Search

In recent years, deep learning has been successfully applied in the field of SAR (Synthetic Aperture Radar) image object detection. However, unlike ships and tanks targets, the oil tank targets in SAR image are usually dense and compact with more overlaps and discrete scattering centers, which greatly increases the difficulty of extracting location and structural parameters. Most of the existing methods transfer the methods suitable for natural image to the SAR image field, without considering the unique characteristics of SAR image. Therefore, in this article, we propose an improved model based on the end-to-end Transformer network, which is the first model introducing Transformer network to 3D detection of oil tank targets from single SAR image. We input the incidence angle into the Transformer model as a priori token. Then we propose feature description operator based on the scattering centers which are used as an aid to improve the precision of predictions. In addition, we also propose a cylinder IOU as a more suitable evaluation metric for 3D detection of oil tank. Finally, we evaluate our model on a SAR image dataset which contain SAR images from RADARSAT-2, TerraSAR-X, GF-3 with different incidence angles. Our experiments demonstrate that our proposed model achieves AP of 77.6% compared with 60.8% of baseline, which proves the effectiveness of the introduction of observation conditions, cylinder IOU loss and the feature description operator based on the scattering centers in our model and is appealing for 3D detection of oil tank.

Convolutional Neural Network (CNN) models are widely used in supervised Polarimetric Synthetic Aperture Radar (PolSAR) image classification. They are powerful tools to capture the non-linear dependency between adjacent pixels and outperform traditional methods on various benchmarks. On the contrary, research works investigating unsupervised PolSAR classification are quite rare, because most CNN models need to be trained with labeled data. In this paper, we propose a completely unsupervised model by fusing the Convolutional Autoencoder (CAE) with Vector Quantization (VQ). An auxiliary Gaussian smoothing loss is adopted for better semantic consistency in the output classification map. Qualitative and quantitative experiments are carried out on satellite and airborne full polarization data (RadarSat2/E-SAR, AIRSAR). The proposed model achieves 91.87%, 83.58% and 96.93% overall accuracy (OA) on the three datasets, which are much higher than the traditional H/alpha-Wishart method, and it exhibits better visual quality as well.

Synthetic aperture radar tomography (TomoSAR) is an important 3D mapping method. Traditional TomoSAR requires a large number of observation orbits however, it is hard to meet the requirement of massive orbits. While on the one hand, this is due to funding constraints, on the other hand, because the target scene is changing over time and each observation orbit consumes lots of time, the number of orbits can be fewer as required within a narrow time window. When the number of observation orbits is insufficient, the signal-to-noise ratio (SNR), peak-to-sidelobe ratio (PSR), and resolution of 3D reconstruction results will decline severely, which seriously limits the practical application of TomoSAR. In order to solve this problem, we propose to use a deep learning network to improve the resolution and SNR of 3D reconstruction results under the condition of very few observation orbits by learning the prior distribution of targets. We use all available orbits to reconstruct a high resolution target, while only very few (around 3) orbits to reconstruct a low resolution input. The low-res and high-res 3D voxel-grid pairs are used to train a 3D super-resolution (SR) CNN (convolutional neural network) model, just like ordinary 2D image SR tasks. Experiments on the Civilian Vehicle Radar dataset show that the proposed deep learning algorithm can effectively improve the reconstruction both in quality and in quantity. In addition, the model also shows good generalization performance for targets not shown in the training set.

Synthetic aperture radar (SAR) image simulators based on computer-aided drawing models play an important role in SAR applications, such as automatic target recognition and image interpretation. However, the accuracy of such simulators is due to geometric error and simplification in the electromagnetic calculation. In this letter, an end-to-end model was developed that could directly synthesize the desired images from the known image database. The model was based on generative adversarial nets (GANs), and its feasibility was validated by comparisons with real images and ray-tracing results. As a further step, the samples were synthesized at angles outside of the data set. However, the training process of GAN models was difficult, especially for SAR images which are usually affected by noise interference. The major failure modes were analyzed in experiments, and a clutter normalization method was proposed to ameliorate them. The results showed that the method improved the speed of convergence up to 10 times. The quality of the synthesized images was also improved.

Ship target recognition has always been a hot issue in the field of ocean surveillance. Due to the serious shortage of samples in ship target recognition for synthetic aperture radar (SAR) images, the template-based method is still one of the most effective ways to solve the problem. In this letter, we put forward a novel ship recognition method based on the projection shape template (PST), aiming at increasing both the accuracy and the robustness of the recognition. The PST of each category is calculated by projecting the 3-D model obtained from the two-view images of the target to the 2-D slant-plane image according to the SAR imaging model. Then, we propose a contour extraction method to detect the profile of ships, which served as the feature. Finally, the identity of the query ship is obtained through contour matching. Experimental results indicate that the proposed method is effective even when the number of samples is extremely small, consequently providing a promising way for the automatic interpretation of ship targets in the SAR images.

A Siamese network based metric learning method is proposed for SAR target classification with few training samples. The network consists of two identical CNNs sharing the weights. Different from classification networks that predict the category of one sample, the Siamese network implements a metric learning to measure the similarity between two samples. Since the input is the sample pair, the amount of training data dramatically increases which contributes to training a better network. When generating the pairs, a hard negative mining scheme is proposed for improving the performance. To avoid computing the similarity between the test sample and each training sample at the test stage, which is time consuming, a two stages scheme is employed with an additional classification network taking the output of the single branch of Siamese network as the input and predicting the category. Experiments on the MSTAR dataset validate the effectiveness of the proposed method.

Accumulation of target features from multi-angle observation data is of great significance for SAR Automatic Target Recognition. How to make correspondence matching with multi-angle data effectively for man-made targets? Due to the intensities and positions of the scattering centers varies with the aspect angle strongly, it is difficult to register SAR images using traditional matching methods. In this work, an approach for feature matching of man-made targets is proposed from complex SAR data. And it is based on the mechanisms of the dominate scattering to build up the relationship of the different multi-aspect images. Scattering map is employed to make scattering center extractions. Then the scattering centers are matching by using the physical model. Terra-SAR data of an aircraft test the validity of the approach.

SAR images of aircrafts usually consist of several discrete scattering centers. For targets like aircrafts having relatively smooth surfaces, understanding and modeling about these scattering centers is of great use for the detection and the recognition in SAR images. In this work, an approach for modeling of the features about the dominant scattering centers of the aircrafts is proposed. The approach generates a scattering map based on the analytic scattering model of some typical unit structures. According to scattering maps, the equivalent parameters are adjusted for detail feature modeling. Through this approach, the main mechanisms of aircrafts can be interpreted and the main features are modeling too. This approach provides a way to characterize the features of aircrafts in SAR images without the large computational amount. Furthermore, it sets up a frame based on typical structures to model the local scattering features of the aircrafts in SAR images. The experiments based on the Terra-SAR data and airborne data test the validity of the approach. The work would be useful for SAR Automatic Target Recognition.

Due to the special principle of synthetic aperture radar (SAR), SAR images exhibit many special phenomena. This becomes more obvious on high-resolution (HR) SAR images, as much more details are contained. We firmly believe that these details are where the advantages of a SAR image lie on and they provide some key clues for building the framework to understand SAR images. It comes to our attention that many special details in SAR images are due to the mechanism of multipath (MP) scattering. Dominated by the synthetic aperture progress, MP scattering reveals many interesting properties in SAR images. In this paper, we first analyze the mechanism of MP scattering by using the ray perspective on typical structure units. The main characteristics of the MP scattering in the SAR image are presented, such as the offset, prolong, segment, and blurring. Then, the analysis is extended to typical structures with MP scattering, such as bridges, buildings, and oil tanks by using Terra-SAR images. Finally, we explore the utilization of characteristics of MP scattering on geometry extraction from HR SAR images. The results prove the validity and the precision of our analysis. Some advices are also provided on the applications of the characteristics of the MP scattering in the SAR image. It is expected that this paper is helpful for the SAR image understanding and application.

The CNNs manifest outstanding performance in SAR ATR applications. The most widely used means for evaluation is to test them on a separate testing set. However, as there exists a strong correlation between the working conditions of the training and the testing sets, the reliability of the method degrades. We revealed the problem by training and testing the models with pure clutters, and found that the model could still achieve a high accuracy. Furthermore, we noticed that some models showed approximately the same performance when the working condition was altered, while others suffered significant degradation. Analysis of the two types of models were conducted via saliency maps. Finally, a new inner feature ratio (IFR) metric for evaluation was proposed. Results demonstrated that the new metric could effectively reject those with false high accuracies, and help choose the robust ones.

The edges of shadows are blurred in Synthetic Aperture Radar (SAR) images due to the moving of the radar when data are collected. This phenomenon becomes obvious in High Resolution (HR) SAR images. In this work, an adaptive approach for shadow enhancements is proposed. The performance of the shadow enhancement has some relationship with the precision of the estimation of the height and this rule is used in this work. The Height-Variant Phase Compensation (HVPC) and golden section algorithm are employed. The adaptive method is built by iterative progress of calculating the quantities of pixels corresponding to the shadow region. This method provides an automatic way for shadow enhancements and it is suitable for objects mainly composed of flat-like structures. The experiments based on the Mini-SAR of a helicopter are implemented to test the validity of the approach. The work in this paper provides a way for shadow enhancement for HR SAR images and would be useful for SAR Automatic Target Recognition.

In synthetic aperture radar (SAR) imagery, relating to maritime surveillance studies, the ship has always been the main focus of study. In this letter, a method of ship classification in SAR images is proposed to enhance classification accuracy. In the proposed method, to fully exploit the distinguishing characters of the ship targets, both topology and intensity of the scattering points of the ship are considered. The results of testing the proposed method on a data set of three types of ships, collected via a space-borne SAR sensor designed by the Institute of Electronics, Chinese Academy of Sciences (IECAS), establish that the proposed method is superior to several existing methods, including the original shape contexts method, traditional invariant moments and the recent approach.

In synthetic aperture radar (SAR) images, the edge of the shadow is blurred because the radar is moving while the data are collected. In this letter, this problem is expanded on by using the imaging formation perspective. First, an approximate method to represent the imaging quality of the boundary of the shadow region based on the quadratic phase errors (QPEs) is provided for the first time, which built up the relationship between the parameters of the shadow caster and the behavior of the shadow in the SAR image. We notice that the QPE is approximately a linear function of the height of the caster. Second, we deduced the height-dependent phases due to the synthetic aperture process to the raw data, and a novel algorithm called height-variant phase compensation (HVPC) on the complex SAR image data is proposed by compensating the unexpected phases in the azimuth to sharpen the shadow. Compared with the traditional approach called fixed-focus shadow enhancement (FFSE), HVPC removes twice as much of the QPE as FFSE approximately. Experiments on simulation and real data demonstrate the precision and the better effect on shadow enhancement of our work. It is expected that the work in this letter could be some help for the SAR image understanding and application.

The edges of the shadow region are blurred in the SAR image due to the moving of the radar during data collection. This phenomenon becomes obvious in the High Resolution SAR images. Shadow enhancement is of great value for ATR especially when the scattering centers of the target itself are not clear. In this paper, an approach for shadow enhancement in the SAR images for targets with plat structures is presented. And experiments on the Mini-SAR data test the validity of the approach.

In this letter, a stationary-wavelet-based despeckling algorithm based on the two-sided generalized gamma distribution (GΓD) model is proposed. We first introduce the two-sided GΓD as a flexible and efficient model for the wavelet coefficients of logarithmically transformed synthetic aperture radar intensity or amplitude. The strength of the model is highlighted in terms of its fit to the data, its low computational cost, and the ease of parameter estimation. By empirical results, we then motivate the GΓD as model for the wavelet coefficients of the noise-free signal. The GΓD model parameters are estimated with moment methods, using both absolute central moments for the wavelet coefficients of the noisy signal and the noise. Finally, we exploit the prior information contained in the model by designing a Bayesian maximum a posteriori estimator for estimating the noise-free wavelet coefficients. Experimental results demonstrate the superiority of our method in terms of simultaneously reducing speckle and preserving structural details.

In this letter, a novel synthetic aperture radar (SAR) imaging simulator is proposed based on analytical electromagnetic and geometric models for urban structures. The backscatter contributions are evaluated by an analytical electromagnetic model based on the Kirchhoff approach (KA) in either physics or geometrical optics approximations rather than specular and Lambertian models. In addition, the position vectors of object facets in the SAR imaging plane are evaluated by a closed-form analytical geometrical model based on the ray-tracing model. These models are expressed in terms of few and basic parameters. Compared with other numerical methods, they are helpful for improving the efficiency of the simulation, but more importantly, they are significant for direct understanding of and further interpreting the SAR image features. Some experiments validate the geometric and electromagnetic models and demonstrate the efficiency of the simulator.

The shadow is a particular phenomenon in SAR images, inflecting some information of the target. However, the shadow edges are blurred in SAR images. Thus, we analyze the causes for the blurring phenomenon of shadow edges in terms of SAR imaging algorithms in this paper. Taking the range Doppler algorithm for example, we conduct four simulation experiments to compensate for different processing steps and compare the imaging discrepancy among the refocused shadow edges. The conclusions are that the blurring phenomenon of shadow edges in SAR images is mainly reflected in azimuth, and azimuth compression is the major impact-factor to the shadow imaging quality. It is obvious that optimization of azimuth compression should get more attention for shadow enhancement in SAR images.

The boundary of the shadow region is blurred in SAR images for the moving of the radar during the collection of data. This phenomenon gets particularly obvious for tall and narrow targets in High Resolution (HR) SAR images. In this work, based on the Height-Variant Phase Compensation Algorithm (HVPC) according to the property of the target like poles, an approach for shadow enhancement about tall and narrow targets in SAR images is presented. This approach uses a group of a compensation filters in azimuth direction to focus the edge of the shadow. In addition, the experiments for Terra-SAR and Mini-SAR data are implemented and the results prove the validity of the approach.

This paper proposes a novel radar imaging simulator based on analytical electromagnetic and geometric models for a common typical kind of urban structure. The analytical models are presented not only for improving the efficiency of the simulation but also for direct and further understanding the features in the SAR image.

A novel height-retrieval method of individual urban structure from high-resolution (HR) synthetic aperture radar (SAR) images is presented based on the geometric property of the double-bounce contribution. The double-bounce contributions caused by the interaction of the visible walls and the surrounding ground are the key features of urban structure. Their scattering distributions and geometric properties are analyzed, a set of geometric models is built, and then a building-height retrieval approach based on these models is proposed. An analysis of the sensitiveness of the height retrieval to errors on the sensor system, building, and measured parameters is performed. The validity and superiority of the proposed approach are demonstrated by four simulation examples, two real very high-resolution MiniSAR examples, and four real HR TerraSAR-X examples.