Explore the vast range of titles available.

With the wide application of convolutional neural networks (CNNs), a variety of ship detection methods based on CNNs in synthetic aperture radar (SAR) images were proposed, but there are still two main challenges: (1) Ship detection requires high real-time performance, and a certain detection speed should be ensured while improving accuracy; (2) The diversity of ships in SAR images requires more powerful multi-scale detectors. To address these issues, a SAR ship detector called Duplicate Bilateral YOLO (DB-YOLO) is proposed in this paper, which is composed of a Feature Extraction Network (FEN), Duplicate Bilateral Feature Pyramid Network (DB-FPN) and Detection Network (DN). Firstly, a single-stage network is used to meet the need of real-time detection, and the cross stage partial (CSP) block is used to reduce the redundant parameters. Secondly, DB-FPN is designed to enhance the fusion of semantic and spatial information. In view of the ships in SAR image are mainly distributed with small-scale targets, the distribution of parameters and computation values between FEN and DB-FPN in different feature layers is redistributed to solve the multi-scale detection. Finally, the bounding boxes and confidence scores are given through the detection head of YOLO. In order to evaluate the effectiveness and robustness of DB-YOLO, comparative experiments with the other six state-of-the-art methods (Faster R-CNN, Cascade R-CNN, Libra R-CNN, FCOS, CenterNet and YOLOv5s) on two SAR ship datasets, i.e., SSDD and HRSID, are performed. The experimental results show that the AP50 of DB-YOLO reaches 97.8% on SSDD and 94.4% on HRSID, respectively. DB-YOLO meets the requirement of real-time detection (48.1 FPS) and is superior to other methods in the experiments.

Multi-station TDOA positioning is a more accurate positioning method, which can locate the acoustic emitter by processing the arrival time of signals collected by three or more measuring stations. This paper presents a closed-form localization algorithm using the angle-of-arrival and difference time of scan time measurements from the scan-based sonar (SBS).The basic principle of multi station TDOA passive location is proposed. Location scheme based on the combination of different platforms is used. The basic principle of TDOA passive location is discussed, as well as the realization scheme of the main problems such as the synchronization of observation station and acoustic target, the selection of ground observation station, error correction and so on.

In this paper, an output error (OE) model with random time delay is identified by using the expectation maximization (EM) algorithm. Since the regression model of the OE system has a colored noise, the finite impulse response (FIR) method is used to transform the OE model into an FIR model, whose regression model contains a white noise. An EM algorithm is proposed to iteratively estimate the time-delays and model parameters. Furthermore, the parameters of the OE model can be yielded based on the parameter estimates of the FIR model through the matrix transformation method. The convergence analysis and simulation results are given to illustrate the effectiveness of the proposed algorithm.

The single-pixel imaging (SPI) technique enables the tracking of moving targets at a high frame rate. However, when extended to the problem of multi-target tracking, there is no effective solution using SPI yet. Thus, a multi-target tracking method using windowed Fourier single-pixel imaging (WFSI) is proposed in this paper. The WFSI technique uses a series of windowed Fourier basis patterns to illuminate the target. This method can estimate the displacements of K independently moving targets by implementing 6K measurements and calculating 2K windowed Fourier coefficients, which is a measurement method with low redundancy. To enhance the capability of the proposed method, we propose a joint estimation approach for multi-target displacement, which solves the problem where different targets in close proximity cannot be distinguished. Using the independent and joint estimation approaches, multi-target tracking can be implemented with WFSI. The accuracy of the proposed multi-target tracking method is verified by numerical simulation to be less than 2 pixels. The tracking effectiveness is analyzed by a video experiment. This method provides, for the first time, an effective idea of multi-target tracking using SPI.

Membership function identification is an important part of studying fuzzy control theory. Gaussian membership functions are widely used in the defuzzification processes, while the simple fuzzy processing reduces the dynamic characteristics of models. In order to reflect the dynamic performance of the nonlinear systems accurately, this paper introduces the idea of the multi-model control and fits a kernel function for the defuzzification processes by selecting the scheduling modes. Based on the gradient search, we present a least mean square (LMS) algorithm to solve the parameter estimation problem of the nonlinear systems. Considering the difficulty of determining the step sizes in the LMS algorithm, an overall stochastic gradient (O-SG) algorithm is deduced to obtain the optimal step size and estimate the unknown parameters. In order to improve the estimation accuracy, we introduce a forgetting factor into the O-SG algorithm to obtain the overall forgetting factor stochastic gradient (O-FFSG) algorithm. With the appropriate forgetting factors, the O-FFSG algorithm can effectively used for identifying the nonlinear systems. The performances of the proposed algorithms are tested by a numerical example.

This paper studies the identification problems of a nonlinear finite impulse response system with saturation nonlinearity. Introducing a symbolic function, an over-parameterization gradient-based iterative algorithm is presented for estimating the parameters of the nonlinear system with saturation nonlinearity. In order to enhance the computational efficiency, a gradient-based iterative algorithm and a hierarchical gradient-based iterative algorithm are presented for the nonlinear systems. The computational loads of these algorithms are analyzed and compared.

The parameter estimation problem of the ARX model is studied in this paper. First, some traditional identification algorithms are briefly introduced, and then a new parameter estimation algorithm—the modified momentum gradient descent algorithm—is developed. Two gradient directions with their corresponding step sizes are derived in each iteration. Compared with the traditional parameter identification algorithms, the modified momentum gradient descent algorithm has a faster convergence rate. A simulation example shows that the proposed algorithm is effective.

The instrument detection methods of underwater part of beach obstacle mainly include multi-beam bathymetric system and three-dimensional panoramic imaging sonar system. SeaBat T50-P multi beam bathymetry and BV5000-1350 sonar system are widely used in the area of underwater detection. The underwater part of beach obstacles is measured and analyzed, and the application scope of both equipment is discussed. The results show that the BV5000-1350 sonar system can be used to detect underwater incomplete obstacles with wider application scope, high accuracy, convenient installation of instruments, and no auxiliary equipment such as navigation, positioning and attitude sensor is needed; SeaBat T50-P multi-beam bathymetric system has high requirements for the structure of the measured object, moderate accuracy, and is more suitable for large-scale underwater obstacle survey.

The traditional least squares (LS) and gradient descent (GD) algorithms can estimate the parameters of the regression models. They can be inefficient when the models have complex structures: (1) the unknown parameters in the information vector make the algorithm be impossible to update the parameters; (2) the zigzagging nature of the gradient descent algorithm and the complex structures lead to slow convergence rates; and (3) the step-size and derivative function calculations may be unsolvable for complex nonlinear models. This paper proposes two kinds of algorithms for exponential nonlinear models. The first is the two-stage algorithm, which decomposes the complex model into a linear part and a nonlinear part, where the linear part is estimated using the LS algorithm and the nonlinear part is identified based on the GD algorithm. The second is the particle swarm optimization algorithm which can simultaneously obtain all the parameters. To increase the convergence rates, the Aitken method is also introduced. The simulation results demonstrate the effectiveness of the proposed algorithms.

The classification and recognition of radar clutter is helpful to improve the efficiency of radar signal processing and target detection. In order to realize the effective classification of uniform circular array (UCA) radar clutter data, a classification method of ground clutter data based on the chaotic genetic algorithm is proposed. In this paper, the characteristics of UCA radar ground clutter data are studied, and then the statistical characteristic factors of correlation, non-stationery and range-Doppler maps are extracted, which can be used to classify ground clutter data. Based on the clustering analysis, results of characteristic factors of radar clutter data under different wave-controlled modes in multiple scenarios, we can see: in radar clutter clustering of different scenes, the chaotic genetic algorithm can save 34.61% of clustering time and improve the classification accuracy by 42.82% compared with the standard genetic algorithm. In radar clutter clustering of different wave-controlled modes, the timeliness and accuracy of the chaotic genetic algorithm are improved by 42.69% and 20.79%, respectively, compared to standard genetic algorithm clustering. The clustering experiment results show that the chaotic genetic algorithm can effectively classify UCA radar’s ground clutter data.