检索结果-内蒙古大学图书馆

IET International radar Conference (IRC 2023)

作者： Xi Cen Tong Gu Yachao Li Sizhe Zhao Dongning Fu Jiarui Yang The National Key Laboratory of Radar Signal Processing Xidian University Xi'an People's Republic of China Hangzhou Institute of Technology Xidian University Hangzhou People's Republic of China The 39th Research Institute of China Electronics Technology Group Corporation Xi'an People's Republic of China HWA-NCUT Radar RF Simulation Laboratory Beijing People's Republic of China

ISBN: (数字)9781837240982

In the face of the current complex and variable electromagnetic interference environment, the broadband characteristics of synthetic aperture radar (SAR) make it extremely susceptible to other electromagnetic interference in the operating frequency band, which seriously restricts the information acquisition capability of SAR. Existing interference suppression methods based on notch filtering often rely on the interference a priori to set a fixed notch threshold, which suffers from poor adaptive ability and poor generalisation. Aiming at the aforementioned problems, this paper proposes a time-frequency domain adaptive SAR interference suppression method based on clustering, which makes use of the potential difference between the interference signal and the target signal in the time-frequency domain to adaptively locate the interference position in the time-frequency spectrum by unsupervised clustering, and then carries out zero-notch filtering to achieve the interference suppression on the basis of this method. The results of interference suppression from simulated and measured interference data show that the proposed method is able to overcome the need for interference a priori and effectively suppress different types of interference, with strong adaptive capability, generalisation to a wide range of interferences, and has value for practical application.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Electromagnetic Parameter Estimation Method for Microwave Photonic signal Based on PSO

An Electromagnetic Parameter Estimation Method for Microwave...

引用

IEEE International Conference on radar

作者： Yiyuan Xie Yuexin Gao Mengdao Xing National Laboratory of Radar Signal Processing Xidian University Xi'an China School of Aerospace Science and Technology Xidian University Xi'an China

ISBN: (纸本)9781665468893

Microwave photonics radar generates cross-band signals, which provides a basis for precise electromagnetic characteristics description and accurate identification of targets. As a result, a corresponding electromagnetic model parameter extraction method is urgently required under the cross-band and wide-angle condition. This paper proposes a parameter estimation method based on an improved Particle Swarm Optimization (PSO). The representation dictionary without range-azimuth coupling of scattering behavior for the data processed by PFA is firstly formed based on the attributed scattering center (ASC) model. Based on the proposed scattering behavior dictionary, the improved PSO algorithm and the CLEAN algorithm are implemented to estimate the electromagnetic parameters of each scattering center. Further, the simulated annealing (SA) algorithm is introduced to improve the method's capacity to find the global optimum. Finally, the structure of each scattering center can be identified according to the parameter estimation results. The processing results of simulation data verify the effectiveness of the algorithm. Compared with traditional algorithms, the proposed algorithm is insensitive to the initialization value and does not require image segmentation, which reduces the complexity of computation.

关键词： Parameter estimation Computational modeling radar radar scattering radar imaging Microwave theory and techniques Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

A tor anonymity attack experiment platform driven by raspberry pi 11

A tor anonymity attack experiment platform driven by raspber...

引用

11th International Conference on Prognostics and System Health Management, PHM-Jinan 2020

作者： Wang, Qi Cao, Weiquan National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (纸本)9781728151816

Private Tor network is essential for analyzing security issues both for Tor project as well as for numerous researchers. However, current research work mainly focus on improving scalability and efficiency by simulating traffic discretely with single node and restoration level by deploying a complete private network with high cost. In this paper, we propose a novel methodology constructing real private tor network by editing and controlling Raspberry Pis, called Tor anonymity attack experiment platform. Compared with other platforms of the same type, the platform has the advantages of low cost, easy to scale, high quality of real-time data transmission, high degree of network protocol restoration as well as convenient configuration. In order to demonstrate the platform can be used as a private and complete Tor anonymous network experiment environment, we conduct a source tracing attack as a study case. Experimental results and theoretical analysis both show that the platform can support researchers to carry out numerous Tor network security research with high degree of restoration efficiently and cheaply. © 2020 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Alignment-Free RGB-T Salient Object Detection: A Large-scale Dataset and Progressive Correlation Network

arXiv

引用

arXiv 2024年

作者： Wang, Kunpeng Chen, Keke Li, Chenglong Tu, Zhengzheng Luo, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University China Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University China

Alignment-free RGB-Thermal (RGB-T) salient object detection (SOD) aims to achieve robust performance in complex scenes by directly leveraging the complementary information from unaligned visible-thermal image pairs, without requiring manual alignment. However, the labor-intensive process of collecting and annotating image pairs limits the scale of existing benchmarks, hindering the advancement of alignment-free RGB-T SOD. In this paper, we construct a large-scale and high-diversity unaligned RGB-T SOD dataset named UVT20K, comprising 20,000 image pairs, 407 scenes, and 1256 object categories. All samples are collected from real-world scenarios with various challenges, such as low illumination, image clutter, complex salient objects, and so on. To support the exploration for further research, each sample in UVT20K is annotated with a comprehensive set of ground truths, including saliency masks, scribbles, boundaries, and challenge attributes. In addition, we propose a Progressive Correlation Network (PCNet), which models inter- and intra-modal correlations on the basis of explicit alignment to achieve accurate predictions in unaligned image pairs. Extensive experiments conducted on unaligned and aligned datasets demonstrate the effectiveness of our method. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boundary-Guided Fusion of Multi-Level Features Network for Camouflaged Object Detection

Boundary-Guided Fusion of Multi-Level Features Network for C...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Songlin Li Zhe Li Boyuan Li Xiuhong Li Jiabao Sheng School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China Department of Electrical and Electronic Engineering Hong Kong Polytechnic University HongKong China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Camouflaged objects, exhibiting high similarity with their surroundings, pose a substantial challenge for both humans and machines to detect when concealed within the environment. Existing methods for camouflage object detection (COD) struggle in accurately segmenting the overall structure of camouflaged objects. To address this issue, we propose a novel boundary-guided fusion of multi-level features network (BGFM-Net) for COD. In contrast to existing boundary-guided methods, we pay more attention to addressing the significant imbalance in the pixel quantities between boundary and background features, allowing for a more comprehensive representation of boundary features. BGFM-Net primarily consists of a multi-scale aggregation module (MSAM), a boundary-guided feature module (BFM), and a cross-Level fusion module (CLFM). MSAM effectively integrates contextual semantics at different scales, achieving a powerful and efficient feature representation. BFM adeptly combines edge features while constraining interference from background features, guiding the learning of camouflaged object boundary representation. CLFM integrates multi-level features for predicting camouflaged objects while adaptively adjusting channel weights to emphasize important channels and diminish the impact of less relevant channels for the task. Extensive experiments on three benchmark camouflage datasets demonstrate that our BGFM-Net outperforms other state-of-the-art COD models.

关键词： Adaptation models Semantics Neural networks Object detection Interference Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research On Sliding Spotlight And TOPS SAR Variable PRF Imaging technology

Research On Sliding Spotlight And TOPS SAR Variable PRF Imag...

引用

IEEE International Conference on radar

作者： Songtao Gong Zhi Wang Guang-cai Sun Yang Jun Mengdao Xing National Laboratory of Radar Signal Processing Xidian University Xi'an China College of Geomatics Xi'an University of Science and Technology Xi'an China

ISBN: (纸本)9781665468893

Because the traditional single-based spaceborne synthetic aperture radar (SAR) cannot receive signals while transmitting signals, there is a defect that high azimuth resolution and wide swath imaging cannot be achieved at the same time. In response to this problem, researchers have proposed the use of variable pulse repetition frequency (PRF) technology to achieve high-resolution wide swath imaging. However, the echo data of the variable PRF SAR will have the problem of sampling at different intervals in the azimuth direction. Using traditional frequency domain algorithms to process the data will cause serious deterioration of the imaging quality, or even imaging; the time domain algorithm can directly focus on the data of the variable PRF, but the amount of calculation is huge. In this paper, we deduced the change rule of PRF and proposed a variable PRF imaging algorithm based on time-frequency scale scaling. A new interpolation method is used to perform uniform sampling of the unambiguous signal in the time domain. Then use the Omega-K algorithm to achieve range cell migration correction (RCMC), and finally focuses the signal in the azimuth frequency domain. The proposed SAR working system with variable PRF is verified by simulation experiments.

关键词： Time-frequency analysis Interpolation Image resolution Azimuth Spaceborne radar Imaging radar imaging

来源：评论

学校读者我要写书评

暂无评论

An Underdetermined Environmental Sound Source Separation Algorithm Based on Improved Complete Ensemble EMD with Adaptive Noise and ICA 21

An Underdetermined Environmental Sound Source Separation Alg...

引用

21st IEEE International Conference on Communication technology, ICCT 2021

作者： Wang, Mei Bai, Lu Luo, Liyan Jin, Ye He, Ruibin Guo, Shuting Guilin University of Technology College of Information Science and Engineering Guilin China Guilin University of Electronic Technology Provincial Ministry of Education Key Laboratory of Cognitive Radio and Signal Processing Guilin China

ISBN: (纸本)9781665432061

In order to solve the problem that Independent component analysis (ICA) cannot achieve complete signal separation under underdetermined conditions, we propose an environmental sound source separation algorithm under underdetermined conditions based Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Independent Component Analysis (ICA). This algorithm can effectively break through the limitations of ICA under underdetermined conditions, and solve the problems of insufficient number of observed signals and mode mixing existing in Empirical Mode Decomposition (EMD). Firstly, the algorithm uses ICEEMDAN to estimate the local mean of the signal to decompose the existing observed signals. Then, a filtering method based on kurtosis and correlation is used to filter the intrinsic mode functions (IMFs) generated in the decomposition process, and the appropriate IMFs are selected to construct the virtual channel. Finally, FastlCA is used to separate the reconstructed observation signals and obtain the estimated source signals. The experimental results show that compared with EMD-ICA and EEMD-ICA, the proposed algorithm has better separation ability for the observed signals constructed from both analog signals and dataset signals in terms of correlation coefficient, Mean Square Error (MSE) and signal Distortion Ratio (SDR). The MSE increased by 61.3%, 34.2% and 35.2%, 69.7%, respectively. Taking glass breaking sound as an example, the correlation coefficient is increased by 10.8% and 4.3%, and the SDR is increased by 35.9% and 16.7%, respectively. © 2021 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Fast Human Body Scan for Security Inspection Based on Multi-Mode Vortex Electromagnetic Wave

Fast Human Body Scan for Security Inspection Based on Multi-...

引用

IEEE International Conference on radar

作者： Xiankang Zhang Kun Lv Hui Ma Shuai Shao Jiaqi Wei HongWei Liu The National Laboratory of Radar Signal Processing Xidian University Xi'an China School of Information Science and Technology Northwest University Xi'an China

ISBN: (纸本)9781665468893

The current security inspection technology is mostly composed of imaging and recognition steps, in which high-pixel imaging corresponds to high accuracy but high computational burden. In this paper, we propose a fast end-to-end method to connect the original data to security check results directly, where the two-dimensional fast beamforming is achieved by a one-dimensional mode scanning of the vortex electromagnetic wave. Vortex electromagnetic wave achieves a helical wavefront through phase modulation related to azimuth Angle, which can cover two-dimensional space through one-dimensional scanning, and different modal vortex echoes contain information of different parts of the human body, but modal dimension signals do not have a clear corresponding relationship with the scene like the image. So the rapid detection of human body is realized by the combination of multi-modal vortex wave and feed-forward neural network. Through the training and simulation of the network, the feasibility of the proposed system and method is proved, and the high recognition rate can be obtained with very little computation.

关键词： Training Target recognition Shape Phase modulation Electromagnetic scattering Imaging radar

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Hierarchical Knowledge Graph Embeddings for Link Prediction in Low Dimensions

arXiv

引用

arXiv 2022年

作者： Zheng, Wenjie Wang, Wenxue Zhao, Shu Qian, Fulan Nanjing University of Science and Technology China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China

Knowledge graph embeddings (KGE) have been validated as powerful methods for inferring missing links in knowledge graphs (KGs) that they typically map entities into Euclidean space and treat relations as transformations of entities. Recently, some Euclidean KGE methods have been enhanced to model semantic hierarchies commonly found in KGs, improving the performance of link prediction. To embed hierarchical data, hyperbolic space has emerged as a promising alternative to traditional Euclidean space, offering high fidelity and lower memory consumption. Unlike Euclidean, hyperbolic space provides countless curvatures to choose from. However, it is difficult for existing hyperbolic KGE methods to obtain the optimal curvature settings manually, thereby limiting their ability to effectively model semantic hierarchies. To address this limitation, we propose a novel KGE model called Hyperbolic Hierarchical KGE (HypHKGE). This model introduces attention-based learnable curvatures for hyperbolic space, which helps preserve rich semantic hierarchies. Furthermore, to utilize the preserved hierarchies for inferring missing links, we define hyperbolic hierarchical transformations based on the theory of hyperbolic geometry, including both inter-level and intra-level modeling. Experiments demonstrate the effectiveness of the proposed HypHKGE model on the three benchmark datasets (WN18RR, FB15K-237, and YAGO3-10). The source code will be publicly released at https://***/wjzheng96/HypHKGE. Copyright © 2022, The Authors. All rights reserved.

关键词： Knowledge graph

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：