检索结果-内蒙古大学图书馆

Spatio-Temporal Dynamic Graph Attention Network-Based Detector for Sea-Surface Small Targets

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2024年第6期60卷 8010-8021页

作者： xu, shuwen He, Qi Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

This article presents a spatio-temporal dynamic graph attention network (STGAT)-based detector for the detection of sea-surface small targets. It utilizes graphical modeling of radar returns to capture the inherent relationships. With two segmentation operations applied to the received sequence, it is first modeled as a static graph and then arranged chronologically to form a dynamic graph. The topology of a structured graph reflects inherent coherence, while the vertex attributes, which comprise features, facilitate the process of multifeature fusion. The relative maximum degree (RMD) feature are proposed as one of the vertex attributes and shows superiority. Subsequently, the STGAT, a dynamic graph neural network with double convolutions, integrates graph and standard convolution to process dynamic graphs. The network will be trained on simulated datasets and then tested on measured datasets. The outputs of the proposed detector are 2-D vectors belonging to vertices. They are used as classification probabilities for the purpose of distinguishing the target from sea clutter. The decision threshold is obtained through a Monte Carlo experiment at a given false alarm probability. A comparison experiment between the proposed detector and existing detectors is carried out on 80 datasets of IPIX radar database, which indicates the proposed method works effectively in 70% situations.

关键词： Clutter Radar Feature extraction Convolution Aerodynamics Detectors Vectors Double convolutions dynamic graph modeling dynamic graph neural networks (DGNNs) graph attention network (GATs) sea clutter target detection

来源：评论

学校读者我要写书评

暂无评论

Persymmetric adaptive polarimetric detection of subspace range-spread targets in compound Gaussian sea clutter

引用

Journal of Systems Engineering and Electronics 2024年第1期35卷 31-42页

作者： xu shuwen HAO Yifan WANG Zhuo xuE Jian National Key Laboratory of Radar Signal Processing Xidian UniversityXi’an 710071China Xi’an Electronic Engineering Research Institute Xi’an 710100China Beijing Institute of Radio Measurement Beijing 100039China School of Communications and Information Engineering Xi’an University of Posts and TelecommunicationsXi’an 710121China

This paper focuses on the adaptive detection of range and Doppler dual-spread targets in non-homogeneous and nonGaussian sea *** sea clutter from two polarimetric channels is modeled as a compound-Gaussian model with different parameters,and the target is modeled as a subspace rangespread target *** persymmetric structure is used to model the clutter covariance matrix,in order to reduce the reliance on secondary data of the designed *** adaptive polarimetric persymmetric detectors are designed based on the generalized likelihood ratio test(GLRT),Rao test,and Wald *** the proposed detectors have constant falsealarm rate property with respect to the clutter texture,the speckle covariance *** results on simulated and measured data show that three adaptive detectors outperform the competitors in different clutter environments,and the proposed GLRT detector has the best detection performance under different parameters.

关键词： sea clutter adaptive polarimetric detection compound Gaussian model subspace range-spread target persymmetric structure

来源：评论

学校读者我要写书评

暂无评论

Sea Surface Floating Small Target Detection Based on a Priori Feature Distribution and Multiscan Iteration

引用

IEEE JOURNAL OF OCEANIC ENGINEERING 2025年第1期50卷 94-119页

作者： xu, shuwen Zhang, Tian Ru, Hongtao Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China McMaster Univ Hamilton ON L8S 4L8 Canada

To address the issue that the detection performance of conventional sea target detectors deteriorates seriously in short accumulated pulses, this article designs a feature detection method based on a priori feature distribution and multiscan iteration, which enhances the feature extraction ability of existing feature-based detection methods. The initial step involves the utilization of kernel density estimation for the purpose of fitting the a priori feature distribution model. Subsequently, the original feature vectors of the current scan are iterated based on the a priori feature distribution model to obtain improved feature vectors. After the feature iteration of the current scan is completed, the original feature vectors of the current scan are incorporated into the historical features to generate a new distribution model. The improved feature vectors after iteration are employed for training the decision region and detecting targets by the convex hull algorithm. The proposed method is designed to enhance the stability and reliability of detection features, thereby facilitating a greater degree of separation between the extracted features of sea clutter and target returns within the feature space. The measured IPIX data sets and Naval Aviation University X-Band data sets demonstrate that the proposed method can effectively improve the detection performance of existing multifeature-based detection methods in scenarios involving short accumulated pulses.

关键词： Feature extraction Detectors Clutter Doppler effect Radar Vectors Radar detection Object detection Sea surface Radar clutter A priori feature distribution feature-based detection kernel density estimation (KDE) multiscan iteration sea clutter

来源：评论

学校读者我要写书评

暂无评论

Adaptive detection of radar range-Doppler dual-spread targets in lognormal-texture clutter

引用

DIGITAL SIGNAL PROCESSING 2025年 157卷

作者： xue, Jian Fan, Zhen xu, shuwen Pan, Meiyan Xian Univ Posts & Telecommun Sch Commun & Informat Engn Xian 710121 Peoples R China Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China Xidian Univ Collaborat Innovat Ctr Informat Sensing & Understa Xian 710071 Peoples R China Xian Elect Engn Res Inst Xian Peoples R China

This paper investigates the problem of adaptive detection of radar targets in non-Gaussian clutter, where the target to be detected is considered to behave the dual-spread in the Doppler frequency dimension and the range dimension. The clutter is assumed to follow the compound Gaussian model with lognormal texture and unknown covariance matrix structure. The multi-rank linear subspace model and the range-spread model are employed to depict the Doppler and range spread characteristics of target echoes. Then, the range-Doppler dual-spread adaptive radar target detector with lognormal-texture is proposed using the two-step generalized likelihood ratio criteria, which replaces the true values of the unknown parameters with their maximum likelihood and maximum a posteriori estimates. Experimental results on simulated and measured data demonstrate that the proposed detector shows superior performance in different clutter and target parameters compared to the competitors.

关键词： Adaptive detection Lognormal texture Subspace model Doppler spread Range spread

来源：评论

学校读者我要写书评

暂无评论

ACFNet: An adaptive cross-fusion network for infrared and visible image fusion

引用

PATTERN RECOGNITION 2025年 159卷

作者： Chen, Xiaoxuan xu, shuwen Hu, Shaohai Ma, Xiaole Beijing Jiaotong Univ Sch Comp Sci & Technol Visual Intellgence Int Cooperat Joint Lab MOE X Beijing 100044 Peoples R China Res Inst TV & Electroacoust Beijing 100044 Peoples R China

Considering the prospects for image fusion, it is necessary to guide the fusion to adapt to downstream vision tasks. In this paper, we propose an Adaptive Cross-Fusion Network (ACFNet) that utilizes an adaptive approach to fuse infrared and visible images, addressing cross-modal differences to enhance object detection performance. In ACFNet, a hierarchical cross-fusion module is designed to enrich the features at each level of the reconstructed images. In addition, a special adaptive gating selection module is proposed to realize feature fusion in an adaptive manner so as to obtain fused images without the interference of manual design. Extensive qualitative and quantitative experiments have demonstrated that ACFNet is superior to current state-of-the-art fusion methods and achieves excellent results in preserving target information and texture details. The fusion framework, when combined with the object detection framework, has the potential to significantly improve the precision of object detection in low-light conditions.

关键词： Image fusion Object detection Auto-encoder Global features Adaptive fusion method

来源：评论

学校读者我要写书评

暂无评论

DGFD: A dual-graph convolutional network for image fusion and low-light object detection

引用

INFORMATION FUSION 2025年 119卷

作者： Chen, Xiaoxuan xu, shuwen Hu, Shaohai Ma, Xiaole Beijing Jiaotong Univ Sch Comp Sci & Technol Visual Intellgence Int Cooperat Joint Lab 10 MOE Beijing 100044 Peoples R China China Elect Technol Grp Corp Res Inst 3 Beijing 100015 Peoples R China

Traditional convolutional operations primarily concentrate on local feature extraction, which can result in the loss of global features. However, current fusion methods for extracting global features exhibit high time complexity and have difficulties in capturing long-range dependencies. In this paper, a dual-graph convolutional neural network is constructed to perform cross-modal graph inference based on the modal structures of infrared and visible images. Specifically, to aggregate the global and local features of different modal images, a contextual graph convolutional module is proposed that allows the network structure adapting to the features of different modal images and facilitates the extraction of features at various levels. A content graph convolutional module is also proposed to construct correlation relationships between infrared and visible images, which achieves feature fusion without manually designing interference. Furthermore, the fused features are fed into a unified framework to integrate the fusion and detection tasks. Extensive qualitative and quantitative experiments have demonstrated that the proposed unified network significantly reduces the time complexity and improves detection performance under low-light conditions.

关键词： Image fusion Object detection Graph neural network Global features

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Maximum Connected-Component Learning Algorithm for Small Target Detection in Maritime Radars

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第1期61卷 250-265页

作者： Bai, Xiaohui xu, shuwen Guo, Zixun Shui, Penglang Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China

Anomaly detection needs to learn one-class classifiers from normal instances in observation or feature spaces. In the Neyman-Pearson criterion, the design of one-class classifiers boils down to finding the minimal-volume decision region subject to the error probability of normal instances no larger than a desired false alarm rate. The theoretical solution to this design problem is the probability density function (pdf) level set of normal instances. In low-dimensional feature spaces, by combining training samples with the convexity regularity on decision regions, the convexhull learning algorithm is a technique for designing one-class classifiers. In order to overcome its dimension limitation and the mismatch of convexity to the level sets of a multimodal pdf, this article considers the approach to replace the convexity by the connectivity to regularize decision regions. A fast graph-based maximum connected-component learning algorithm is proposed to design one-class classifiers in high-dimensional feature spaces, which exploits the fast maximum connected-component search algorithm in a large-scale undirected graph. Moreover, for the application of sea-surface small target detection, the proposed algorithm combines ten-dimensional features to design feature-based detectors. Experimental results on the recognized radar database indicate the effectiveness of the proposed algorithm.

关键词： Training Detectors Level set Feature extraction Classification algorithms Signal processing algorithms Radar Anomaly detection convexhull learning algorithm feature-based detection graph-based maximum connected-component (GMCC) learning algorithm sea-surface small target detection

来源：评论

学校读者我要写书评

暂无评论

Sea-Surface Small Target Detection Using Spiking Neural Network With Controllable False Alarm

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Jiao, Yang Wang, Zeyu Wang, Dewu xu, shuwen Beijing Univ Posts & Telecommun Sch Informat & Commun Engn State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Inst Technol Beijing 100081 Peoples R China Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Shaanxi Peoples R China

Convolutional neural network (CNN)-based detectors for small targets on the sea surface have proven effective, yet their increasingly complex structures and high energy demands pose challenges to deployment on resource-limited devices. To address this issue, this letter proposes a residual spiking network (RSN), which is developed within the advanced framework of spiking neural networks (SNNs). By using spiking neurons (SNs) as core computational units, the RSN can efficiently transmit features extracted from time-frequency graphs (TFGs) through discrete spikes in the backbone network. Meanwhile, the output is derived from the membrane voltage of the SNs, enabling reliable control over false alarms. Experimental results from the IPIX dataset validate the RSN's stability in controlling the probability of false alarms (PFAs). With an observation time of 1.024 s and a PFA of 0.001, the average probability of detection (PD) is 0.8266. The RSN demonstrates a PD comparable to that of ResNet18 while consuming only 70% of its energy, highlighting its potential for practical applications in resource-constrained environments.

关键词： Feature extraction Clutter Training Radar Time-frequency analysis Sea surface Object detection Neurons Vectors Spiking neural networks Controllable false alarm deep learning sea-surface small target spiking neural network (SNN) time-frequency graph (TFG)

来源：评论

学校读者我要写书评

暂无评论

Physical Degradation of Anode Catalyst Layer in Proton Exchange Membrane Water Electrolysis

引用

ADVANCED MATERIALS INTERFACES 2025年第4期12卷

作者： xu, shuwen Liu, Han Zheng, Nanfeng Tao, Hua Bing Xiamen Univ State Key Lab Phys Chem Solid Surfaces Collaborat Innovat Ctr Chem Energy Mat New Cornerstone Sci Lab Xiamen 361005 Peoples R China Xiamen Univ Coll Chem & Chem Engn Xiamen 361005 Peoples R China Innovat Lab Sci & Technol Energy Mat Fujian Prov I Xiamen 361005 Peoples R China

The proton exchange membrane water electrolysis (PEMWE) is a promising technology for green hydrogen production. However, the wide-spread application of PEMWE is hindered by the insufficient lifetime due to the degradation of anode material and structure, thus it is crucial first to understand the degradation mechanisms of PEMWE in actual applications. Generally, the degradation in anode side can be classified as chemical degradation and physical degradation. The considerable research focus from academia to enhance performance and durability is mainly by chemical methods. However, based on the experience from industry, many of the performance and lifetime limitations originated from physical factors. Herein, the impact of the physical characteristic of anode catalyst layer (ACL) on performance and durability of PEMWE is investigated, including cracking and deformation of ACL, swelling and creeping of ionomers, and detachment of catalyst particles. Finally, an outlook of future research focus is provided, based on the demand of developing efficient and durable industrial PEMWE devices. This article reviews the degradation mechanisms of PEMWE devices, focusing on the physical degradation of the anode catalyst layer. Specifically, it emphasizes issues including crack formation, ionomer swelling and creeping, and catalyst particle detachment. Highlighting the gap between academic research and industrial applications, it offers new insights for the development of efficient and durable PEMWE systems. image

关键词： anode catalyst layer durability physical degradation proton exchange membrane water electrolysis triple-phase boundaries

来源：评论

学校读者我要写书评

暂无评论

Classification of Small Targets on Sea Surface Based on Improved Residual Fusion Network and Complex Time-Frequency Spectra

引用

REMOTE SENSING 2024年第18期16卷 3387-3387页

作者： xu, shuwen Niu, Xiaoqing Ru, Hongtao Chen, Xiaolong Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China Naval Aviat Univ Yantai 264001 Peoples R China

To address the problem that conventional neural networks trained on radar echo data cannot handle the phase of the echoes, resulting in insufficient information utilization and limited performance in detection and classification, we extend neural networks from the real-valued neural networks to the complex-valued neural networks, presenting a novel algorithm for classifying small sea surface targets. The proposed algorithm leverages an improved residual fusion network and complex time-frequency spectra. Specifically, we augment the Deep Residual Network-50 (ResNet50) with a spatial pyramid pooling (SPP) module to fuse feature maps from different receptive fields. Additionally, we enhance the feature extraction and fusion capabilities by replacing the conventional residual block layer with a multi-branch residual fusion (MBRF) module. Furthermore, we construct a complex time-frequency spectrum dataset based on radar echo data from four different types of sea surface targets. We employ a complex-valued improved residual fusion network for learning and training, ultimately yielding the result of small target classification. By incorporating both the real and imaginary parts of the echoes, the proposed complex-valued improved residual fusion network has the potential to extract more comprehensive features and enhance classification performance. Experimental results demonstrate that the proposed method achieves superior classification performance across various evaluation metrics.

关键词： target classification residual network complex neural networks time-frequency spectra

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：