A gesture recognition method is proposed in this paper, which leverages millimeter-wave radar point clouds, primarily for identifying six basic human gestures. First, the raw radar signals collected by the MIMO millimeter-wave radar are converted into 3D point cloud sequences using a microcontroller integrated into the radar’s baseband processor. Next, based on the SequentialPointNet network, a multiscale feature extraction module is proposed in this paper, which enhances the network’s ability to extract local and global features through convolutional layers at different scales. This compensates for the lack of feature understanding capability caused by single-scale convolution kernels. Moreover, the CBAM in the network is replaced with GAM, which effectively enhances the extraction of global features by more precisely modeling global contextual information, thereby increasing the network’s focus on global features. A separable MLP structure is introduced into the network. The separable MLP operation is used to separately extract local point cloud features and neighborhood features, and then fuse these features, significantly improving the model’s performance. The effectiveness of the proposed method is confirmed through experiments, achieving a 99.5% accuracy in recognizing six fundamental human gestures, effectively distinguishing between gesture categories, and confirming the potential of millimeter-wave radar 3D point clouds in recognizing gestures.

As electronic warfare becomes the core of modern warfare, radio frequency (RF) stealth radar is becoming the focus of modern electronic warfare. The anti-sorting strategy of RF stealth radar is a new effective method of the anti-enemy electronic reconnaissance system. Hence, research on the failure mechanism of sorting algorithms has become the cornerstone of anti-sorting technology. In this paper, the mechanism of algorithm failure is studied because the SDIF algorithm is widely used in engineering practice throughout the whole workflow of the sequential difference histogram (SDIF) algorithm, from the estimation of pulse repetition interval (PRI) destroyed by the algorithm and algorithm analysis to the staggered signal. Firstly, the working steps of the SDIF histogram sorting algorithm are considered. Key steps of signal sorting by the algorithm are analyzed, and the failure principle of the sorting algorithm is proposed. It is pointed out that if the PRI signal center value of the two groups of radars is within the tolerance range of the sorting algorithm, when the two signal center values are not of the same order of magnitude, the difference is more than 10 times, and the signal variation is less than 30% of the center value, the sorting error of the algorithm for the radar signal is at least 25%. The sorting algorithm fails to sort signals. At the same time, for the sorting failure of the staggered signal, the sub-PRI design formula of the staggered signal is proposed, and the staggered signal satisfying the design formula can make the sorting algorithm invalid. Finally, the correctness of the SDIF failure principle is further verified by formula derivation, signal design simulation and experiment. The principle of sorting failure provides theoretical support and foundation for the design of anti-sorting RF stealth signal. The principle of sorting failure makes up for the shortcomings of random signal design and improves the design efficiency of RF stealth signal.

Anti-sorting signal design is an important direction of radio frequency (RF) stealth signal design. The RF stealth signal design is based on the anti-sorting signal design principle, which is essentially the failure principle of the radar signal sorting algorithm. Cluster pre-sorting, the key to radar signal sorting, has the advantages of fast sorting, simultaneous sorting of multiple sources, and greatly reduced computational pressure of the main sorting. However, a unified and widely applicable cluster-sorting failure principle guiding the anti-sorting signal design has not been formally reported in RF stealth anti-sorting signal design. In this paper, the principles of the data field-based K-means clustering algorithm and the fuzzy C-means clustering algorithm are first studied. Aiming at the key step of data similarity measurement in the clustering algorithm, the failure principle of cluster sorting based on pseudo-center wide-agile multi-dimensional compound modulation is proposed. This principle can correctly guide the design of the anti-clustering sorting signal, so it is also called the design principle of the RF stealth anti-sorting signal based on pseudo-center wide-agile multi-dimensional compound modulation. The correctness of the principle is proved by formula derivation, signal simulation, and a sorting experiment. Through a signal comparison simulation with random interference pulse anti-sorting signals, it is strongly proved that the anti-sorting performance of signals designed under the guidance of the anti-clustering signal design principle proposed in this paper is stronger than that of random interference pulse signals. This study provides theoretical support for designing RF stealth anti-sorting signals. Using the signal design principle proposed in this paper, the anti-sorting performance of the RF stealth signal is improved by 10%. The principle of signal design helps to improve design efficiency.

The superheterodyne digital receiver (SDR) is the main equipment for frequency guidance in modern digital radio frequency memory (DRFM) jamming devices. Lo

A radar with a limited aperture may lack sufficient cross-range resolution to separate closely spaced members of an unmanned aerial vehicle (UAV) swarm. This paper proposes a localization method that combines lateral-Doppler scaling, data-driven estimation of the equivalent cross-range reference velocity, and acceleration-hypothesis backprojection (BP). The reference velocity is estimated by maximizing a regularized spatial-concentration criterion, and target-dependent motion is accommodated by pixel-wise maximum fusion over an acceleration grid. For a fixed 15-target formation with acceleration scales from 1.8 to 9 m/s², the method achieved conditional localization RMSE values of 0.81–1.15 m and single-scene detection rates of 0.87–1.00. The differences relative to range–Doppler (RD) and second- and third-order Taylor-Chirplet processing were most pronounced at the larger acceleration scales. Monte Carlo experiments with randomized noise and Swerling-I scattering further showed that maximum fusion yielded higher matched-detection probabilities and lower miss-penalized RMS errors than mean fusion and a zero-acceleration baseline over per-pulse SNRs from $-18$ to $-6$ dB. Acceleration-grid, PRF, and reference-velocity sweeps characterized the associated computational trade-offs and operating range.