检索结果-内蒙古大学图书馆

IET International radar Conference (IRC 2023)

作者： Junxiang Yang Ying Zhou Hui Ma Kun Lv Hongwei Liu Lin Liu National Key Laboratory of Radar Signal Processing Xidian University Xi'an People's Republic of China Beijing Institute of Remote-sensing Equipment Science and Technology on Millimeter-wave Laboratory Beijing People's Republic of China

ISBN: (数字)9781837240982

The application of deep learning to fast radar data processing has important significance. The effectiveness of complex deep neural networks (CDNNs) has recently been demonstrated, and complex networks are important for processing complex data because they have the ability to handle phases. And the complex-valued activation function introduces a nonlinear transformation to the network, which has a great potential to improve the network performance. In this paper, we test the feasibility of CDNNs and the effect of different activation functions in the framework of complex networks under the goal of retaining more phase information. In particular, we propose a new complex-valued activation RℂReLU based on RℂeLu and test its performance in a classification and auto-encoder context. Finally, we perform radar imaging reconstruction by different activation functions in complex networks, and the results show that RℂReLU is more suitable for processing radar data in CDNNs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Least-Squares-Based Algorithm for Estimating ATI SAR Interferometric Phase Errors

A Least-Squares-Based Algorithm for Estimating ATI SAR Inter...

引用

signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Zhibin Wang Huancheng Guo Qingjun Zhang Zhang Qi Zhengfang Li Changshan He Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China National Key Laboratory of Radar Signal Processing Xidian University Xi’an China School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

ATI SAR systems have immense potential for high-resolution, wide-swath measurements of sea surface currents. However, due to the sensitivity of ATI interferometric phase to phase errors, the retrieval of sea surface currents using ATI technology often relies on ground scene calibration. To address this issue, we first review the principles of ATI SAR sea surface current measurement and analyze the sources and characteristics of phase errors. Based on this analysis, we propose a least-squares-based method for estimating and compensating ATI SAR phase errors. This method ensures robust estimation and correction of phase errors by accounting for their distinct distribution characteristics. Finally, we validate the proposed method using data from the PIESAT-1 satellite constellation, demonstrating its effectiveness.

关键词： Sea surface Satellite constellations Sensitivity Reviews Current measurement Estimation Sea measurements Data processing radar polarimetry Calibration

来源：评论

学校读者我要写书评

暂无评论

Adaptively feature matching via joint transformational-spatial clustering

Adaptively feature matching via joint transformational-spati...

引用

作者： Wang, Linbo Tan, Li Fang, Xianyong Guo, Yanwen Wan, Shaohua MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei China National Key Lab for Novel Software Technology Nanjing University Nanjing China School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan China

The transformational and spatial proximities are important cues for identifying inliers from an appearance based match set because correct matches generally stay close in input images and share similar local transformations. However, most existing approaches only check one type of them or both types consecutively with manually set thresholds, and thus their matching accuracy and flexibility in handling large-scale images are limited. In this paper, we present an efficient clustering based approach to identify match inliers with both proximities simultaneously. It first projects the putative matches into a joint transformational-spatial space, where mismatches tend to scatter all around while correct matches gather together. A mode-seeking process based on joint kernel density estimation is then proposed to obtain significant clusters in the joint space, where each cluster contains matches mapping the same object across images with high accuracy. Moreover, kernel bandwidths for measuring match proximities are adaptively set during density estimation, which enhances its applicability for matching different images. Experiments on three standard datasets show that the proposed approach delivers superior performance on a variety of feature matching tasks, including multi-object matching, duplicate object matching and object retrieval. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Clustering Density estimation Feature matching Mode-seeking

来源：评论

学校读者我要写书评

暂无评论

A Novel Strong Clutter Suppression Algorithm for Airborne Passive radar

A Novel Strong Clutter Suppression Algorithm for Airborne Pa...

引用

2021 CIE International Conference on radar, radar 2021

作者： Sui, Jinxin Wang, Jun Gao, Jie Fan, Xiaoyan Xidian University National Laboratory of Radar Signal Processing Xi'an710071 China Xi'an Institute of Space Radio Technology National Key Laboratory of Space Microwave Technology Xi'an710100 China

ISBN: (纸本)9781665498142

Owing to the continuous random and non-periodic characteristics of the passive signal, the random range sidelobe coupling (RRSC) effects of the strong clutter will exacerbate the performance of space-time adaptive processing (STAP) algorithm in airborne passive radar (APR). In this paper, a cascaded least square algorithm (CLS) based on the directional dependence of clutter Doppler frequency is proposed for side-looking APR to suppress strong clutter. The advantage of the method is that it cannot only cancel clutter along the clutter ridge, but also effectively prevent the suppression of targets falling in the clutter Doppler band. A series of simulations are conducted to test the proposed algorithms. © 2021 IEEE.

关键词： airborne passive radar cascaded least square algorithm random range sidelobe

来源：评论

学校读者我要写书评

暂无评论

Integrating Conjugate Gradients Into Evolutionary Algorithms for Large-Scale Continuous Multi-Objective Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1801-1817页

作者： Ye Tian Haowen Chen Haiping Ma Xingyi Zhang Kay Chen Tan Yaochu Jin the Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China the Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230601China IEEE the Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial IntelligenceAnhui UniversityHefei 230601China the Department of Computing The Hong Kong Polytechnic UniversityHong Kong SARChina the Faculty of Technology Bielefeld UniversityBielefeld 33619Germany

Large-scale multi-objective optimization problems(LSMOPs)pose challenges to existing optimizers since a set of well-converged and diverse solutions should be found in huge search *** evolutionary algorithms are good at solving small-scale multi-objective optimization problems,they are criticized for low efficiency in converging to the optimums of *** contrast,mathematical programming methods offer fast convergence speed on large-scale single-objective optimization problems,but they have difficulties in finding diverse solutions for ***,how to integrate evolutionary algorithms with mathematical programming methods to solve LSMOPs remains *** this paper,a hybrid algorithm is tailored for LSMOPs by coupling differential evolution and a conjugate gradient *** the one hand,conjugate gradients and differential evolution are used to update different decision variables of a set of solutions,where the former drives the solutions to quickly converge towards the Pareto front and the latter promotes the diversity of the solutions to cover the whole Pareto *** the other hand,objective decomposition strategy of evolutionary multi-objective optimization is used to differentiate the conjugate gradients of solutions,and the line search strategy of mathematical programming is used to ensure the higher quality of each offspring than its *** comparison with state-of-the-art evolutionary algorithms,mathematical programming methods,and hybrid algorithms,the proposed algorithm exhibits better convergence and diversity performance on a variety of benchmark and real-world LSMOPs.

关键词： Conjugate gradient differential evolution evolutionary computation large-scale multi-objective optimization mathematical programming

来源：评论

学校读者我要写书评

暂无评论

A Sparse Recovery Method on EPC-MIMO radar System

A Sparse Recovery Method on EPC-MIMO Radar System

引用

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： Kun Liu Xiongpeng He Guisheng Liao Jingwei Xu Shengqi Zhu Yifan Guo National Laboratory of Radar Signal Processing Xidian University Xi'an China School of Marine Science and technology Northwestern Polytechnical University Xi'an China

Multiple-Input Multiple-Output radar with Element-Pulse Coding (EPC) is a novel way to address the performance degradation caused by range ambiguity in space-time adaptive processing. In this paper, we use the sparse recovery method to solve the problem that EPC-MIMO has a large demand for independent and identically distributed (IID) samples. On the one hand, we use the Sparse Bayesian Learning (SBL) to achieve space-time spectral estimation under the small sample condition, and on the other hand, the use of prior knowledge, reduce the redundancy of the sparse recovery dictionary and improve the computational efficiency of the algorithm. The simulation results demonstrate the effectiveness of the proposed method.

关键词： Degradation Dictionaries Spaceborne radar Simulation Redundancy signal processing algorithms Estimation

来源：评论

学校读者我要写书评

暂无评论

A data-assisted adaptive detection algorithm for shortwave burst signals 5

A data-assisted adaptive detection algorithm for shortwave b...

引用

5th International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2022

作者： Yi Wei, Feng Wen Zhong, Qu Yan, Zhao Yu Mei, Zhou Pla Strategic Support Force Information Engineering University College of Information System Engineering Zhengzhou China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781665484749

ISBN: (纸本)9781665484749

For shortwave signals with unique code frame structure, a data-assisted adaptive burst detection algorithm is proposed in this paper. The algorithm weakens the high bottom-noise undulation of signal correlation values due to shortwave channel fading by using a locally normalized sliding differential correlation. Also based on this, an adaptive gate limit detection strategy based on sliding window comparison judgments is used to improve the burst detection accuracy. This paper focuses on the effects of signal-to-noise ratio and shortwave channel environment on the performance of this algorithm, and simulation experiments are conducted under different conditions. The simulation results show that the algorithm has good robustness and can still achieve good detection results in the case of low signal-to-noise ratio as well as short-wave poor channels. © 2022 IEEE.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

Data Association for Maneuvering Targets Through a Combined Siamese Network and Xgboost Model

SSRN

引用

SSRN 2023年

作者： Gao, Chang Yan, Junkun Chen, Bo Varshney, Pramod K. Jia, Tianyi Liu, Hongwei National Laboratory of Radar Signal Processing Xidian University Xian710071 China Department of Electrical Engineering and Computer Science Syracuse University NY13244 United States

Data association plays an important role in forming target tracks when false alarms exist. Its accuracy is key to reducing the computational burden of the combinatorial explosion problem inherent to target tracking in environments where false alarms are densely distributed. Traditional methods are usually developed according to some assumed motion models and suffer performance degradation when there is mismatch between assumed models and the actual motion, which may often be the case for maneuvering targets. To cope with this problem, we propose a data-driven method that learns the association criteria directly from data. By use of the domain knowledge and a convolutional Siamese network, features of different attributes present in the observations are extracted. Then the features are fused through the use of XGBoost. Simulation results show that the proposed method performs better than the traditional model-based methods in correlating observations of maneuvering targets and avoiding correlations of false alarms. By visualizing the decision process of the feature fusion model, it is found that the proposed method learns from the data to make comprehensive use of multiple features and does not simply set hard thresholds for the features. The computational complexity is also analyzed both theoretically and experimentally. © 2023, The Authors. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A 3D Geometry Reconstruction Method for Space Targets Utilizing Improved ISAR Image Sequence Energy Accumulation

A 3D Geometry Reconstruction Method for Space Targets Utiliz...

引用

2021 CIE International Conference on radar, radar 2021

作者： Zhou, Zuobang Du, Rongzhen Liu, Lei Zhou, Feng Key Laboratory of Electronic Information Countermeasure and Simulation Technology Ministry of Education Xidian University Xi'an China Xidian University National Laboratory of Radar Signal Processing Xi'an China

ISBN: (纸本)9781665498142

As for space targets with unknown motion, the accurate projection matrix cannot be obtained in advance, which makes the three-dimensional (3D) geometry reconstruction method based on inverse synthetic aperture radar (ISAR) image sequence energy accumulation (ISEA) inapplicable. To tackle this problem, a joint factorization and ISEA-based method is proposed. Firstly, the range-Doppler measurement matrix can be formed through the steadily tracking of a small number of feature points in the ISAR image sequence. Then the factorization method is utilized to estimate the projection matrix, which reflects the projection relationship between the 3D geometry and corresponding ISAR image sequence. Next, when projected to ISAR image sequence, feature points with larger ISEA values can be regarded as the true scattering points on the geometry of the target. Therefore, all the scattering points can be reconstructed by searching the feature points with maximum ISEA values. Experimental results based on simulated point model verify the effectiveness of the proposed method. © 2021 IEEE.

关键词： factorization method image sequence energy accumulation ISAR image sequence range-Doppler measurement matrix three-dimensional geometry reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Cross-Task Transfer SAR Target Recognition Method Based on AMFFNet and IACGAN

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Wan, Xunyang Du, Xiaolin Cui, Guolong Chen, Xiaolong Zheng, Jibin Yantai University School of Computer and Control Engineering Yantai264005 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Naval Aviation University Yantai264001 China Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China

Convolutional neural networks (CNN) have shown excellent capability in synthetic aperture radar (SAR) target recognition. However, obtaining sufficient training samples for improving network recognition is difficult due to the deficiency of labeled SAR image data. To tackle the problem, a cross-task transfer method for SAR target recognition is proposed in this paper, which is based on a designed attention multi-scale feature fusion network (AMFFNet) and an improved auxiliary classifier generative adversarial network (IACGAN). In this method, firstly, a data augmentation method based on you only cut twice (YOCT) is devised for expanding the training samples. Secondly, the partial weight parameters of AMFFNet are initialized by the pre-trained IACGAN discriminator. Finally, AMFFNet is fine-tuned using the training samples. Additionally, on the network structure of AMFFNet, multi-scale features are extracted by adopting a multi-scale depth separable convolution module, which allows the model to acquire more informative features. Attention mechanisms are employed in this network to enhance its ability to capture important features while reducing the effects of noise. A multi-level feature fusion structure is used to further raise the representational capability of the model. Experimental results on multiple open-source real SAR datasets show that the proposed method can achieve better recognition performance under different percentages of training data, and the effectiveness and superiority of the method are confirmed by its robustness to noise. © 1965-2011 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：