According to the real-living environment, radar-based human activity recognition (HAR) is dedicated to recognizing and classifying a sequence of activities rather than individual activities, thereby drawing more attention in practical applications of security surveillance, health care and human–computer interactions. This paper proposes a parallelism long short-term memory (LSTM) framework with the input of multi-frequency spectrograms to implement continuous HAR. Specifically, frequency-division short-time Fourier transformation (STFT) is performed on the data stream of continuous activities collected by a stepped-frequency continuous-wave (SFCW) radar, generating spectrograms of multiple frequencies which introduce different scattering properties and frequency resolutions. In the designed parallelism LSTM framework, multiple parallel LSTM sub-networks are trained separately to extract different temporal features from the spectrogram of each frequency and produce corresponding classification probabilities. At the decision level, the probabilities of activity classification from these sub-networks are fused by addition as the recognition output. To validate the proposed method, an experimental data set is collected by using an SFCW radar to monitor 11 participants who continuously perform six activities in sequence with three different transitions and random durations. The validation results demonstrate that the average accuracies of the designed parallelism unidirectional LSTM (Uni-LSTM) and bidirectional LSTM (Bi-LSTM) based on five frequency spectrograms are 85.41% and 96.15%, respectively, outperforming traditional Uni-LSTM and Bi-LSTM networks with only a single-frequency spectrogram by 5.35% and 6.33% at least. Additionally, the recognition accuracy of the parallelism LSTM network reveals an upward trend as the number of multi-frequency spectrograms (namely the number of LSTM subnetworks) increases, and tends to be stable when the number reaches 4.

In this paper, we propose an approach that uses generative adversarial nets (GAN) to eliminate multipath ghosts with respect to through-wall radar imaging (TWRI). The applied GAN is composed of two adversarial networks, namely generator G and discriminator D. Generator G learns the spatial characteristics of an input radar image to construct a mapping from an input to output image with suppressed ghosts. Discriminator D evaluates the difference (namely, the residual multipath ghosts) between the output image and the ground-truth image without multipath ghosts. On the one hand, by training G, the image difference is gradually diminished. In other words, multipath ghosts are increasingly suppressed in the output image of G. On the other hand, D is trained to improve in evaluating the diminishing difference accompanied with multipath ghosts as much as possible. These two networks, G and D, fight with each other until G eliminates the multipath ghosts. The simulation results demonstrate that GAN can effectively eliminate multipath ghosts in TWRI. A comparison of different methods demonstrates the superiority of the proposed method, such as the exemption of prior wall information, no target images with degradation, and robustness for different scenes.

Through-wall-radar imaging is of interest for mapping the wall layout of buildings and for the detection of stationary targets within buildings. In this paper, we present an easy single-side two-location spotlight imaging method for both wall layout mapping and stationary target detection by utilizing multiple-input multiple-output (MIMO) through-wall-radar. Rather than imaging for building walls directly, the images of all building corners are generated to speculate wall layout indirectly by successively deploying the MIMO through-wall-radar at two appropriate locations on only one side of the building and then carrying out spotlight imaging with two different squint-views. In addition to the ease of implementation, the single-side two-location squint-view detection also has two other advantages for stationary target imaging. The first one is the fewer multi-path ghosts, and the second one is the smaller region of side-lobe interferences from the corner images in comparison to the wall images. Based on Computer Simulation Technology (CST) electromagnetic simulation software, we provide multiple sets of validation results where multiple binary panorama images with clear images of all corners and stationary targets are obtained by combining two single-location images with the use of incoherent additive fusion and two-dimensional cell-averaging constant-false-alarm-rate (2D CA-CFAR) detection.

Wind profiler radar (WPR) is used for all-weather atmospheric wind-field monitoring. However, the reliability of these observations reduces significantly when there is electromagnetic interference echo, generally caused by ground objects, birds, or rain. Therefore, to optimize the data reliability of WPR, we proposed a synthetic data quality control process. The process included the application of a minimum connection method, judgment rule, and median test optimization algorithm for optimizing clutter suppression, spectral peak symmetry detection, and radial speed, respectively. We collected the base data from a radiosonde and multiple radars and conducted an experiment using these data and algorithms. The results indicated that the quality control method: (1) had good adaptability to multiple WPRs both in clear sky and precipitation; (2) was useful for suppressing ground clutter and (3) was superior to those of the manufacturer as a whole. Thus, the data quality control method proposed in this study can improve the accuracy and reliability of WPR products and multiple types of WPR, even when they function under vastly different weather conditions.