With the rapid development of emitter individual identification technology in cognitive radio networks, electromagnetic emitter individual target identification based on deep learning has received much attention. However, the confusion of unintentional features (i.e., individual fingerprint features) and modulation features resulting from the received signal might lead to low identification accuracy. In order to address this narrow, we propose an emitter individual identification network based on the competitive collaboration framework, called Specific Emitter Identification with Adaptive Decomposition and Extraction of individual fingerprint features (SEI-ADE), which can adaptively decompose and extract individual fingerprint features. Firstly, a signal adaptive decomposition network is proposed to distinguish the emitter signal and the interference signal by adopting the gradient inversion layer and the non-sequential characteristics of the signal. Then, in order to distinguish and extract corresponding features, the feature extractor and the training loss constraints are constructed for individual fingerprint feature signals, modulation signals, and external emitter interference signals, respectively. The proposed framework can continuously adjust the gradient loss, classification loss, and timing coding contrast loss, thus minimizing the entire training loss. For the separation of the modulation signal and individual fingerprint feature signal, the signal is transformed into the feature domain, and a mask prediction network is proposed to locate the domain of the individual fingerprint feature. The obtained experimental results show the outstanding performance of our proposal, compared with the current benchmarks. All our models and code are available athttps://github.com/jn-z/SEI-ADE.

This paper focuses on the problem of reconfigurable intelligent surface (RIS) aided co-design for multiple-input-multiple-output (MIMO) radar and MIMO communication systems with shared spectrum resources. The purpose is to maximize the radar output signal-to-interference-plus-noise-ratio (SINR) while ensuring the communication functionalities, where there is no line-of-sight (NLOS) propagation between the radar and the target. To achieve the goal, we develop a cyclic framework based on semi-definite programming (SDP), semi-definite relaxation (SDR), and alternating direction method of multiplier (ADMM) to jointly optimize the radar transmit waveforms, the receive filters, the communication codebook, and the RIS coefficients. Numerical experiments are conducted to evaluate the effectiveness of the proposed algorithm.

Multitask joint learning technology continues gaining more attention as a paradigm shift and has shown promising performance in many applications. Depth estimation and semantic understanding from monocular images emerge as a challenging problem in computer vision. While the other joint learning frameworks establish the relationship between the semantics and depth from stereo pairs, the lack of learning camera motion renders the frameworks that fail to model the geometric structure of the image scene. We make a further step in this article by proposing a multitask learning method, namely DPSNet, which can jointly perform depth and camera pose estimation and semantic scene segmentation. Our core idea for depth and camera pose prediction is that we present the rigid semantic consistency loss to overcome the limitation of moving pixels from image reconstruction technology and further infer the segmentation of moving instances based on them. In addition, our proposed model performs semantic segmentation by reasoning the geometric correspondences between the pixel semantic outputs and the semantic labels at multiscale resolutions. Experiments on open-source datasets and a video dataset captured on a micro-smart car show the effectiveness of each component of DPSNet, and DPSNet achieves state-of-the-art results in all three tasks compared with the best popular methods. All our models and code are available at https://github.com/jn-z/DPSNet: Multitask Learning Using Geometry Reasoning for Scene Depth and semantics.

This letter deals with the joint design of transmit waveform and receive filter bank for airborne multiple-input multiple-output (MIMO) radar under the target uncertainties. Assuming that the spatial angle and the Doppler frequency of the target are unknown, we formulate the maximin joint design problem by maximizing the worst-case signal-to-interference-plus-noise ratio (SINR) under the energy constraint, flexible modulus constraint, and similarity constraint on the transmit waveform. To tackle this problem, we develop a computationally efficient algorithm based on iterative feasible point pursuit successive convex approximation (FPP-SCA). Numerical results are provided to demonstrate the effectiveness and robustness of the proposed algorithm.

The mutual interference between similar radar systems can result in reduced radar sensitivity and increased false alarm rates. To address the interference mitigation problems in similar radar systems, we propose herein two slow-time coding schemes to modulate the pulses within a coherent processing interval (CPI). Specifically, the first coding scheme is designed through Doppler shifting and the second is devised via an optimization method. The proposed coding schemes are very easy to implement in practice and the incorporation of the coding schemes only requires slight modification of the existing systems. Our numerical examples indicate that the proposed coding schemes can reduce the interference power level in a desired area of the cross-ambiguity function significantly.

Focusing on the faint turbulent wake detection in polarimetric synthetic aperture radar (PolSAR) images, this letter introduces a novel two-step (coarse and fine processing) detector. Based on the polarization decomposition theory, a new parameter that enhances the contrast between wake and sea, which is called surface scattering randomness (SSR), is proposed. The coarse detection process extracts the regions of potential ship wakes by digital axoids transform of SSR. During the fine detection process, the regions detected by the coarse detection are segmented and processed independently in the polarization feature domain. Finally, by introducing the regularity least-squares method, the line parameters of ship wake are obtained, while the a priori knowledge is obtained from Radon transform. Experiments are performed on Radarsat-2 data, and the results demonstrate that the proposed algorithm has strong ability to detect faint turbulent wake in PolSAR images compared with the current detectors, which are based on the Radon or Hough transform.

This paper investigates the waveform design problem of wideband cognitive radar for the detection of extended targets in which the knowledge of target impulse response and interference is imprecise. We resort to a maximin approach to design the waveform that is robust to the model uncertainties, i.e., we optimize the waveform to maximize the worst-case signal to interference plus noise ratio (SINR) over the uncertainty region. We show that the maximin waveform design problem can be formulated into a convex optimization problem. Results indicating the robustness of the proposed method are provided via numerical simulations.

Due to its long-standing importance, the problem of designing the receive filter and transmit sequence for clutter/interference rejection in active sensing has been studied widely in the last decades. In this letter, we propose a cyclic optimization of the transmit sequence and the receive filter. The proposed approach can handle arbitrary peak-to-average-power ratio (PAR) constraints on the transmit sequence, and can be used for large dimension designs (with ~ 103variables) even on an ordinary PC.

In this letter, we analyze the convergence rate of loaded sample matrix inversion (LSMI) algorithm in amplitude heterogeneous clutter environment. The probability density function of output signal to interference and noise ratio loss (SINR Loss) is derived. Then we give an approximate expression of average SINR loss. Compared with the case where samples used for estimation of covariance matrix of cell under test (CUT) are independent and identically distributed (i.i.d.) with the snapshot of CUT, if the clutter to noise ratio (CNR) of the training samples is larger than that of CUT, the convergence rate of LSMI is faster and output SINR is higher; conversely, the convergence rate of LSMI is slower and SINR is lower. Simulation validates the theoretical analysis.