检索结果-内蒙古大学图书馆

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Dou, Fabing Wang, Linhai Zhou, Shenghua Zhang, Mengchen Chen, Yidi Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China Academy of Space Information Systems Xi'an710199 China China Academy of Launch Vehicle Technology Beijing100076 China

ISBN: (纸本)9798331515669

Passive radars that rely on angle-only measurements cannot obtain the distance between radars and targets. To obtain position estimates of targets, passive radars can be connected to a central processor through communication links. Therefore, fusion algorithms are required to combine observations from distributed passive radars. For the scenario where all radars and targets are moving, most existed fusion algorithms use filtering methods to estimate the velocity and position of moving targets. In fact, most filtering algorithms have some limitations which will limit the algorithm's effectiveness to a large extent. In this paper, two fusion algorithms are proposed for the central processor. The first algorithm, known as the gross least squares (GLS), employs all observations from passive radars to implement moving target estimation, and thus needs significant computation at the central processor. The second algorithm, termed as the recursive least squares (RLS), iteratively optimizes the velocity and position of moving target. Exploiting the continuity of target motion, current target position and velocity estimates are used as initial values in the next moment. With good initial values, the number of iterations decreases and thus the computational cost is reduced at the central processor. Numerical results show that both algorithms benefit from more observations. The GLS algorithm provides more accurate position and velocity estimates of the target but requires substantial computation cost. The RLS algorithm may suffer a slight performance loss but offers a lower computation cost. The results demonstrate the trade-off between accuracy and computational cost, providing useful insights for practical applications. © 2024 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A SAR Target Recognition Strategy Guided by Electromagnetic Scattering Feature 2

A SAR Target Recognition Strategy Guided by Electromagnetic ...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Yin, Yifei Chen, Liang Liu, Lujiao Meng, Yufan Chen, Fan Shi, Hao National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Chinese Academy of Sciences Aerospace Information Research Institute Beijing China

ISBN: (纸本)9798331515669

SAR target Automatic Target Recognition (ATR) is indispensable in SAR image interpretation. Recently, deep learning technology has been widely used in SAR target recognition tasks. Most networks achieve incremental improvements in target recognition by modifying their structures to extract visual features of targets. However, due to the unique imaging mechanism, relying solely on visual features often leads to the loss of target information. In contrast, the ASC model, which captures the electromagnetic scattering characteristics of the target, plays a crucial role in target recognition tasks. Unfortunately, traditional parameter estimation methods for extracting the ASC model are computationally expensive and time-consuming, making them impractical for real-world applications. To address these issues, we propose a novel target recognition method based on electromagnetic scattering features in this paper. First, a lightweight network-based feature extraction module is designed. Then, the target ASC image is used as the ground truth for guidance, with image intensity and target structure serving as the loss functions during training. Finally, an ASC model-guided feature fusion network is designed, utilizing the fused features for target recognition. On the MSTAR dataset, a visual assessment experiment demonstrated that the proposed feature extraction module effectively extracts electromagnetic scattering features under various operating conditions. Subsequently, in downstream classification tasks, the inclusion of the proposed module resulted in improved accuracy compared to other networks. Additionally, a visualization analysis of the classification network showed that, under the guidance of electromagnetic scattering features, the network achieved good interpretability. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fast Moving Target Focusing with FDMA radar 2

Fast Moving Target Focusing with FDMA Radar

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Wang, Yanxing Yan, Shi Lan, Lan Zhu, Shengqi Cui, Lei Chen, Guozhong Li, Ximin Guo, Yixuan Xidian University National Key Laboratory of Radar Signal Processing Xian710071 China Beijing Institute of Remote Sensing Device Beijing100854 China Shanghai Institute of Satellite Engineering Shanghai200090 China

ISBN: (纸本)9798331515669

This paper deal with the challenge of focusing on fast-moving targets in a frequency division multiple access (FD-MA) radar system. At the modeling stage, the linear frequency modulation (LFM) waveform is transmitted by introducing a frequency increment (at least equal to the bandwidth) across the transmit array elements. The received signals are subsequently processed by a filter bank to separate the transmitted waveforms, which in turn provides additional degrees of freedom in the range domain. Particularly, a compensation procedure is designed to eliminate the incoherence between echos between different transmit element due to frequency diversity. To this end, as the outputs of different matched filters become coherent in the spatial domain, the keystone transform (KT) operation is employed to correct the range walk caused by the fast movement of the target, making it possible to focus the target in the space-time-range domain. Furthermore, the angle of the target is estimated and further utilized for beamforming, enhancing the range resolution. Numerical results are provided to verify the effectiveness of the proposed method in focusing the fast moving target with a FDMA radar. © 2024 IEEE.

关键词： Matched filters

来源：评论

学校读者我要写书评

暂无评论

APPLICATION OF COMPLEX DEEP NEURAL NETWORKS IN COMPLEX DATA processing AND COMPARATIVE ANALYSIS OF ACTIVATION FUNCTIONS

APPLICATION OF COMPLEX DEEP NEURAL NETWORKS IN COMPLEX DATA ...

引用

IET International radar Conference 2023, IRC 2023

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

ISBN: (纸本)9781839539954

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 R ReLU based on ReLu 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 R ReLU is more suitable for processing radar data in CDNNs. © The Institution of Engineering & Technology 2023.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Small-sample Trajectory Classification Algorithm via Bayesian Program Learning

A Small-sample Trajectory Classification Algorithm via Bayes...

引用

International Conference on signal processing Proceedings (ICSP)

作者： Yanshan Li Ruoqiang Yao Institute of Intelligent Information Processing Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Institute of Intelligent Information Processing Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Trajectory classification algorithms are widely used in fields such as behavior recognition, anomaly detection and monitoring, and video content analysis. To overcome the issues of traditional trajectory classification algorithms that require large supporting data and continuous model updates to ensure effectiveness, we take inspiration from the concept learning approach proposed by Brenden et al. We simulate how humans learn rich concepts from a single hand-drawn sample and propose a Bayesian program learning-based trajectory classification algorithm. This algorithm first builds concepts from a set of hand-drawn trajectories and then classifies trajectory data based on these constructed concepts. Experimental results show that our algorithm outperforms traditional single-sample learning algorithms in trajectory classification tasks and also shows superior performance over traditional single-sample learning algorithms when the dataset includes noisy data.

关键词： Content management Noise signal processing algorithms Programming Data models Trajectory Classification algorithms Bayes methods Noise measurement Monitoring

来源：评论

学校读者我要写书评

暂无评论

Video Group Activity Recognition Based On Multidimensional Spatio-Temporal Relationships

Video Group Activity Recognition Based On Multidimensional S...

引用

International Conference on signal processing Proceedings (ICSP)

作者： Yanshan Li Hailin Zong Suixuan He Miaomiao Wei Institute of Intelligent Information Processing Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Spatio-temporal relationships play an important role in group activity recognition. The spatio-temporal relationships are complex and varied, containing relationships between individuals, between individuals and subgroups, and between subgroups. However, there is no unified method for measuring these multidimensional spatio-temporal relationships. Therefore, this paper proposes a set of metric methods for multidimensional spatio-temporal relationships based on geometric algebra, including the metric method based on positional features and the metric method based on appearance features. And this paper proposed a deep network for video group activity recognition based on multidimensional spatio-temporal relationships. The experimental results show that the proposed algorithm can effectively improve the accuracy of group activity recognition.

关键词： Measurement Accuracy Algebra signal processing algorithms Activity recognition signal processing Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

Multi-frame Temporal Modeling for Multi-object Tracking in Satellite Video 2

Multi-frame Temporal Modeling for Multi-object Tracking in S...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Chai, Bingqian Qiao, Tingting Xie, Baorong Wang, Jue Liu, Wenchao Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China Shanghai Aerospace Electronic Technology Institute Shanghai China

ISBN: (纸本)9798331515669

With the advancement of remote sensing technology, video satellites have played an increasingly important role in both military and civilian domains, and they are widely used in areas such as military guidance, intelligent transportation, and disaster response. Multi-object tracking (MOT) in satellite video is a crucial research topic in these fields and has made certain progress. However, due to the difficulty of tracking objects in complex scene and low resolution, current MOT methods face issues of low accuracy in satellite video. In this work, we propose a joint-detection-and-tracking method called multi-frame temporal MOT (MFT-MOT). Firstly, a heatmap guided multi-frame temporal modeling method is introduced to extract features with temporal semantic information while suppressing background noise. Then, we utilize a weights-shared encoder-decoder network to facilitate interaction of temporal and spatial information and capture inter-frame object motion tracks at low resolution. Experiments on SAT-MTB dataset shows the effectiveness of our method. © 2024 IEEE.

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

A Privacy Preservation Method for Attributed Social Network Based on Negative Representation of information

引用

Computer Modeling in Engineering & Sciences 2024年第7期140卷 1045-1075页

作者： Hao Jiang Yuerong Liao Dongdong Zhao Wenjian Luo Xingyi Zhang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei230601China Chongqing Research Institute School of Computer Science and Artificial IntelligenceWuhan University of TechnologyWuhan430070China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and TechnologyHarbin Institute of TechnologyShenzhen518055China

Due to the presence of a large amount of personal sensitive information in social networks,privacy preservation issues in social networks have attracted the attention of many *** by the self-nonself discrimination paradigmin the biological immune system,the negative representation of information indicates features such as simplicity and efficiency,which is very suitable for preserving social network ***,we suggest a method to preserve the topology privacy and node attribute privacy of attribute social networks,called ***,a negative survey-based method is developed to disturb the relationship between nodes in the social network so that the topology structure can be kept ***,a negative database-based method is proposed to hide node attributes,so that the privacy of node attributes can be preserved while supporting the similarity estimation between different node attributes,which is crucial to the analysis of social *** evaluate the performance of the AttNetNRI,empirical studies have been conducted on various attribute social networks and compared with several state-of-the-art methods tailored to preserve the privacy of social *** experimental results show the superiority of the developed method in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topology disturbing and attribute hiding *** experimental results show the superiority of the developed methods in preserving the privacy of attribute social networks and demonstrate the effectiveness of the topological interference and attribute-hiding components.

关键词： Attributed social network topology privacy node attribute privacy negative representation of information negative survey negative database

来源：评论

学校读者我要写书评

暂无评论

A RIS-Aided MIMO Secure Communication Scheme Based on Subarray Partition 9

A RIS-Aided MIMO Secure Communication Scheme Based on Subarr...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Wang, Suzhen Zhi, Hui Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei China Anhui University School of Electronic and Information Engineering Hefei China

ISBN: (纸本)9798350317251

Subarray partition of reconfigurable intelligent surface (RIS) can significantly reduce the computational complexity of solving optimal reflection coefficients. However, there is no research about the RIS subarray partition of RIS-aided multiple-input multiple-output (MIMO) communication for the eavesdropper scenario. In this paper, we intend to solve the optimization subarray partition problem for the eavesdropper scenario, design a RIS-aided MIMO secure communication scheme based on subarray partition (RSC-SP). We consider minimizing the number of subarrays while satisfying secrecy rate requirements. First, this problem is described as a nonconvex combinatorial optimization problem, then we solve it by combining alternating optimization and bisection. In this scheme, we derive the closed expressions of the optimal transmit covariance matrix and the optimal reflection coefficients of RIS. The alternating optimization algorithm is used to jointly optimize the transmit covariance matrix and the reflection coefficients of RIS, the bisection method is used to calculate the minimum number of subarrays. Simulation results show that compared with the traditional scheme without subarray partition, RSC-SP can significantly reduce the computational complexity while meeting secrecy rate requirements. © 2023 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

A method for enhancing infrared small target images under complex sky backgrounds 2

A method for enhancing infrared small target images under co...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Xu, Yuhan Tang, Linbo Sun, Haotian Beijing Institute of Technology Beijing Key Laboratory of Embedded Real-Time Information Processing Radar Research Lab School of Information and Electronics Beijing China Advanced Technology Research Institute Beijing Institute of Technology Jinan250300 China

ISBN: (纸本)9798331515669

Infrared target detection is currently widely used in both military and civilian fields. Due to the lower resolution of infrared images compared to visible light images and the lack of texture information in small targets, the quality of infrared small target images is often poor and not suitable for direct detection. Therefore, enhancing low-quality infrared small target images is a necessary step before object detection can be performed. This article presents a method for enhancing infrared images of small targets. The process begins with applying guided filtering to the original image. The resulting detail layer is then used as a guided image for a second guided filtering of the base layer, producing a second detail layer. Additionally, a novel approach to local contrast enhancement is introduced, which applies contrast enhancement specifically to this secondary detail layer. Experimental results has been demonstrated that the enhancement method proposed in this paper significantly improves the visibility of the target area while reducing background interference, without losing information about small targets. Additionally, this method outperforms other common techniques in terms of enhancement effect, as shown in comparative experiments. © 2024 IEEE.

关键词： Wiener filtering

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：