Ground-penetrating radar (GPR) has been widely used to detect subsurface objects. In recent years, deep learning techniques have achieved significant success in image recognition, which has potential implications for interpreting GPR data. However, reliable training of deep learning models requires massive amounts of labeled data, which can be difficult to obtain due to the high costs of data acquisition and field validation. This letter proposes a GPR data augmentation method based on generative adversarial networks (GANs) - Wasserstein GANs (WAEGAN). This proposed method utilizes a GANs model with an encoder E, a joint generator G, and a discriminator D to generate data. A pre-trained classifier C imposes target category constraints on the generated data, while a Wasserstein loss function is employed to stabilize the training process.The performance of the proposed method is evaluated in terms of the validity, diversity, and impact on the classifier performance of the generated fake GPR data. The experimental results verify the superiority of the proposed method in simultaneously generating multiple target categories and generating GPR data that conforms to reality.

Ultra-wideband (UWB) multiple-input multiple-output (MIMO) through-wall radar is widely used in through-wall human target detection for its good penetration characteristics and resolution. However, in actual detection scenarios, weak target masking and adjacent target unresolving will occur in through-wall imaging due to factors such as resolution limitations and differences in human reflectance, which will reduce the probability of target detection. An improved U-Net model is proposed in this paper to improve the detection probability of through-wall targets. In the proposed detection method, a ResNet module and a squeeze-and-excitation (SE) module are integrated in the traditional U-Net model. The ResNet module can reduce the difficulty of feature learning and improve the accuracy of detection. The SE module allows the network to perform feature recalibration and learn to use global information to emphasize useful features selectively and suppress less useful features. The effectiveness of the proposed method is verified via simulations and experiments. Compared with the order statistics constant false alarm rate (OS-CFAR), the fully convolutional networks (FCN) and the traditional U-Net, the proposed method can detect through-wall weak targets and adjacent unresolving targets effectively. The detection precision of the through-wall target is improved, and the missed detection rate is minimized.

Ground-penetrating radar (GPR) has been widely used to detect subsurface objects. However, the target reflection experiences interference owing to clutter, such as direct coupling, interface reflection, and other undesired reflections. Reducing such clutter is a valuable processing step to improve detection accuracy. This letter proposes a GPR clutter reduction algorithm based on dictionary learning (DL). DL learns an adaptive dictionary that can sparsely represent the GPR B-scan image and enable clutter suppression. The learned dictionary atoms are divided into target atoms and clutter atoms, the target component and the clutter component can be reconstructed using these two types of dictionary atoms, respectively. The performance of the proposed algorithm is validated using both simulation data and real GPR data. The results of the visual evaluation and quantitative analysis demonstrate that the proposed algorithm outperforms the existing clutter reduction algorithms.

The life detection radar plays an important role in earthquake rescue, but the vital signal acquired in practice is often submerged in noise. Improving the signal-to-noise ratio (SNR) of through-wall vital signals is still a challenging task. In this paper, we propose a new vital signal enhancement algorithm based on low-rank, sparse representation. The proposed algorithm decomposes the acquired time-frequency image of echo signals into low-rank and sparse components. The low-rank component captures vital signals, and the environmental noise is contained in the sparse component. The proposed algorithm is compared with the traditional Fast Fourier transform (FFT) algorithm and singular value decomposition (SVD) enhanced algorithm through simulation and experimental data verification. Visual images and quantitative data prove that the output SNR of the proposed vital enhancement algorithm is better than that of the FFT and SVD algorithms.

This paper designs a large-depth 3D imaging method for Gaussian beam focusing scanning radar system. It aims to detect continuously moving targets in non-cooperative scenarios. The designed system obtains high resolution in azimuth through multiple-input multiple-output (MIMO) linear array illumination. Cylindrical lenses are used for focused imaging in the height dimension. In addition, in order to extend the imaging depth, the focused area and non-focused area of the Gaussian beam focusing scanning system are defined in this paper, and the corresponding imaging model is constructed. Single-slice imaging algorithm and multi-slice fusion imaging algorithm are proposed for the focused area and non-focused area, respectively. And the detailed formula for solving the defocused image of the non-focused area is derived. In the full imaging scene, each slice of data in the height dimension is unrelated to each other for imaging. High frame rate real-time imaging can be achieved through graphics processing unit (GPU) parallel computing. Finally, the imaging results of the focused area and the non-focused area were verified by experiments. The proposed method effectively expands the depth of the imaging scene.