To achieve efficient ship detection in high-resolution synthetic aperture radar images, an improved superpixel-level constant false alarm rate (CFAR) detection method is proposed with three modifications. First, the weighted information entropy (WIE) describes the statistical characteristics of superpixels, yielding a better distinction between target and clutter superpixels. Second, a two-stage CFAR detection scheme is proposed to detect target superpixels, including global detection and local detection. Specifically, the WIE-based global detector is utilized to prescreen candidate target superpixels (CTSs) and then the local CFAR detector is adaptively conducted over the selected CTSs to refine target superpixels. Third, the superpixels selected by the global detection can be excluded as outliers for clutter estimation, thus the disturbance from adjacent targets in multitarget situations can be reduced and more accurate detection results can be obtained. Compared with CFAR methods implemented with the sliding window technique, the computational burden of the proposed method is significantly reduced without loss of detection performance. Experiments of ship detection on three TerraSAR-X datasets are presented to validate the effectiveness of the proposed method.

For high-resolution range profile (HRRP)-based radar automatic target recognition (RATR), adequate training data are required to characterize a target signature effectively and get good recognition performance. However, collecting enough training data involving HRRP samples from each target orientation is hard. To tackle the HRRP-based RATR task with limited training data, a novel dynamic learning strategy is proposed based on the single-hidden layer feedforward network (SLFN) with an assistant classifier. In the offline training phase, the training data are used for pretraining the SLFN using a reduced kernel extreme learning machine (RKELM). In the online classification phase, the collected test data are first labeled by fusing the recognition results of the current SLFN and assistant classifier. Then the test samples with reliable pseudolabels are used as additional training data to update the parameters of SLFN with the online sequential RKELM (OS-RKELM). Moreover, to improve the accuracy of label estimation for test data, a novel semi-supervised learning method named constraint propagation-based label propagation (CPLP) was developed as an assistant classifier. The proposed method dynamically accumulates knowledge from training and test data through online learning, thereby reinforcing performance of the RATR system with limited training data. Experiments conducted on the simulated HRRP data from 10 civilian vehicles and real HRRP data from three military vehicles demonstrated the effectiveness of the proposed method when the training data are limited.

Compressed sensing (CS)-based frequency agile radar (FAR) is attractive due to its superior data rate and target measurement performance. However, traditional frequency strategies for CS-based FAR are not cognitive enough to adapt well to the increasingly severe active interference environment. In this paper, we propose a cognitive frequency design method for CS-based FAR using reinforcement learning (RL). Specifically, we formulate the frequency design of CS-based FAR as a model-free partially observable Markov decision process (POMDP) to cope with the non-cooperation of the active interference environment. Then, a recognizer-based belief state computing method is proposed to relieve the storage and computation burdens in solving the model-free POMDP. This method is independent of the environmental knowledge and robust to the sensing scenario. Finally, the double deep Q network-based method using the exploration strategy integrating the CS-based recovery metric into the ϵ-greedy strategy (DDQN-CSR-ϵ-greedy) is proposed to solve the model-free POMDP. This can achieve better target measurement performance while avoiding active interference compared to the existing techniques. A number of examples are presented to demonstrate the effectiveness and advantage of the proposed design.

This paper presents a $\mathcal {G}_p^0$ mixture model-based ship detection method for polarimetric synthetic aperture radar (PolSAR) images. The proposed method is based on the assumption that target pixels can be regarded as a general class and that the PolSAR data contain abundant structure and textural information, which may help distinguish target from azimuth ambiguities and clutter. In the proposed method, a weighted combination of $\mathcal {G}_p^0$ distributions is used to characterize the PolSAR data to balance the complexity of parameter estimation and modeling accuracy. The proposed method is capable of automatically determining the number of class with an iterative expectation-maximization algorithm incorporating the $\mathcal {G}_p^0$ distribution. Besides, a prescreening process is integrated to realize computational acceleration. Instead of clustering all pixels in the PolSAR data, only potential target pixels selected in the prescreening stage are clustered. Therefore, fewer class is required to reach convergence due to the removal of most complex background. As a result, better computational efficiency can be achieved. After the clustering, the cluster corresponding to the targets can be distinguished conveniently with the averaged SPAN value of each cluster. The effectiveness and efficiency of the proposed method has been validated by using actual PolSAR datasets and by contrasting the proposed approach with other methods. Experimental results demonstrate its superiority in improving target detection rate while reducing false alarms caused by clutter and azimuth ambiguities.

General synthetic aperture radar (SAR) image automatic target recognition (ATR) methods perform well under standard operation conditions (SOCs). However, they are not effective in extended operation conditions (EOCs). To improve the robustness of the ATR system under various EOCs, an ATR method for SAR images based on the scattering parameter Gaussian mixture model (GMM) is proposed in this paper. First, an improved active contour model (ACM) is used for target–background segmentation, which is more robust against noise than the constant false alarm rate (CFAR) method. Then, as the extracted attributed scattering center (ASC) is sensitive to noise and resolution, the GMM is constructed using the extracted ASC set. Next, the weighted Gaussian quadratic form distance (WGQFD) is adopted to measure the similarity of GMMs for the recognition task, thereby avoiding false alarms and missed alarms caused by the varying number of scattering centers. Moreover, adaptive aspect–frame division is employed to reduce the number of templates and improve recognition efficiency. Finally, based on the public measured MSTAR dataset, different EOCs are constructed under noise, resolution change, model change, depression angle change, and occlusion of different proportions. The experimental results under different EOCs demonstrate that the proposed method exhibits excellent robustness while maintaining low computation time.

This paper presents a microwave imaging algorithm for high-squint airborne synthetic aperture radar (SAR), which combines back-projection and spectrum fusion together. Two spectrum center functions are proposed for linear and nonlinear trajectories respectively, which are the main contributions of this paper, and not considered in conventional work for high-squint SAR. For linear trajectory, the whole aperture data is first divided into sub-apertures with equal length, and the sub-aperture data is backprojected to a unified polar coordinate to generate multiple low-resolution sub-images. Then, these sub-images are corrected by an accurate spectrum center function, which is caused by the presence of squint angle. After spectrum center correction, spectrums of these sub-images can be coherently connected in cross-range wavenumber domain, generating the whole aperture spectrum. Next, the full-resolution image can be obtained by cross-range Fourier transform. For nonlinear trajectory, the deviations introduce extra spectrum shift, which degrades the focusing performance. Another spectrum center function is proposed according to angular-variant motion-error model, which helps to perform precise spectrum fusion. The proposed imaging algorithm is called high-squint accelerated factorized back-projection (HS-AFBP), and it helps to improve the focusing precision. Both the simulation and real data experiments validate the effectiveness of the proposed HS-AFBP algorithm.