Convolutional neural networks (CNN) have successfully been employed to tackle several remote sensing tasks such as image classification and show better performance than previous techniques. For the radar imaging community, a natural question is: Can CNN be introduced to radar imaging and enhance its performance? This letter gives an affirmative answer to this question. We first propose a processing framework by which a complex-valued CNN (CV-CNN) is used to enhance radar imaging. Then we introduce two modifications to the CV-CNN to adapt it to radar imaging tasks. Subsequently, the method to generate training data is shown and some implementation details are presented. Finally, simulations and experiments are carried out, and both results show the superiority of the proposed method on imaging quality and computational efficiency.

Information divergences are commonly used to measure the dissimilarity of two elements on a statistical manifold. Differentiable manifolds endowed with different divergences may possess different geometric properties, which can result in totally different performances in many practical applications. In this paper, we propose a total Bregman divergence-based matrix information geometry (TBD-MIG) detector and apply it to detect targets emerged into nonhomogeneous clutter. In particular, each sample data is assumed to be modeled as a Hermitian positive-definite (HPD) matrix and the clutter covariance matrix is estimated by the TBD mean of a set of secondary HPD matrices. We then reformulate the problem of signal detection as discriminating two points on the HPD matrix manifold. Three TBD-MIG detectors, referred to as the total square loss, the total log-determinant and the total von Neumann MIG detectors, are proposed, and they can achieve great performances due to their power of discrimination and robustness to interferences. Simulations show the advantage of the proposed TBD-MIG detectors in comparison with the geometric detector using an affine invariant Riemannian metric as well as the adaptive matched filter in nonhomogeneous clutter.

Based on a novel prototype terahertz screening system, its ability of fast three-dimensional (3-D) image reconstruction is demonstrated. We first give a brief introduction of the system. Then detailed analyses on signal model, system calibration, the influences of approximations, and the imaging performances are conducted. At last, proof-of-concept experiments are performed and preliminary 2-D and 3-D imaging results are presented. We show that the imaging problem can be resorted to a problem of spectral estimation finally. At this stage on this prototype system, a 180 cm$\,\times\,$90 cm region at 4-m range costs less than 0.1 s for 2-D imaging, 1 s for 3-D imaging and an extra 2 s for mechanical scanning. Faster speeds are on the horizon as hardware and software updates are ongoing. These results show its potential of real-time 3-D imaging for standoff concealed threats detection.

The electromagnetic (EM) vortex imaging has demonstrated superior performance in target detection and imaging with azimuthal super-resolution. However, the restricted elevation resolution degrades the acquisition of target spatial information, which limits the development of the radar imaging technology based on orbital angular momentum (OAM). This article offers a solution to achieve the 3-D EM vortex imaging, by effectively utilizing relative motion between radar and target in the line-of-sight (LOS) direction. First, the forward-looking radar imaging scenario is presented, the 3-D echo model is derived, and the characteristics are analyzed as well. Second, the imaging method, based on the back-projection (BP) and spectrum estimation method, is proposed to obtain the target’s 3-D focused image. Furthermore, the influence factors about the elevation resolution are analyzed by the point spread function (PSF). Finally, simulations are carried out to verify the effectiveness of the theoretical analyses.

A novel three-dimensional (3D) imaging method is proposed, based on the vortex electromagnetic (EM) waves and the stripmap synthetic aperture radar (SAR). Firstly, the imaging model is deduced and the echo characteristics are analyzed. Then, the imaging processing algorithm is proposed to reconstruct the target’s profiles, where the 3D echoes are decomposed into two two-dimensional (2D) echoes. The azimuthal profile can be obtained by performing fast Fourier transform (FFT) in the orbital angular momentum (OAM) domain, and the target information in the y dimension is calculated by the azimuthal distribution, which is as a function of the slow time. The range-Doppler (RD) algorithms used in the fast time and slow time domains to achieve the range profile and cross-range profile. Finally, the target’s 3D image in the Cartesian coordinate is obtained according to the spatial geometric relationship. This work can benefit the applications of OAM-carrying waves in radar realms as well as the development of the 3D imaging technique.

At present, there are two obvious problems in radar-based gait recognition. First, the traditional radar frequency band is difficult to meet the requirements of fine identification with due to its low carrier frequency and limited micro-Doppler resolution. Another significant problem is that radar signal processing is relatively complex, and the existing signal processing algorithms are poor in real-time usability, robustness and universality. This paper focuses on the two basic problems of human gait detection with radar and proposes a human gait classification and recognition method based on millimeter-wave array radar. Based on deep-learning technology, a multi-channel three-dimensional convolution neural network is proposed on the basis of improving the residual network, which completes the classification and recognition of human gait through the hierarchical extraction and fusion of multi-dimensional features. Taking the three-dimensional coordinates, motion speed and intensity of strong scattering points in the process of target motion as network inputs, multi-channel convolution is used to extract motion features, and the classification and recognition of typical daily actions are completed. The experimental results show that we have more than 92.5% recognition accuracy for common gait categories such as jogging and normal walking.