The method proposed in this letter for synthetic aperture radar (SAR) image classification has two main stages. In the first stage, a convolutional neural network (CNN) is trained for normal SAR image classification task. After training, the sample features can be obtained by extracting the output of middle layer in the forward propagation process of CNN. In the second stage, an end-to-end metric network is trained to measure the relations between sample features. The method proposed in this letter is tested with some of the larger targets in OpenSARShip data set which is collected from Sentinel-1 satellite, and it is also tested with the MSTAR data set which is created by the U.S. Air Force Laboratory. The experimental results show that our method can get a higher recognition accuracy than normal CNN structure.

As a typical navigation system, the strapdown inertial navigation system (SINS) is crucial for autonomous underwater vehicles (AUVs) since the SINS accuracy determines the performance of AUVs. Initial alignment is one of the key technologies in SINS, and initial alignment time and initial alignment accuracy affect the performance of SINS directly. As actual systems are nonlinear, the nonlinear filter is widely used to improve the accuracy of the initial alignment. Due to its higher precision and lower computational load, the cubature Kalman filter (CKF) has done well in state estimation. However, the noise characteristics need to be known exactly as prior knowledge, which is difficult or even impossible to achieve. Thus, the adaptive filter should be introduced in the initial alignment algorithm to suppress the uncertainty effect caused by the unknown system noise. Therefore, taking the nonlinearity and uncertainty into account, a novel initial alignment algorithm for AUVs is proposed in this manuscript, based on CKF and the adaptive variance components estimation (VCE) filter (VCKF). Additionally, the simulation and experiment results show that not only the accuracy, but also the convergence speed can be improved with this proposed method. The validity and superiority of this novel adaptive initial alignment algorithm based on VCKF are verified.

You only look once (YOLO) is one of the most efficient target detection networks. However, the performance of the YOLO network decreases significantly when the variation between the training data and the real data is large. To automatically customize the YOLO network, we suggest a novel transfer learning algorithm with the sequential Monte Carlo probability hypothesis density (SMC-PHD) filter and Gaussian mixture probability hypothesis density (GM-PHD) filter. The proposed framework can automatically customize the YOLO framework with unlabelled target sequences. The frames of the unlabelled target sequences are automatically labelled. The detection probability and clutter density of the SMC-PHD filter and GM-PHD are applied to retrain the YOLO network for occluded targets and clutter. A novel likelihood density with the confidence probability of the YOLO detector and visual context indications is implemented to choose target samples. A simple resampling strategy is proposed for SMC-PHD YOLO to address the weight degeneracy problem. Experiments with different datasets indicate that the proposed framework achieves positive outcomes relative to state-of-the-art frameworks.

Distributed consensus formation tracking problem of slow convergence and low accuracy for multiple quad rotors are solved in this paper. Continuous nonsingular terminal sliding model algorithm (CNTSMA) under Inner-Outer loop control structure is considered to deal with the control problem of nonlinear, strong coupling and underactuated characteristic of a quad rotor. For better convergence and higher tracking accuracy, an adaptive algorithm (denoted by ACNTSMA) further focused on coupling of x and y directions, with sliding model observer (SMO) to compensate system disturbances and uncertainties is proposed. Furthermore, to solve the consensus formation tracking problem, a consensus control protocol under a full-connected topology based on ACNTSMA is proposed, including formation pattern consensus controller and formation distance consensus controller. Stability theory and simulation results prove the proposed control algorithm is able to accurately achieve the first-order (position and velocity) consensus for multiple quad rotors’ formation tracking. Besides, stability analysis of the proposed consensus control protocol illustrates that all sliding modes with finite-time stability applicable to second-order integral models are supposed to be established. And the proposed controller also has better convergence and faster response speed with no chattering for trajectory tracking.

In this paper, we focus on the interference management in the cognitive radio (CR) network comprised of multiple primary users (PUs) and multiple secondary users (SUs). Firstly, two interference alignment (IA) schemes are proposed to mitigate the interference among PUs. The first one is an interference rank minimization (IRM) scheme, which aims to minimize the rank of the joint interference matrix via alternating between the forward and reverse communication links. Considering the overhead of information exchanged between the transmitters and receivers in the IRM scheme, we further develop an interference subspace distance minimization (ISDM) scheme which runs at the transmitters only. The ISDM scheme focuses on aligning the subspaces spanned by interference with an aligned subspace introduced in this paper. For the secondary network, though IRM and ISDM mitigate the received interference at secondary receivers, they make no attempt to eliminate the interference from SUs to PUs. To address this, we improve the IRM and ISDM schemes by putting a rank constraint into their optimizations, where the rank constraint forces the ranks of the interference matrices from SUs to PUs to be zero. Simulation results validate the effectiveness of the proposed schemes in terms of the average sum rate.