measured areas of fields under cultivation of wheat, barley, and canola were studied. Materials and Methods Thirteen Sentinel-2 multispectral satellite images with 10-meter spatial resolution from the Bajgah region in Fars province, Iran from Nov 2018 to June 2019 were downloaded at the Level-1C processing level to classify the cultivated lands and other phenomena. Ground truth data were collected through several field visits using handheld GPS to pinpoint different phenomena in the region of study. The seven classes of distinguished land coverage and phenomena include (1) Wheat, (2) Barley, (3) Canola, (4) Tree, (5) Residential regions, (6) Soil, and (7) others. After the preprocessing operations such as radiometric and atmospheric corrections using predefined built-in algorithms recommended by other researchers in ENVI 5.3, and cropping the region of interest (ROI) from the original image, the Normalized Difference Vegetation Index (NDVI) was calculated for each image. The DEM was obtained from the PALSAR sensor radar image with the 12.5-meter spatial resolution of the ALOS satellite. After preprocessing and cropping the ROI, a binary mask of radar images was created using threshold values of altitudes between 1764 and 1799 meters above the sea level in ENVI 5.3. The NDVI time series was then composed of all 13 images and integrated with radar images using the pixel-level integration method. The purpose of this process was to remove the high-altitude points in the study area that would reduce the accuracy of the classification map. The image fusion process was also performed using ENVI 5.3. The support Vector Machine (SVM) classification method was employed to train the classifier for both fused and unfused images as suggested by other researchers. To evaluate the effectiveness of image fusion, Commission and Omission errors, and the Overall accuracy were calculated using a Confusion matrix. To study the accuracy of the estimated area under cultivation of main crops in the region versus the actual measured values of the area, regression equation and percentage of difference were calculated. Results and Discussion Visual inspection of classified output maps shows the difference between the fused and unfused images in classifying similar classes such as buildings and structures versus regions covered with bare soil and lands under cultivation versus natural vegetation in high altitude points. Statistical metrics verified these visual evaluations. The SVM algorithm in fusion mode resulted in 98.06% accuracy and 0.97 kappa coefficient, 7.5% higher accuracy than the unfused images. As stated earlier, the similarities between the soil class (stones and rocks in the mountains) and manmade buildings and infrastructures increase omission error and misclassification in unfused image classification. The same misclassification occurred for the visually similar croplands and shallow vegetation at high altitude points. These results were consistence with previous literature that reported the same misclassification in analogous classes. The predicted area under cultivation of wheat and barley were overestimated by 3 and 1.5 percent, respectively. However, for canola, the area was underestimated by 3.5 percent. Conclusion The main focus of this study was employing the image fusion technique and improving the classification accuracy of satellite imagery. Integration of PALSAR sensor data from ALOS radar satellite with multi-spectral imagery of Sentinel 2 satellite enhanced the classification accuracy of output maps by eliminating the highaltitude points and biases due to rocks and natural vegetation at hills and mountains. Statistical metrics such as the overall accuracy, Kappa coefficient, and commission and omission errors confirmed the visual findings of the fused vs. unfused classification maps. [ABSTRACT FROM AUTHOR]

For the complex background of traditional radar image target detection methods is affected by multiple interferers, which leads to a low recognition rate of multi-target classification and a high false alarm rate. In this paper, the current hot research BM3D denoising method is introduced into radar image target detection. Firstly, the detection process of the BM3D algorithm is constructed, and the image pixels are reasonably clustered by denoising so that the image blocks in homogeneous regions have a high matching degree and those in non-homogeneous regions have a low matching degree. Secondly, the clustering recognition feature is used to limit the search range of similar blocks to homogeneous regions, to improve the denoising efficiency of the algorithm. Finally, the simulation results of this paper show that compared with previous algorithms, the BM3D detection method has significantly improved in both the subjective visual effect map and objective numerical indexes. For example, the image denoising quality is improved by about 0.716dB on average and up to 1.031dB, the image denoising time is shortened by about 19.962s on average, and the algorithm runs 1.211 times faster than the original algorithm. It is proved that the algorithm can improve denoising efficiency and reduce computational complexity while enhancing detailed information.

Presented data includes two datasets named RealSAR-RAW and RealSAR-IMG. The first one contains unprocessed (raw) radar data obtained using Ground Based Synthetic Aperture Radar (GBSAR), while the second one contains images reconstructed using Omega-K algorithm applied to raw data from the first set. The GBSAR system moves the radar sensor along the track to virtually extend (synthesize) the antenna aperture and provides imaging data of the area in front of the system. The used sensor was a Frequency Modulated Continuous Wave (FMCW) radar with a central frequency of 24 GHz and a 700 MHz wide bandwidth which in our case covered the observed scene in 30 steps with 1 cm step size. The measured (recorded) scenes were made on combinations of three test objects (bottles) made of different material (aluminum, glass, and plastic) in different positions. The aim was to develop a small dataset of GBSAR data useful for classification applications focused on distinguishing different materials from sparse radar data.

In subtropical regions, heavy rains from cumulonimbus clouds can cause disasters such as flash floods and mudslides. The accurate prediction of cumulonimbus cloud distribution is crucial for mitigating such losses. Traditional machine learning approaches have been used on radar echo data generated by constant altitude plan position indicator (CAPPI) radar systems for predicting cumulonimbus cloud distribution. However, the results are often too foggy and fuzzy. This paper proposes a novel approach that integrates graph convolutional networks (GCN) and trajectory gated recurrent units (TrajGRU) with an attention mechanism to predict cumulonimbus cloud distribution from radar echo data. Experiments were conducted using the moving modified National Institute of Standards and Technology (moving MNIST) dataset and real-world radar echo data, and the proposed model showed a 59.12% improvement in mean square error (MSE) and a 16.26% improvement in structure similarity index measure (SSIM) on average in the moving MNIST dataset, a 65.40% improvement in MSE, and an 10.29% improvement in SSIM on average in the radar echo dataset. These results demonstrate the effectiveness of the proposed approach for improving the prediction accuracy of cumulonimbus cloud distribution. [ABSTRACT FROM AUTHOR]

In this paper, the shadow statistical method, which has the merit of without calibration, is further investigated for retrieving significant wave height (SWH) based on shadowing from X-band marine radar images. For the shadow statistical method, the Smith fitting function (SFF) is utilized to fit the illumination probability obtained from the radar image and calculate the SWH. By deeply investigating the estimation of wave steepness from the shadow image, it is found that the analytic solution of wave steepness is not obtained, due to the complementary error function and exponential term in the SFF. Meanwhile, several screening processes of gradually discarding illumination probability are required to obtain accurate root mean square (RMS) wave steepness, which makes the calculation time-consuming. To solve these problems, both the complementary error function and exponential term in the SFF are approximated under the working conditions of marine radar in practice, and the analytic solution of the wave steepness is described with the illumination probability. The shore-based X-band radar images at Pingtan station from November 9 to 17, 2014 are collected to validate the validity of the proposed method. By using 254 sets of radar data with the SWH range of 0.5 ~ 3.5 m, the experimental results demonstrate that the correlation coefficient (CC) of the estimated SWH between the proposed method and the traditional method is 0.996, and the root mean square error (RMSE) is 0.034. The average running time is significantly reduced from 2.76 s to 0.44 s. [ABSTRACT FROM AUTHOR]

Many different filters can be used to reduce multiplicative speckle noise on radar images. Most of these filters have some parameters whose values influence the result of filtering. Finding optimal values of such parameters may be a non-trivial task. In this paper, a formal automated method for finding optimal parameters of speckle noise reduction filters is proposed. Using a specially designed test image, optimal parameters for the most commonly used filters were found using several image quality assessment metrics, including the Structural Similarity Index (SSIM) and Gradient Magnitude Similarity Deviation (GMSD). The use of filters with optimal parameters allows processing (detection, segmentation, etc.) of radar images with minimal influence of speckle noise.

Grassland fires are one of the main disturbances in Hulunbuir Grassland and have a great effect on the regional ecological environment and the production and life of herdsmen. The characteristics of fuel load and spatial distribution of grassland in the fire season are the main indices in simulating grassland fire behavior. Based on a field survey of fuel load in Hulunbuir Grassland in different seasons, vegetation indices of optical images (Landsat-8 OLI) and the texture characteristic parameters of radar data (Sentinel-1) were selected as input parameters, and three models, multiple linear regression (MLR), stepwise regression (SR) and random forest (RF), were used to estimate fuel load in the study region. Considering the limitations of optical images in estimating vegetation changes in fire seasons, this study explored a method of estimating vegetation biomass in the growing season and then transforming it to fuel load in fire seasons based on the relationships between biomass and fuel load. The results show that a combination of optical and SAR images is advantageous for estimating grassland fuel load. Of the three estimation models, the accuracy of RF is better than that of SR and better than that of MLR. This study provides a new method for large-scale grassland fuel inversion, and the continuous data of large-scale grassland fuel can improve the simulation accuracy of grassland fire behavior and provide strong support for grassland fire prediction. Furthermore, the policy of national grassland contracts to herdsmen in China has made enormous contributions to decreasing grassland fires.

In the report the features of formation of radar images (RI) and optical images (OI) in the mobile test stand of radiovision systems (RVS) of a car are presented. The radiovision system of a car (CRVS) of the millimeter-wavelength with frequency modulation is considered. Features of formation and processing of the radar-tracking image in CRVS are discussed, in particular: the sizes of the image, system of coordinates, primary and secondary processing of RI, requirements for speeds of transfer of figures in real time of processing, for subsystem of display of RI and synchronization. The structure of the mobile test stand of CRVS is described. This stand consists of: CRVS, a video camera, the module of formation, recording and display of RI and of optical images, the module of control of a stand, the power supply unit. Features of formation and display OI are considered, in particular: the coordination of scale and shortening of images, creation of time synchronization at display and records of OI, and questions of synchronous fusion of RI and OI also.

Flood susceptibility mapping plays a crucial role in flood risk assessment and management. Accurate identification of areas prone to flooding is essential for implementing effective mitigation measures and informing decision-making processes. In this regard, the present study used high-resolution remote sensing products, i.e., synthetic aperture radar (SAR) images for flood inventory preparation and integrated four machine learning models (Random Forest: RF, Classification and Regression Trees: CART, Support Vector Machine: SVM, and Extreme Gradient Boosting: XGBoost) to predict flood susceptibility in Metlili watershed, Morocco. Initially, 12 independent variables (elevation, slope angle, aspect, plan curvature, topographic wetness index, stream power index, distance from streams, distance from roads, lithology, rainfall, land use/land cover, and normalized vegetation index) were used as conditioning factors. The flood inventory dataset was divided into 70% and 30% for training and validation purposes using a popular library, scikit-learn (i.e., train_test_split) in Python programming language. Additionally, the area under the curve (AUC) was used to evaluate the performance of the models. The accuracy assessment results showed that RF, CART, SVM, and XGBoost models predicted flood susceptibility with AUC values of 0.807, 0.780, 0.756, and 0.727, respectively. However, the RF model performed better at flood susceptibility prediction compared to the other models applied. As per this model, 22.49%, 16.02%, 12.67%, 18.10%, and 31.70% areas of the watershed are estimated as being very low, low, moderate, high, and very highly susceptible to flooding, respectively. Therefore, this study showed that the integration of machine learning models with radar data could have promising results in predicting flood susceptibility in the study area and other similar environments.

In high-traffic harbor waters, marine radar frequently encounters signal interference stemming from various obstructive elements, thereby presenting formidable obstacles in the precise identification of ships. To achieve precise pixel-level ship identification in the complex environments, a customized neural network-based ship segmentation algorithm named MrisNet is proposed. MrisNet employs a lightweight and efficient FasterYOLO network to extract features from radar images at different levels, capturing fine-grained edge information and deep semantic features of ship pixels. To address the limitation of deep features in the backbone network lacking detailed shape and structured information, an adaptive attention mechanism is introduced after the FasterYOLO network to enhance crucial ship features. To fully utilize the multi-dimensional feature outputs, MrisNet incorporates a Transformer structure to reconstruct the PANet feature fusion network, allowing for the fusion of contextual information and capturing more essential ship information and semantic correlations. In the prediction stage, MrisNet optimizes the target position loss using the EIoU function, enabling the algorithm to adapt to ship position deviations and size variations, thereby improving segmentation accuracy and convergence speed. Experimental results demonstrate MrisNet achieves high recall and precision rates of 94.8% and 95.2%, respectively, in ship instance segmentation, outperforming various YOLO and other single-stage algorithms. Moreover, MrisNet has a model parameter size of 13.8M and real-time computational cost of 23.5G, demonstrating notable advantages in terms of convolutional efficiency. In conclusion, MrisNet accurately segments ships with different spot features and under diverse environmental conditions in marine radar images. It exhibits outstanding performance, particularly in extreme scenarios and challenging interference conditions, showcasing robustness and applicability.

Determining the attitude of a non-cooperative target in space is an important frontier issue in the aerospace field, and has important application value in the fields of malfunctioning satellite state assessment and non-cooperative target detection in space. This paper proposes a non-cooperative target attitude estimation method based on the deep learning of ground and space access (GSA) scene radar images to solve this problem. In GSA scenes, the observed target satellite can be imaged not only by inverse synthetic-aperture radar (ISAR), but also by space-based optical satellites, with space-based optical images providing more accurate attitude estimates for the target. The spatial orientation of the intersection of the orbital planes of the target and observation satellites can be changed by fine tuning the orbit of the observation satellite. The intersection of the orbital planes is controlled to ensure that it is collinear with the position vector of the target satellite when it is accessible to the radar. Thus, a series of GSA scenes are generated. In these GSA scenes, the high-precision attitude values of the target satellite can be estimated from the space-based optical images obtained by the observation satellite. Thus, the corresponding relationship between a series of ISAR images and the attitude estimation of the target at this moment can be obtained. Because the target attitude can be accurately estimated from the GSA scenes obtained by a space-based optical telescope, these attitude estimation values can be used as training datasets of ISAR images, and deep learning training can be performed on ISAR images of GSA scenes. This paper proposes an instantaneous attitude estimation method based on a deep network, which can achieve robust attitude estimation under different signal-to-noise ratio conditions. First, ISAR observation and imaging models were created, and the theoretical projection relationship from the three-dimensional point cloud to the ISAR imaging plane was constructed based on the radar line of sight. Under the premise that the ISAR imaging plane was fixed, the ISAR imaging results, theoretical projection map, and target attitude were in a one-to-one correspondence, which meant that the mapping relationship could be learned using a deep network. Specifically, in order to suppress noise interference, a UNet++ network with strong feature extraction ability was used to learn the mapping relationship between the ISAR imaging results and the theoretical projection map to achieve ISAR image enhancement. The shifted window (swin) transformer was then used to learn the mapping relationship between the enhanced ISAR images and target attitude to achieve instantaneous attitude estimation. Finally, the effectiveness of the proposed method was verified using electromagnetic simulation data, and it was found that the average attitude estimation error of the proposed method was less than 1°. [ABSTRACT FROM AUTHOR]

In this study, a new method combining wave-number energy spectrum (WES) and Genetic algorithm-back propagation neural network (GA-BPNN) is proposed to retrieve the rainfall intensity level from rain-contaminated X-band marine radar image. Since the intensity of spatial rainfall can be reflected by the distribution of energy in the wavenumber frequency domain, the obtained WES is divided into three wavenumber segments (low, medium and high wavenumber segments), and the ratio of the wavenumber in each wavenumber segment to the total wavenumber is calculated separately as the characteristic parameters. Based on the excellent network convergence speed and data prediction accuracy of the GA-BPNN, these calculated parameters are input into the constructed GA-BPNN for training to complete the task of rainfall intensity level retrieval. The proposed method is tested using data collected at the ocean observation station of Haitan Island in Pingtan County. Referring to the actual rainfall intensity synchronously recorded by the rain gauge, the retrieval accuracy of the proposed method is 97.4%, which is 4.3% higher than that of back propagation neural network (BPNN) not optimized by Genetic algorithm (GA). In addition, compared with the retrieval performance of the ratio of zero intensity to echo (RZE) method based on the occlusion area of radar image, the retrieval accuracy of the proposed method is improved by about 12.9%. [ABSTRACT FROM AUTHOR]

In subtropical regions, heavy rains from cumulonimbus clouds can cause disasters such as flash floods and mudslides. The accurate prediction of cumulonimbus cloud distribution is crucial for mitigating such losses. Traditional machine learning approaches have been used on radar echo data generated by constant altitude plan position indicator (CAPPI) radar systems for predicting cumulonimbus cloud distribution. However, the results are often too foggy and fuzzy. This paper proposes a novel approach that integrates graph convolutional networks (GCN) and trajectory gated recurrent units (TrajGRU) with an attention mechanism to predict cumulonimbus cloud distribution from radar echo data. Experiments were conducted using the moving modified National Institute of Standards and Technology (moving MNIST) dataset and real-world radar echo data, and the proposed model showed a 59.12% improvement in mean square error (MSE) and a 16.26% improvement in structure similarity index measure (SSIM) on average in the moving MNIST dataset, a 65.40% improvement in MSE, and an 10.29% improvement in SSIM on average in the radar echo dataset. These results demonstrate the effectiveness of the proposed approach for improving the prediction accuracy of cumulonimbus cloud distribution.

Optimal time selection for inverse synthetic aperture radar imaging of ship target is significant for the determination of image project plane, and the performance of it is dependent on the accuracy of ship centerline extraction. In this article, a novel optimal time selection method based on the random sample consensus (RANSAC) technique is proposed, which can extract the ship centerline with high accuracy in the case of ship superstructure and low signal to noise ratio. First, a necessary distance threshold is determined for the RANSAC algorithm combined with the ship body width estimation. Then, a novel cost function is proposed according to the amplitude characteristic of radar image, which can alleviate the influence of randomness. Finally, the robustness of the optimal time selection method is demonstrated by the results of simulated and real measured data.

Nonlocal means synthetic aperture radar (SAR) image despeckling approaches have attracted much research attention. However, high computational burden always limits its application in practice, especially using complex similarity measures. We present a fast patchwise nonlocal method using joint intensity and structure measures for SAR image despeckling. Nonlocal methods often define the similarity criterion only based on amplitude or intensity image. In order to preserve structure details, the structure information is also introduced into similarity measure by constructing gradient orientation feature map. The gradient orientation statistical test is performed to determine whether the patches contain the same structural components, and the similar patches are selected through the constant false alarm ratio strategy. Furthermore, we reorganize the patchwise nonlocal despeckling method and accelerate it using fast Fourier transform. Meanwhile, we utilize a Gaussian kernel to aggregate patchwise weights for each pixel in its patch area, so as to reduce the blur effect of classical patchwise nonlocal methods on details. The experiments have demonstrated that the proposed method is an efficient restoration method and has great structure and texture retention ability.

The features of the implementation of the algorithm for the synthesis of detail radar images for an aperture synthesis radar using the built-in functions of the Cuda library are presented. The estimation of computational complexity from the standpoint of the organization of parallel computing on Nvidia GPUs is given. The estimation of the real performance of radar synthesis is given, taking into account the volume and features of the placement of primary radar information.

The ice–bedrock interfaces at the bottoms of ice sheets and the internal ice layers record the historical evolution of the ice sheets and are important indicators for inferring glacier dynamics and explaining subglacial topographies. Radar-detected bedrock and internal ice layers can be used to observe conditions in the interiors and bottoms of ice sheets. The low contrast of the internal layers’ feature in radar images, as well as the effects of ice flow, makes it challenging to automatically extract and trace the layers and interfaces of ice sheets. Manual or semiautomatic methods are extensively applied in bedrock and internal ice layers’ extractions. However, the conventional methods require large amounts of time. Especially when processing a large number of radar observation data, the accuracy and efficiency of conventional methods are untoward. Therefore, we propose EisNet, a fusion system consisting of deep neural networks, to extract the multiple types of internal layers. Because of the rareness of high-precision extraction of ice layers, it is virtually impossible to train EisNet in observational data with the corresponded label of ice layers. To train EisNet, we design a novel synthetic method for radar images based on artifact noise and characteristic textures that are similar to those in the observation data. The validation in synthetic data proves EisNet’s capacity for layer extraction and noise removal. The field data application shows the generalization and adaptation abilities of EisNet and indicates that EisNet can significantly improve the efficiency of the automatic processing of ice sheet radiostratigraphy. [ABSTRACT FROM AUTHOR]

Subject and Purpose. The paper is concerned with Synthetic Aperture Radar (SAR) imaging and data processing and seeks to modify the conventional time-domain back projection algorithm (BPA) used for creating a SAR image. The modification consists in the radar squint-angle control at the stage of data processing. Methods and Methodology. Mathematical modeling methods are used. The modeling results are verified by reference to the experimental data. Results. A modification proposed for the back projection algorithm (BPA) enables fast-moving targets to be detected on a stationary image created by synthetic-aperture squint-angle side-looking radar. The back projection algorithm with the squint angle control was experimentally verified by a speedboat example to show that the SAR image has signatures of fast-moving targets which are not observed on the image formed by the classic back projection algorithm. Conclusion. The proposed modification of the back projection algorithm improves the detection probability of fast-moving targets on a SAR image and does it without any complication of the classic back projection algorithm or additional computing time.

Determining the attitude of a non-cooperative target in space is an important frontier issue in the aerospace field, and has important application value in the fields of malfunctioning satellite state assessment and non-cooperative target detection in space. This paper proposes a non-cooperative target attitude estimation method based on the deep learning of ground and space access (GSA) scene radar images to solve this problem. In GSA scenes, the observed target satellite can be imaged not only by inverse synthetic-aperture radar (ISAR), but also by space-based optical satellites, with space-based optical images providing more accurate attitude estimates for the target. The spatial orientation of the intersection of the orbital planes of the target and observation satellites can be changed by fine tuning the orbit of the observation satellite. The intersection of the orbital planes is controlled to ensure that it is collinear with the position vector of the target satellite when it is accessible to the radar. Thus, a series of GSA scenes are generated. In these GSA scenes, the high-precision attitude values of the target satellite can be estimated from the space-based optical images obtained by the observation satellite. Thus, the corresponding relationship between a series of ISAR images and the attitude estimation of the target at this moment can be obtained. Because the target attitude can be accurately estimated from the GSA scenes obtained by a space-based optical telescope, these attitude estimation values can be used as training datasets of ISAR images, and deep learning training can be performed on ISAR images of GSA scenes. This paper proposes an instantaneous attitude estimation method based on a deep network, which can achieve robust attitude estimation under different signal-to-noise ratio conditions. First, ISAR observation and imaging models were created, and the theoretical projection relationship from the three-dimensional point cloud to the ISAR imaging plane was constructed based on the radar line of sight. Under the premise that the ISAR imaging plane was fixed, the ISAR imaging results, theoretical projection map, and target attitude were in a one-to-one correspondence, which meant that the mapping relationship could be learned using a deep network. Specifically, in order to suppress noise interference, a UNet++ network with strong feature extraction ability was used to learn the mapping relationship between the ISAR imaging results and the theoretical projection map to achieve ISAR image enhancement. The shifted window (swin) transformer was then used to learn the mapping relationship between the enhanced ISAR images and target attitude to achieve instantaneous attitude estimation. Finally, the effectiveness of the proposed method was verified using electromagnetic simulation data, and it was found that the average attitude estimation error of the proposed method was less than 1°.

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the problem of electro-optical feature fusion simultaneous interpreting the sky and sky targets from the same sensor angle, a three dimensional structure inversion method is proposed, which integrates the parameters of scattering centers and the features of contour points. Firstly, based on orthogonal matching pursuit (OMP) algorithm, the feature of two-dimensional scattering center in radar image sequence is estimated, and the corner feature of continuous visible image is extracted by Freeman chain code. Then, based on graph theory, two-dimensional feature points in radar and visible images are associated. Finally, the fusion of scattering center feature and optical corner feature is realized by three dimensional reconstruction of feature points, so as to reconstruct more abundant and accurate target structure information than single source feature. Simulation results verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Multiple-input multiple-output (MIMO) radar is a radar system that simultaneously uses multiple transmitting antennas and receiving antennas to transmit and receive diversity waveforms for centralized processing. The MIMO system avoids the mechanical transmission structure in traditional RCS measurement and has high data acquisition efficiency, making it possible for three-dimensional (3D) imaging with large data volume requirements. Compared with the traditional two-dimensional (2D) radar image, the target 3D radar image can provide the spatial three-dimensional position of the scattering center of the complex target and its scattering intensity information, making the RCS measurement data more complete. The 3D imaging technology based on the MIMO system uses a portable MIMO array to quickly acquire data, and then uses the back-projection (BP) imaging algorithm to perform 3D imaging. This method obtains data quickly with simple hardware conditions, which has the characteristics of low cost and high efficiency. This paper derives a 3D BP imaging algorithm using MIMO system. And the applicability and correctness are verified by simulation experiments on PSF and multiple point targets. [ABSTRACT FROM AUTHOR]

The influence of wave polarization on texture parameters of objects in radar images (RIs) is examined by calculations of the second-order statistics (the fractal dimension and the Haralick textural features) on the basis of polarimetric data acquired with the Spaceborne Imaging Radar-C/X-Band Synthetic Aperture Radar (SIR-C/X-SAR) system for two wavelengths of the C- and L-ranges. The variance analysis of the samples of fractal dimension values for natural forested and water objects have revealed no influence of polarization on the values before the speckle filtering; however, after speckle filtering, statistically valid differences have been found in the mean values of some pairs of samples. For sample pairs of the copolarizations VV–HH and cross polarizations HV–VH, a random nature of the differences observed in the mean fractal dimension values has been shown. This conclusion is also true for the Haralick textural features of a water object—the contrast, inverse moment, and entropy. Statistically valid differences in the mean values of the Haralick textural features for urban and water objects have been revealed both before and after speckle filtering. For a forested object, variance analysis shows that the polarization-dependent differences in the mean values of the textural feature samples are statistically unreliable. [ABSTRACT FROM AUTHOR]

Electronic charts and marine radars are indispensable equipment in ship navigation systems, and the fusion display of these two parts ensures that the vessel can display dangerous moving targets and various obstacles on the sea. To reduce the noise interference caused by external factors and hardware, a novel radar image denoising algorithm using the concept of Generative Adversarial Network (GAN) using Wasserstein distance is proposed. GAN focuses on transferring the image noise distribution between strong and weak noise, while the perceptual loss approach is to suppress the noise by comparing the perceptual characteristics of the output after denoising. Afterwards, an image registration method based on image transformation is proposed to eliminate the imaging difference between the radar image and chart image, in which the visual attribute transfer approach is used to transform images. Finally, the sparse theory is used to process the high frequency and low frequency subband coefficients of the detection image obtained by the fast Fourier transform in parallel to realizing the image fusion. The results show that the fused contour has a high consistency, fast training speed and short registration time.

Collision avoidance is one of the high-level safety objectives and requires a complete and reliable description of the maritime traffic situation. The radar is specified by the IMO as the primary sensor for collision avoidance. In this paper we study the performance of multi-target tracking based on radar imagery to refine the maritime traffic situation awareness. In order to achieve this we simulate synthetic radar images and evaluate the tracking performance of different Bayesian multi-target trackers (MTTs), such as particle and JPDA filters. For the simulated tracks, the target state estimates in position, speed and course over ground will be compared to the reference data. The performance of the MTTs will be assessed via the OSPA metric by comparing the estimated multi-object state vector to the reference. This approach allows a fair performance analysis of different tracking algorithms based on radar images for a simulated maritime scenario.

In order to improve the capability of monitoring and predicting strong convective weather of Zhaoqing area, monitoring and early-warning system of strong convective weather is developed. Graphic and image technology is applied in the development of the system. The region growing method is used in image segmentation. The map of all towns of Zhaoqing area is drawn by coordinate transformation and graphics technologies. The processed radar image and the map of Zhaoqing area have been overlapped. By using improved arc-length method, the system can judge which areas are affected by strong convective echo. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract: In this paper, we discuss the time series of the coefficient of backscattering from forest cover and unused land in the Moscow region based on 29 C-band sessions of the Sentinel 1A satellite over a one-year period from March 10, 2015 to March 4, 2016. The data were interpreted using the MIMICS model of the change in the permittivity of the elements of the forest cover and the model of the change in the permittivity of the soil. The seasonal features of the change in backscattering from the forest using two polarizations of VV and VH are shown for the Losinyi Ostrov forest. A strong positive correlation was found between values ​​of the backscattering coefficient of the forest and values of air temperature. Using the MIMICS model, we were also able to relate the annual changes in the backscattering coefficient of the forest to changes in the permittivity of the trees dependent on temperature. The soil moisture content of unused land in the vicinity of Fryazino, Moscow Region was estimated based on the radar data for 2015-2016. Data on soil moisture can be extracted using a single equation of Dubois et al., 1995 for consistent polarization and regression of Rao et al., 2003 under a number of conditions. The time series of the values ​​of the equivalent water layer for the studied field is shown for the snow period. [ABSTRACT FROM AUTHOR]