As an outstanding method for ocean monitoring, synthetic aperture radar (SAR) has received much attention from scholars in recent years. With the rapid advances in the field of SAR technology and image processing, significant progress has also been made in ship detection in SAR images. When dealing with large-scale ships on a wide sea surface, most existing algorithms can achieve great detection results. However, small ships in SAR images contain little feature information. It is difficult to differentiate them from the background clutter, and there is the problem of a low detection rate and high false alarms. To improve the detection accuracy for small ships, we propose an efficient ship detection model based on YOLOX, named YOLO-Ship Detection (YOLO-SD). First, Multi-Scale Convolution (MSC) is proposed to fuse feature information at different scales so as to resolve the problem of unbalanced semantic information in the lower layer and improve the ability of feature extraction. Further, the Feature Transformer Module (FTM) is designed to capture global features and link them to the context for the purpose of optimizing high-layer semantic information and ultimately achieving excellent detection performance. A large number of experiments on the HRSID and LS-SSDD-v1.0 datasets show that YOLO-SD achieves a better detection performance than the baseline YOLOX. Compared with other excellent object detection models, YOLO-SD still has an edge in terms of overall performance.

Deep learning makes radar-based human activity recognition (HAR) attract more attention in the fields of intelligent security, traffic management, medical rehabilitation and military operation, because it has the ability to automatically extract comprehensive features of human activity. This paper proposes a recognition method based on multi-spectrogram and mixed convolutional neural network (MCNN). Specifically, three time-frequency analyses, including short-time Fourier transform (STFT), reduced interference distribution with Hanning kernel (RIDHK) and smoothed pseudo Wigner-Ville distribution (SPWVD), are performed on radar echo data to obtain the time-frequency spectrograms with different feature expressions, and then the spectrograms are fed into the MCNN for recognition and classification. In the MCNN, three two-dimensional CNNs (2DCNNs) are used to extract the independent spatial features from three types of spectrograms, and one three-dimensional CNN (3DCNN) with unit convolution kernel is employed to focus on extracting the correlation features between three kinds of spectrograms. The behavioral features in the spectrograms are characterized comprehensively by fusing these two kinds of features, which is able to improve the recognition accuracy. Experimental results illustrate that the proposed method improves the average recognition accuracy of eight human activities by at least 2.16% compared with other methods.

Non-line-of-sight (NLOS) detection is widely encountered in military and civilian fields, such as urban battles and disaster rescues. In this study, a novel multipath imaging approach is proposed to solve the problem of multi-target localization behind an L-shaped corner for a single-channel ultra-wide-band (UWB) radar. Specifically, a multipath propagation model based on an L-shaped corner is established, and the positions of virtual radars are analyzed by the specular reflection feature of electromagnetic wave, which forms a virtual array aperture to achieve enough image resolution. Then, the radar echo is mapped based on each propagation path to form multiple images. Finally, according to the trajectory distribution in each image, the incoherent addition is exploited to fuse the multiple images to focus on the target locations. Simulation and experimental results demonstrate that the estimated target positions are consistent with the actual target locations, and the proposed multipath imaging algorithm is applicable in the case of partial path loss.

Owing to the ability of automatic feature extraction, deep learning is extensively applied in human activity recognition (HAR) based on radar. In this paper, a recognition method based on multi-spectrogram and deep learning model is proposed. The radar echo data are transformed into spectrograms with different feature expressions by performing three time-frequency analyses, including short-time Fourier transform (STFT), reduced interference distribution with Hanning kernel (RIDHK) and smoothed pseudo Wigner-Ville distribution (SPWVD), and then the spectrograms are sent to deep learning model to realize HAR. The model employs three long short-term memory (LSTM) networks to learn the temporal features of the spectrograms, and uses three-dimensional convolutional neural network (3DCNN) to extract the independent spatial features of single spectrogram and the spatial correlation features between different kinds of spectrograms, named parallel LSTM-CNN network (PLCN). PLCN is capable of effectively improving the degree of feature utilization in the spectrogram and the accuracy of human activity classification by fusing both temporal and spatial features. The final experimental results show that the average recognition accuracy of the method based on PLCN for eight human activities reaches 94.75%, which is significantly higher than that of the three parallel LSTMs and the single 3DCNN.

This letter mainly deals with the problem of counting moving human targets in an enclosed building space for through-the-wall radar. Specifically, a typical deep convolutional neural network, namely, residual neural network (ResNet), is designed to identify the line-like texture information associated with the target number from the blurred range-time images of a single-channel stepped-frequency continuous-wave (SFCW) radar. Experiments demonstrate that the ResNet-based counting algorithm achieves an accuracy of 91.54% for one to six human targets, and the accuracy rises to 97.12% when only counting one to three humans, even under conditions of wall penetration degradation, limited spatial resolution, heavy multipath clutters, and target-to-target occlusion. The achieved number of information of moving human targets not only contributes directly to the situation assessment behind the wall but also can act as the prior information to promote further target detection.

This paper demonstrates the feasibility of detection and localization of multiple stationary human targets based on cross-correlation of the dual-station stepped-frequency continuous-wave (SFCW) radars. Firstly, a cross-correlation operation is performed on the preprocessed pulse signals of two SFCW radars at different locations to obtain the correlation coefficient matrix. Then, the constant false alarm rate (CFAR) detection is applied to extract the ranges between each target and the two radars, respectively, from the correlation matrix. Finally, the locations of human targets is calculated with the triangulation localization algorithm. This cross-correlation operation mainly brings about two advantages. On the one hand, the cross-correlation explores the correlation feature of target respiratory signals, which can effectively detect all targets with different signal intensities, avoiding the missed detection of weak targets. On the other hand, the pairing of two ranges between each target and two radars is implemented simultaneously with the cross-correlation. Experimental results verify the effectiveness of this algorithm.