Deep learning target detection network guided by physical mechanism

In general, synthetic aperture radar (SAR) imaging and image processing are two sequential steps in SAR image processing. Due to the large size of SAR images, most image processing algorithms require image segmentation before processing. However, the existence of speckle noise in SAR images, as well as poor contrast and the uneven distribution of gray values in the same target, make SAR images difficult to segment. In order to facilitate the subsequent processing of SAR images, this paper proposes a new method that combines the back-projection algorithm (BPA) and a first-order gradient operator to enhance the edges of SAR images to overcome image segmentation problems. For complex-valued signals, the gradient operator was applied directly to the imaging process. The experimental results of simulated images and real images validate our proposed method. For the simulated scene, the supervised image segmentation evaluation indexes of our method have more than 1.18%, 11.2% and 11.72% improvement on probabilistic Rand index (PRI), variability index (VI), and global consistency error (GCE). The proposed imaging method will make SAR image segmentation and related applications easier.

Synthetic aperture radar (SAR) imaging processing is a complex operation that requires a large amount of floating point computations. It is very time-consuming to convert SAR raw data into imagery on microcomputers. The authors have successively developed SAR processors using two kinds of computers-JN3AR of distributed memory multiprocessor architecture (made in China), and SGI Origin 200 of scalable shared memory multiprocessor architecture. The SAR imaging efficiency has been greatly improved.

A novel target detection algorithm for synthetic aperture radar (SAR) images based on an improved visual attention method is proposed in this paper. With the development of SAR technology, target detection algorithms are confronted with many difficulties such as a complicated environment and scarcity of target information. Visual attention of the human visual system can make humans easily focus on key points in a complex picture, and the visual attention algorithm has been used in many fields. However, existing algorithms based on visual attention models cannot obtain satisfactory results for SAR image target detection under complex environmental conditions. After analysing the existing visual attention models, we combine the pyramid model of visual attention with singular value decomposition to simulate the human retina, which can make the visual attention model more suitable to the characteristics of SAR images. We introduce variance weighted information entropy into the model to optimize the detection results. The results obtained by the existing visual attention algorithm for target detection in SAR images yield a large number of false alarms and misses. However, the proposed algorithm can improve both the efficiency and accuracy of target detection in a complicated environment and under weak-target conditions. The experimental results validate the performance of our method.

Although Synthetic Aperture Radar (SAR) can capture rich land cover information as a most important advanced technique in the field of international earth observation, the application effects still limited significantly. The reason is that the study of SAR imaging processing, SAR image processing and SAR applications are conducted respectively, the integrated study are lacked for parameter selection of SAR imaging processing and SAR image processing and targets identification of SAR application. Focusing on above science problems, the study for phase high fidelity model of high precision interferometric SAR, SAR non-stationary backscattering characteristics and cognition, SAR three-dimensional electromagnetic scattering modeling and its scattering mechanism and SAR multi-parameters optimization information extraction has been conducted. The typical natural distributed targets and man-made targets such as surface deformation, sea ice, building complex and collapsed building are selected, the method and application study oriented to SAR environmental parameters inversion are conduced, the main result and conclusion are as follows: (1) The overall theoretical frames of SAR information integrated processing was proposed; The simulation and ground validation system used to assess the effects of SAR information integrated processing was created; furthermore, the spaceborne SAR imaging algorithm with three steps focusing processing was proposed and realized the multi-modal integrated imaging processing and improved the imaging processing precision. (2) In terms of SAR information integrated processing of natural targets, focusing on phase high fidelity imaging processing of interferometric SAR surface deformation monitoring, an novel spaceborne SAR high fidelity simulation method based on stationary RCS and improved Goldstein SAR interferogram filter based on empirical mode decomposition were proposed. Focusing on multi-parameters optimization processing of sea ice types classification, the multi-channel spaceborne SAR sparse imaging method based on compressive sensing, Kalman filter for removal of scalloping and inter-scan banding in ScanSAR images and SVM sea ice classification method combined with sea ice concentration were proposed. (3) In terms of SAR information integrated processing of man-made targets, focusing on non-stationary backscattering from building complex, mitigation of azimuth ambiguities in spaceborne stripmap SAR iamges using selective restoration, SAR image despeckling by selective 3D filtering of multiple compressive reconstructed images and man-made target detection in urban areas based on a new azimuth stationary extraction method were proposed. Focusing on three-dimensional modeling and fast extraction of collapsed building, H-a-p method used for collapsed building extraction was proposed.

The existing Synthetic Aperture Radar (SAR) image target detection methods based on convolutional neural networks (CNNs) have achieved remarkable performance, but these methods require a large number of target-level labeled training samples to train the network. Moreover, some clutter is very similar to targets in SAR images with complex scenes, making the target detection task very difficult. Therefore, a SAR target detection network based on a semi-supervised learning and attention mechanism is proposed in this paper. Since the image-level label simply marks whether the image contains the target of interest or not, which is easier to be labeled than the target-level label, the proposed method uses a small number of target-level labeled training samples and a large number of image-level labeled training samples to train the network with a semi-supervised learning algorithm. The proposed network consists of a detection branch and a scene recognition branch with a feature extraction module and an attention module shared between these two branches. The feature extraction module can extract the deep features of the input SAR images, and the attention module can guide the network to focus on the target of interest while suppressing the clutter. During the semi-supervised learning process, the target-level labeled training samples will pass through the detection branch, while the image-level labeled training samples will pass through the scene recognition branch. During the test process, considering the help of global scene information in SAR images for detection, a novel coarse-to-fine detection procedure is proposed. After the coarse scene recognition determining whether the input SAR image contains the target of interest or not, the fine target detection is performed on the image that may contain the target. The experimental results based on the measured SAR dataset demonstrate that the proposed method can achieve better performance than the existing methods.

Synthetic aperture radar (SAR) image target detection and recognition (SAR-TDR) tasks have become research hot spots in the remote sensing application. These targets include ships, vehicles, aircraft, oil tanks, bridges, and so on. However, with the rapid development of SAR technology and increasingly complex electromagnetic environment, complex characteristics of SAR images bring severe challenges to the accurate SAR-TDR via traditional physical models or manual feature-extraction-based machine learning methods. In recent years, deep learning (DL), as a powerful automatic feature extraction algorithm, has been widely used in the computer vision domain. More specifically, DL has also been introduced into the SAR-TDR tasks and has effectively achieved good performance in terms of accuracy, real-time processing, etc. With the rapid development of DL, SAR image processing, and practical requirements of SAR-TDR in civilian and military domains, it is crucial to conduct a systematic survey on SAR-TDR in the past few years. In this survey article, we mainly conduct a systematic overview of DL-based SAR-TDR literature on two tasks, i.e., target recognition (e.g., ground vehicles, ships, and aircraft) and target detection (e.g., ships, aircraft, change detection, sea surface oil spills, and oil tanks). More specifically, our related works about these topics are also presented to verify the effectiveness of DL-based methods. First, several DL methods (e.g., convolutional neural networks, recurrent neural networks, autoencoders, and generative adversarial networks), commonly used in SAR-TDR, are briefly introduced. Then, a systematic review of DL-based SAR-TDR (including our related works) is presented. Finally, the current challenges and future possible research directions are deeply analyzed and discussed.

The purpose of the paper is to extract the region of interest (ROI) from the coarse detected synthetic aperture radar (SAR) images and discriminate if the RO I contains a target or not, so as to eliminate the false alarm, and prepare for the target recognition. Th e automatic target clustering is one of the most difficult tasks in the SAR-image automatic target recognition system. The density-based spatial clustering of applications with noise (DBSCAN) relies on a density-based notion of clusters which is designed to discover clusters of arbitrary shape. DBSCAN was first used in the SAR image processing, which has many excellent features: only two insensitivity parameters (radius of neighborhood and minimum number of points) are needed; clusters of arbitrary shapes which fit in with the coarse detected SAR images can be discovered; and the cal culation time and memory can be reduced. In the multi-feature ROI discrimination scheme, we extract several target features which contain the geometry features such asthe area discriminator and Radon -transform based target profile discriminator, the distribution characteristics such as the EFF discrimina tor, and the EM scattering property such as the PPR discriminator. The synthesized judgment effectively eliminates the false alarms. Keywords: automatic target recognition, synthetic aperture radar images,

We address the application of model-supported exploitation techniques to synthetic aperture radar (SAR) imagery. The emphasis is on monitoring SAR imagery using wide area 2D and/or 3D site models along with contextual information. We consider here the following tasks useful in monitoring: (a) site model construction using segmentation and labeling techniques, (b) target detection, (c) target classification and indexing, and (d) SAR image-site model registration. The 2-D wide area site models used here for SAR image exploitation differ from typical site models developed for RADIUS applications, in that they do not model specific facilities, but constitute wide area site models of cultural features such as urban clutter areas, roads, clearings, fields, etc. These models may be derived directly from existing site models, possibly constructed from electro-optical (EO) observations. When such models are not available, a set of segmentation and labeling techniques described here can be used for the construction of 2D site models. The use of models can potentially yield critical information which can disambiguate target signatures in SAR images. We address registration of SAR and EO images to a common site model. Specific derivations are given for the case of registration within the RCDE platform. We suggest a constant false alarm rate (CFAR) detection scheme and a topographic primal sketch (TPS) based classification scheme for monitoring target occurrences in SAR images. The TPS of an observed target is matched against candidate targets TPSs synthesized for the preferred target orientation, inferred from context (e.g. road or parking lot targets). Experimental results on real and synthetic SAR images are provided.

It is expensive and time-consuming to obtain a large number of labeled synthetic aperture radar (SAR) images. In the task of small training data size, the results of target detection on SAR images using deep network approaches are usually not ideal. In this study, considering that optical remote sensing images are much easier to be labeled than SAR images, we assume to have a large number of labeled optical remote sensing images and a small number of labeled SAR images with the similar scenes, propose to transfer knowledge from optical remote sensing images to SAR images, and develop a domain adaptive Faster R-CNN for SAR target detection with small training data size. In the proposed method, in order to make full use of the label information and realize more accurate domain adaptation knowledge transfer, an instance level domain adaptation constraint is used rather than feature level domain adaptation constraint. Specifically, generative adversarial network (GAN) constraint is applied as the domain adaptation constraint in the adaptation module after the proposals of Faster R-CNN to achieve instance level domain adaptation and learn the transferable features. The experimental results on the measured SAR image dataset show that the proposed method has higher detection accuracy in the task of SAR target detection with small training data size than the traditional Faster R-CNN.

Synthetic aperture radar (SAR) imaging has been widely applied in drones for its consistent surveillance capability and invulnerability to smoke or cloud. Yet drone platform is unstable and observing distance is much shorter than satellite. As a consequence, the SAR image registration, which is a crucial process in SAR imaging, is influenced by sparkling scattering spots and coherent speckle noise. In this paper, we propose a multi-layer method to improve SAR registration performance on drones. ORB method is applied to mitigate sparkle scattering spot. Multi-layer feature clustering can eliminate the error matches by coherent speckle noise. Experiments were carried out to valid the proposed method. Results demonstrate that the proposed method can improve SAR image registration performance on unstable aerial platforms.

The usage of a hypersonic platform for remote sensing application has promising prospects, especially for hypersonic platform-borne synthetic aperture radar (SAR) imaging. However, the high-speed of hypersonic platform will lead to extreme friction between the platform and air, which will cause the ionization of air. The ionized gas forms the plasma sheath wrapped around the hypersonic platform. The plasma sheath will severely affect the propagation of SAR signal and further affect the SAR imaging. Therefore, hypersonic platform-borne SAR imaging should be studied from a physical perspective. In this paper, hypersonic platform-borne SAR imaging under plasma sheath is analyzed. The SAR signal propagation in plasma sheath is computed using scatter matrix method. The proposed SAR signal model is verified by using a ground experiment system. Moreover, the effect of attenuation caused by plasma sheath on SAR imaging is studied under different SAR parameters and plasma sheath. The result shows that attenuation caused by plasma sheath will degrade the SAR imaging quality and even cause the point and area targets to be submerged into the noise. The real SAR images under plasma sheath also illustrate this phenomenon. Furthermore, by studying imaging results under different SAR and plasma parameters, it can be concluded that the severe degradation of SAR imaging quality appears at condition of high plasma sheath electron density and low SAR carrier frequency. The work in this paper will be beneficial for the study of hypersonic platform-borne SAR imaging and design of hypersonic SAR imaging systems in the future.

As an active microwave imaging sensor, Synthetic Aperture Radar (SAR) has become one of the main means of Earth observation owing to its unique technical advantages of all-day, all-weather operation and long working distance. As such, it plays a very important role in military and civilian fields. With the development of SAR remote-sensing technology, high-resolution, high-quality SAR images are produced continuously. However, manual detection and recognition of targets of interest is time-consuming and laborious, so the development of Automatic Target Recognition (ATR) technology is a matter of urgency. The typical SAR ATR system primarily comprises three stages: detection, discrimination, and classification/recognition. The detection and discrimination stages are the basis of the SAR ATR system, and research on SAR applications in the radar field has been conducted by researchers around the world. For single-channel SAR images, target detection and discrimination from simple scenes yield good results. However, in complex scenes, the clutter scattering intensity is relatively high, the clutter background is heterogenous, the target scattering intensity is relatively weak, and the target distribution is dense. These factors continue to make accurate SAR target detection and discrimination difficult. In this paper, we summarize the recent research progress on single-channel SAR target detection and discrimination methods for complex scenes, analyze the characteristics and problems associated with various methods, and consider the future development trend of single-channel SAR target detection and discrimination methods for complex scenes.

Detection of distributed targets such as internal wave or ship wake on sea surface in Synthetic Aperture Radar (SAR) images is an important application of ocean microwave remote sensing. The chaotic characteristic of sea clutter gives some clues to targets detection on sea surface. Speckle, the inherent noise of SAR image, will affect the predictive accuracy of sea clutter adversely and reduce the detection performance of radar. In order to apply the chaotic characteristic of sea clutter to targets detection in SAR images more effectively, an improved chaos-based detection method is proposed in this paper. First, speckle noise is suppressed by undecimated wavelet transform (UWT), and then targets are detected on the basis of the chaotic characteristic of sea clutter from the denoised SAR images. Experimental results prove that the method proposed in this paper is effective for the distributed targets detection in SAR ocean images.

Synthetic aperture radar (SAR) is able to form high-resolution images, which is beneficial for target identification and recognition. However, High-resolution SAR image formation is of immense computation, especially for large scene. In practice, the region of interest (ROI) that needs high resolution imaging may constitute only a small portion of the whole scene. Since ROI detection may only require image resolution much lower than the highest resolution that can be achieved from SAR data, it is efficient to generate an "adequately low resolution" image to find ROI. If target recognition is needed, full-resolution images can be generated for ROI. In this paper, a novel two-stage framework of SAR image formation and processing is developed. Fast factorized back-projection (FFBP) algorithm is introduced to generate SAR images recursively. The FFBP significantly reduces computation complexity with minimal loss in accuracy compared with traditional back-projection (BP) algorithm through recursive stages. At each stage the resolution of images is finer than previously. When the resolution is adequate for target detection, a detection procedure is processed to find ROI in the whole scene. Full resolution image for ROI is then generated by integrating the low resolution images. Moreover, since moving targets appear at different positions in the "adequately low-resolution" image series, moving targets can be also detected. Simulation results show that with single-pass high-resolution SAR data, the method generates low-resolution images quickly for ROI and moving target detection, and provides high-resolution details efficiently for ROI.

In recent years, the rapid development of Deep Learning (DL) has provided a new method for ship detection in Synthetic Aperture Radar (SAR) images. However, there are still four challenges in this task. (1) The ship targets in SAR images are very sparse. A large number of unnecessary anchor boxes may be generated on the feature map when using traditional anchor-based detection models, which could greatly increase the amount of computation and make it difficult to achieve real-time rapid detection. (2) The size of the ship targets in SAR images is relatively small. Most of the detection methods have poor performance on small ships in large scenes. (3) The terrestrial background in SAR images is very complicated. Ship targets are susceptible to interference from complex backgrounds, and there are serious false detections and missed detections. (4) The ship targets in SAR images are characterized by a large aspect ratio, arbitrary direction and dense arrangement. Traditional horizontal box detection can cause non-target areas to interfere with the extraction of ship features, and it is difficult to accurately express the length, width and axial information of ship targets. To solve these problems, we propose an effective lightweight anchor-free detector called R-Centernet+ in the paper. Its features are as follows: the Convolutional Block Attention Module (CBAM) is introduced to the backbone network to improve the focusing ability on small ships; the Foreground Enhance Module (FEM) is used to introduce foreground information to reduce the interference of the complex background; the detection head that can output the ship angle map is designed to realize the rotation detection of ship targets. To verify the validity of the proposed model in this paper, experiments are performed on two public SAR image datasets, i.e., SAR Ship Detection Dataset (SSDD) and AIR-SARShip. The results show that the proposed R-Centernet+ detector can detect both inshore and offshore ships with higher accuracy than traditional models with an average precision of 95.11% on SSDD and 84.89% on AIR-SARShip, and the detection speed is quite fast with 33 frames per second.