检索结果-内蒙古大学图书馆

Big data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), International Conference on

作者： Jingyi Qu Xinjie Bi Shanliang Liu Tianjin Key Laboratory of Advanced Signal Processing Civil Aviation University of China Tianjin China

ISBN: (数字)9781665415408

ISBN: (纸本)9781665447065

LSS (Low, small and Slow) targets have characteristics of low cost, simple operation, easy to carry, low take-off requirements, strong sudden takeoff, and difficult to find and handle. With the development of aviation industry, the cases of LSS flying illegally and used in terrorist attacks are increasing day by day. It will not only cause great negative effects on economy, but also have serious influence on the national security and the normal development of the national economy. In order to eliminate the threat of illegal flight of UAV in the airport clearance area to the safe operation of airport, a LSS recognition algorithm based on the deep learning was proposed in the paper. Compared with other detection types, the video detection was used in the algorithm, which has many advantages such as strong visualization, low cost and fast detection speed. By using the Yolov3 object detection model, one of the most popular deep learning methods, the problem of low accuracy of small objects such as LSS can be solved. The experiments show that the Yolov3 model can improve the accuracy for small objects and can effectively detect the LSS. Thus, the necessary precondition for the subsequent LSS countermeasures can be provided, and the safe operation of the airport can be ensured.

关键词： Deep learning Atmospheric modeling Training data Object detection Airports Internet of Things National security

来源：评论

学校读者我要写书评

暂无评论

Hough transform-based large micro-motion target detection and estimation in synthetic aperture radar

引用

IET RADAR SONAR AND NAVIGATION 2019年第4期13卷 558-565页

作者： Zhou, Yang Bi, Daping Shen, Aiguo Wang, Xiaoping Natl Univ Def Technol Coll Elect Engn Lab 202 Hefei Anhui Peoples R China

Target vibration or rotation produces special phase modulation of synthetic aperture radar azimuth echo signals, referred to as the micro-Doppler effect, which can provide favourable information for target detection and recognition. However, the pulse repetition frequency will be lower than the azimuth bandwidth of azimuth echo signal when the micro-motion amplitude is too large, resulting in spectral aliasing, which invalidates the conventional detection and estimation algorithm. This study proposes a new target detection and estimation algorithm for large micro-motion targets. First, the authors perform time-frequency (TF) transform on the azimuth echo signals of micro-motion targets. Then extract the TF curves in the TF distribution. After modifying the analytical expression of large micro-motion target TF curves, the target detection and parameter estimation are realised by Hough transform. The algorithm proposed in this study is applicable to the detection of both large and small micro-motion targets. It is capable of detecting multiple micro-motion targets in a single range cell simultaneously and is featured with high parameter estimation precision even if there is strong noise. Simulation results and field experimental data prove the effectiveness of the proposed algorithm and its superiority compared with the inverse radon transform algorithm.

关键词： time-frequency analysis synthetic aperture radar Hough transforms Doppler radar radar signal processing radar resolution object detection Doppler effect Radon transforms parameter estimation radar imaging micromotion target detection synthetic aperture radar rotation microDoppler effect azimuth echo signal micromotion amplitude estimation algorithm micromotion target TF

来源：评论

学校读者我要写书评

暂无评论

Real-Time Detection, Tracking, and Anomaly Analysis of Dim small Space targets for Space Situational Awareness Using Star Sensors

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Wei, Yuheng Chen, Qian Wei, Xinguo Beihang Univ Sch Instrumentat & Optoelect Engn Beijing 100191 Peoples R China Beihang Univ Shen Yuan Honors Coll Beijing 100191 Peoples R China

In the space situation awareness task, high-quality imaging of space targets is the premise of completion of subsequent target orbit determination, cataloging, tracking, and other links. The quality of imaging will directly restrict the number of target detection and positioning accuracy, thus affecting the calculation of orbit. The detection of dim targets in space mainly faces the interference of stars and background noise. According to the spatial distribution characteristics of stars, targets, and noise, we propose an algorithm using the identified stars to estimate the imaging model and use the imaging model to enhance the space target. Through simulation and experimental verification, the proposed algorithm can fully tap the potential of the imaging system and greatly improve the sensitivity and accuracy of target detection. After image enhancement and segmentation, target detection and tracking methods are designed according to the spatiotemporal characteristics of the star, target, and noise imaging. At the same time, the dynamic behavior of the space target is analyzed and predicted, and the anomaly detection and early warning system is designed. As an algorithm suitable for deployment in the detector, it can greatly reduce the amount of calculation for data postprocessing, and provide a technical basis for the star sensor to realize space situation awareness function.

关键词： Stars Space vehicles Imaging signal to noise ratio Object detection Target tracking Real-time systems Satellites Aerospace electronics Feature extraction Dim space target photoelectric detection space situation awareness space target behavior understanding and prediction star background processing star sensors

来源：评论

学校读者我要写书评

暂无评论

small targets recognition in SAR ship image based on improved SSD

Small targets recognition in SAR ship image based on improve...

引用

2019 IEEE International Conference on signal, Information and data processing, ICSIDP 2019

作者： Li, Yong Chen, Jing Ke, Meng Li, Linghao DIng, Zegang Wang, Yan Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9781728123455

Synthetic Aperture Radar(SAR) ship recognition is significant in marine applications and plays an important role in maritime traffic management, fisheries management, and maritime rescue, etc. A major difficulty in SAR ship recognition is that the SAR ships have a small size in images, which results in low recognition accuracy of the SSD. This paper first analyzes the reasons for the low recognition accuracy for small targets in SSD. First, the poor matching of the default boxes leads to a small number of positive samples. Second, the representation ability of low-level feature map for recognizing small targets is weak. Then two strategies are proposed to improve the SSD. Firstly, a default box optimization design method based on Kmeans clustering is proposed, which improves the matching performance of the default boxes. Secondly, a feature fusion method based on deconvolution is proposed, which effectively improves the representation ability of low-level feature maps. The experimental results show that the proposed method can greatly improve the recognition accuracy of SSD for small targets in SAR ship images. © 2019 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Virtual output feedback in parameter estimation

引用

MECHANICAL SYSTEMS AND signal processing 2020年 142卷

作者： Bernal, Dionisio Northeastern Univ Ctr Digital Signal Proc Civil & Environm Engn Boston MA 02115 USA

The use of poles as targets for estimating parameters of linear systems is attractive from a variance perspective but the limitations are well-known, namely: the number of poles that can be identified is often smaller than the parameters to be estimated and their sensitivity can be small. One way to mitigate these limitations, initially put forth about 20 years ago, is to collect data while the structure operates in closed-loop. In this manner, poles for different gains can be aggregated, and some control over the sensitivities can be realized by gain design. This paper shows that closed-loop interrogation can be realized without physical feedback by signal processing supported on the relation between open-loop and closed-loop transfer matrices for a given gain. Guidelines for closed-loop pole locations that provide robustness are derived and two numerical examples that exemplify the scheme in a model updating framework are included. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Control Output feedback Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

基于时频脊-Radon变换的海面小目标检测方法

引用

信号处理 2021年第9期37卷 1599-1611页

作者：伍僖杰丁昊刘宁波关键海军航空大学山东烟台264001 军事科学院国防科技创新研究院北京100071

针对海杂波背景下雷达对海面弱小目标探测技术难题,提出一种基于时频脊-Radon变换的帧平滑双特征检测方法。该方法首先采用分块白化方法对海杂波进行抑制,根据抑制后海杂波单元与目标单元在时频域二维平面呈现的不同能量分布特征,对时... 详细信息

针对海杂波背景下雷达对海面弱小目标探测技术难题,提出一种基于时频脊-Radon变换的帧平滑双特征检测方法。该方法首先采用分块白化方法对海杂波进行抑制,根据抑制后海杂波单元与目标单元在时频域二维平面呈现的不同能量分布特征,对时频脊做Radon变换并在变换域特征空间中提取出峰值和频宽特征。考虑到实际雷达采用的相干脉冲数通常较少(大多情况下为64个或更少),易导致特征不稳定,进而影响海杂波与目标可分性,为此,通过多帧扫描历史数据和当前帧数据的综合应用,对特征做帧平滑处理以增强可分性。最后采用凸包分类算法,在双特征平面进行融合检测。经2级和4级海况实测数据验证,在同等参数条件下,本文检测方法相比已有基于时频三特征的检测方法、频域CFAR检测方法和分形特征检测方法具有更好的检测性能。

关键词：海杂波目标检测时频脊-Radon变换双特征帧平滑

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Low-Speed Dim small Target Detection

A Novel Method for Low-Speed Dim Small Target Detection

引用

International Congress on Image and signal processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Fan Meng Xue Ni Guang Yang Qianqian Jia Nanjing Marine Radar Institute Nanjing China College of Communications Engineering Army Engineering University of PLA Nanjing China

ISBN: (数字)9780738105451

ISBN: (纸本)9781665422994

Low-speed dim small targets are not easily detected by radar in a clutter environment. In this paper, we propose a novel approach to improve the detection probability of low-speed dim small targets, which is to convert radar data into two-dimensional images to achieve background noise suppression. Firstly, we extract the data of the target and its surroundings by setting the detection domain and make the radar data map into the data of 256 gray grades for image processing. In order to suppress clutter, we develop the improved Bilateral filter (IBF) and apply the Doppler velocity as a weight term of the Gaussian function. Combined with the weight term of spatial distance, the detection domain can be significantly enhanced. Then, the target region contour is extracted by the adaptive threshold segmentation method from the background, and the target focused is accumulated, combining with Doppler velocity. The results show that the proposed method can effectively keep the edge of the target domain and weaken the noise background, thereby improving the detection probability of the target.

关键词： Doppler effect Filtering algorithms Clutter Object detection Radar detection Radar imaging Kernel

来源：评论

学校读者我要写书评

暂无评论

A High-Precision Phase-Derived Velocity Measurement Method for High-Speed targets Based on Wideband Direct Sampling LFM Radar

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2019年第12期57卷 10147-10163页

作者： Fan, Huayu Ren, Lixiang Mao, Erke Liu, Quanhua Yang, Jian Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Beijing Inst Technol Minist Educ Key Lab Elect & Informat Technol Satellite Nav Beijing 100081 Peoples R China

This paper proposes a phase-derived velocity measurement (PDVM) method for high-speed targets based on wideband direct sampling linear frequency modulated radar. First, a high-speed target echo model considering intrapulse Doppler modulation is developed. Then, a PDVM model considering acceleration is established. The key to realizing PDVM is resolving phase ambiguity. Under low signal-to-noise ratio (SNR) conditions, a joint processing method combining acceleration information and multiframe data to solve phase ambiguity is proposed, which can significantly reduce the SNR requirement for PDVM. In this paper, the small-amplitude micromotion measurement capability of the proposed method is verified by simulation. Moreover, the measured data of a Ku-band ground-based radar are used to verify the applicability of the PDVM method under low SNR conditions and its feasibility to be applied to complex multi-scattering point targets. Both the simulation and experimental results show that the proposed method is suitable for high-speed targets with radial motion, including acceleration and jerk, and that the PDVM precision can reach the order of magnitude of centimeters per second or millimeters per second.

关键词： High-speed spatial target micromotion measurement phase-derived velocity measurement (PDVM) wideband direct sampling wideband envelope velocity measurement (WEVM)

来源：评论

学校读者我要写书评

暂无评论

Classification of FOD targets based on Polarimetric Characteristics

Classification of FOD Targets based on Polarimetric Characte...

引用

2019 IEEE International Conference on signal, Information and data processing, ICSIDP 2019

作者： Wan, Yangliang Qin, Fei Liu, Yunlong Liang, Xingdong School of Electronics Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China National Key Lab of Microwave Imaging Technology Institute of Electronics Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728123455

The invasion of foreign object debris (FOD) on the airport runway seriously threatens the safety of flight, and the accurate small radar targets classification used for the hazard level discrimination is a challenge. In this paper, a classification method based on polarization information is proposed to be used for FOD targets classification. We utilize electromagnetic simulation software for obtaining radar cross section (RCS) polarimetric data in various incident angles based on typical FOD (e.g. Spanners, Screwdrivers, PVC Pipe) targets. In addition, polarization invariant is applied to characterize targets for classification using support vector machines (SVM). Experimental results indicate that this method can classify the three objects effectively and the great potential of polarization information for FOD targets classification. © 2019 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Space Debris Tracking Via Generalized Labeled Multi-Bernoulli Random Finite Sets

Space Debris Tracking Via Generalized Labeled Multi-Bernoull...

引用

IEEE International Conference on signal processing, Communications and Computing (ICSPCC)

作者： Sun Quan Ding Ding Niu Zhaodong Natl Univ Def Technol Coll Elect Sci & Technol Natl Key Lab Sci & Technol ATR Changsha 410073 Peoples R China Natl Univ Def Technol Ctr Teaching & Res Serv Changsha 410073 Peoples R China

ISBN: (纸本)9781728117089

Y In this paper we present an algorithm for detection and tracking space debris under complex space background via delta-generalized labeled multi-Bernoulli (delta-GLMB) random finite sets (RFS). It includes two parts, position extractor for suspected targets and tracking filter. The core strategy of this position extractor is morphological method. The filter is implemented by Sequential Monte Carlo (SMC) method and each iteration of delta-GLMB multi-target tracking filter includes two operations: update and prediction. The processing results of measured data show that the algorithm has strong detection and tracking ability for dim and small targets under complex space background. To the best of our knowledge, this is the first time that the delta-GLMB multi-target tracking filter has been successfully applied in the field of space debris target detection and tracking.

关键词： space debris detection GLMB tracking filter complex space background dim and small targets

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：