检索结果-内蒙古大学图书馆

2019 IEEE International Conference on signal, information and Data processing, ICSIDP 2019

作者： Tang, Wei Jun, Baozhao Tang, Linbo Pan, Yu Jin, Dongling Quan, Zhengpiao 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 China

ISBN: (纸本)9781728123455

Aircraft detection in optical remote sensing image is an important research direction in the field of remote sensing. The existing detection methods are difficult to achieve satisfactory results. Traditional detection methods are low robustness, due to manual feature modeling are difficult and subject to background interference;The deep learning target detection method, which improves the detection performance at the cost of complexity improvement, cannot be widely used in space-borne platforms limited resources. In view of the above problems, this paper proposes an aircraft target deep learning detection method of lightweight and multi-scale features. On the basis of the multi-scale target detection framework (SSD), the method firstly uses the dense connection structure and the double convolution channels to form the basic backbone networks with feature reuse and high computational efficiency. To improve the detection performance of the small aircraft target, the basis backbone network connects a residual module and deconvolution to compose the multi-scale feature fusion detection module. Compared with the current classical deep learning object detection methods, the experimental results show that the proposed method has the advantages of maintaining low computational complexity and achieving high detection accuracy. © 2019 IEEE.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

Learning fair face representation with progressive cross transformer

arXiv

引用

arXiv 2021年

作者： Li, Yong Sun, Yufei Cui, Zhen Shan, Shiguang Yang, Jian Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology

Face recognition (FR) has made extraordinary progress owing to the advancement of deep convolutional neural networks. However, demographic bias among different racial cohorts still challenges the practical face recognition system. The race factor has been proven to be a dilemma for fair FR (FFR) as the subject-related specific attributes induce the classification bias whilst carrying some useful cues for FR. To mitigate racial bias and meantime preserve robust FR, we abstract face identityrelated representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition. Originating from the signal decomposition theory, we attempt to decouple face representation into i) identity-related components and ii) noisy/identity-unrelated components induced by race. As an extension of signal subspace decomposition, we formulate face decoupling as a generalized functional expression model to cross-predict face identity and race information. The face expression model is further concretized by designing dual cross-transformers to distill identity-related components and suppress racial noises. In order to refine face representation, we take a progressive face decoupling way to learn identity/racespecific transformations, so that identity-unrelated components induced by race could be better disentangled. We evaluate the proposed PCT on the public fair face recognition benchmarks (BFW, RFW) and verify that PCT is capable of mitigating bias in face recognition while achieving state-of-the-art FR performance. Besides, visualization results also show that the attention maps in PCT can well reveal the race-related/biased facial regions. © 2021, CC BY-NC-SA.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Spaceborne Bistatic InSAR Geolocation with Geostationary Transmitter

Spaceborne Bistatic InSAR Geolocation with Geostationary Tra...

引用

2019 IEEE International Conference on signal, information and Data processing, ICSIDP 2019

作者： Wang, Yuekun Lu, Zheng Tian, Feng Suo, Zhiyong Li, Zhenfang Zhu, Yu Nanjing Research Institute of Electronics Technology Nanjing China Beijing Institute of Spacecraft System Engineering Beijing China National Key Laboratory of Radar Signal Processing Xidian University Xi'an China

ISBN: (纸本)9781728123455

The bistatic interferometric synthetic aperture radar (InSAR) system, with a geosynchronous earth orbit (GEO) illuminator and two low-earth-orbit (LEO) receivers, has the advantages of flexibility, lightweight receiving platform and low cost. However, its geometry of bistatic interferometry is complex, and its slant range equation is in the form of round-trip delay. The traditional three-dimensional (3D) positioning methods of InSAR with 'one-transmitter and two-receivers' and repeat tracks are invalid. In order to solve this problem, firstly, we establish the bistatic InSAR target positioning equations. Secondly, according to the interferometric geometry, the conversion relationship between baseline vector and slant range vector is constructed. Then, we derive and present a closed-form solution of the bistatic InSAR target positioning in the form of geostationary GEO SAR orbit. Finally, the effectiveness of the proposed method is verified by simulation data. © 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

A circularly polarized low-profile Metasurface antenna based on CPW feed

A circularly polarized low-profile Metasurface antenna based...

引用

IEEE International Wireless Symposium (IWS)

作者： Changqing Liu Liang Zhang Shijie Huang Chao Wang Xingchuan Yu Xianliang Wu Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University AnHui Province Key Laboratory of simulation and design for Electronic information system Hefei Normal university Hefei China

ISBN: (数字)9781728167039

ISBN: (纸本)9781728167046

A low-profile circularly polarized Metasurfaces antenna based on compact coplanar waveguide (CPW) feed was proposed. The Metasurfaces consists of 16 periodic square-cut metal patches. An hourglass coupled slot was adopted to achieve broadband impedance matching. The antenna has a simple structure and a low cross section, and it can be implemented by a layer of a printed circuit substrate. A circular polarized wave is generated by changing the size of the cut angle of the Metasurfaces, and at the same time, the impedance bandwidth can be widened. To verify the simulation results, a 1λ 0 ×1λ 0 ×0.05λ 0 (at 10 GHz) model antenna was fabricated and measured. The simulation and measurement results show good consistency. The test results show that the -10dB return loss bandwidth reaches 45.3 %, and the circular polarization axis ratio(AR) is less than 3dB with a bandwidth of 18.5%.

关键词： Antenna measurements Polarization Bandwidth Metasurfaces radar antennas Antenna feeds Coplanar waveguides

来源：评论

学校读者我要写书评

暂无评论

A Dual-Port Leaky-Wave Array Antenna Integrated Beam-Steerable Schottky Heterodyne Receiver for Terahertz-Band Applications

引用

IEEE Transactions on Terahertz Science and Technology 2025年

作者： Li, Huanxin Gao, Xiang Chen, Ziru Qiao, Dan Bu, Xiangyuan An, Jianping Beijing Institute of Technology School of Information and Electronics Beijing 100081 China National Institute of Metrology Division of Electronics and Information Metrology Beijing 100020 China Beijing Institute of Technology School of Cyberspace Science and Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing 100081 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing 100081 China

This paper presents a dual-port leaky-wave array antenna integrated beam-steerable Schottky heterodyne receiver that may be attractive for terahertz (THz) sensing applications. The receiver chip features a low-cost wideband quasi-optical design that utilizes one frequency-scanning leaky-wave array and one fixed-beam monopole integrated lens antenna for efficiently coupling the radio-frequency (RF) and local-oscillator (LO) signals, respectively. Operating in the subharmonic mixing mode, a dual-channel beam-steerable Schottky heterodyne receiver circuit was designed for performance maximization via both passive and active modeling. A prototype of THz beam-steerable receiver module was manufactured and experimentally demonstrated. By flexibly switching between seven fixed LO frequencies among 99.5-114.5 GHz, the receiver can reconfigurably detect the RF signal at one of seven equally-divided sub-bands from 200 to 235 GHz, with an intermediate-frequency bandwidth up to 5 GHz. In particular, the receiver can detect the RF beam from unfixed incident direction over a wide steering coverage range of 80°. The measured average single-sideband conversion gain and noise figure are around -9.1 dB and 9.4 dB, respectively. The results have validated good receiver performance and its potential for sensing applications. © 2025 IEEE.

关键词： Single sideband receivers

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

SOPC-based Implementation of Convolutional Neural Network

SOPC-based Implementation of Convolutional Neural Network

引用

2019 IEEE International Conference on signal, information and Data processing, ICSIDP 2019

作者： Feng, Xing Jia, Mingfei Chen, He Radar Research Lab School of Information and Electronics Beijing Institute of Technology China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781728123455

Convolutional Neural Network (CNN) is an algorithm widely used in the field of deep learning. Due to the large number of intensive parallel data operations, the use of CPU to implement the CNN serially consumes too much time. In view of the above research background, the System-on-a-Programmable-Chip (SOPC) implementation and acceleration modules of CNN are designed by using the Zynq-7035 development platform launched by Xilinx as the experimental platform. The experiment results show that our method is effective and efficiency for the target image classification on the development platform. © 2019 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Interferometric Phase of Clutter-Suppression Residuals Aided Multichannel SAR-GMTI

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Min Tian Bin Liao Bo Yuan Deng Hui Hu Hangzhou Institution of Technology Xidian University Hangzhou China Xidian University Xi’an China State Key Laboratory of Radio Frequency Heterogeneous Integration and Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Research Institute Tsinghua University Shenzhen China Innovation Academy for Microsatellites Chinese Academy of Sciences Shanghai China

For multichannel synthetic aperture radar (SAR) ground-moving target identification (GMTI) in heterogeneous and strong clutter backgrounds, it is challenging to accurately detect slow and weak targets when relying solely on the magnitude of clutter-suppression residuals, due to the significant clutter residuals and signal-to-noise losses. To address this, a detector that leverages both the magnitude and phase information in multichannel SAR-GMTI clutter suppression is proposed. For an M-channel SAR system, the detection test is formulated as the product of the residual magnitude from M-channel clutter suppression and a phase factor derived from the interferometric phase between two residuals from the first and last $M-1$ channels. This phase factor captures the dissimilarity from the clutter, enabling the suppression of strong clutter residuals and improving the signal-to-clutter-plus-noise ratio (SCNR). Using the product clutter model, a constant false-alarm ratio (CFAR) detection framework is designed. The receiver operator characteristic (ROC) metrics, obtained from simulations and real-data experiments, validate the proposed method’s superiority over the state-of-the-art techniques, and the detection sensitivity on the clutter heterogeneity, correlation coefficients between pairs of clutter-suppression residuals, and target parameters are analyzed for practicality. In the X-band airborne radar GMTI experiments, the minimum discernible input SCNR of −6 dB for a target radial velocity of 4 m/s and 0 dB for 2 m/s demonstrate the effectiveness in detecting the dim targets within strong clutter.

关键词： Clutter radar polarimetry Synthetic aperture radar Vectors Object detection radar antennas signal to noise ratio Detectors Backscatter Airborne radar

来源：评论

学校读者我要写书评

暂无评论

Three-level Memory Access Architecture for FPGA-based Real-time Remote Sensing Image processing System

Three-level Memory Access Architecture for FPGA-based Real-t...

引用

2019 IEEE International Conference on signal, information and Data processing, ICSIDP 2019

作者： Zhang, Ning Wei, Xin Chen, Lei Chen, He Radar Research Lab School of Information and Electronics Beijing Institute of Technology China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781728123455

Recently, extensive convolutional neural network (CNN)-based methods have been used for real-time remote sensing image processing system. However, the huge storage requirement for model and input image bring a great challenge to hardware implement. In this paper, we propose a three-level memory access architecture for FPGA-based real-time remote sensing image processing system to meet the storage requirement. Moreover, in the proposed architecture, the computational throughput is well matched to the storage bandwidth, which improve the efficiency of arithmetic processing on the hardware platform. In the experiment, we applied the architecture to the hardware implementation of CNN, and implement on Xilinx ZYNQ xc7z035 platform. Our design is evaluated on a main part of the modified YOLOv2 framework [1]. The experimental results demonstrate that this design can access the off-chip memory efficiently, and can provide the required parameters and input data for the CNN on-chip pipeline processing. © 2019 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Ground Moving Target Imaging Based on MSOKT and KT for Synthetic Aperture radar

Ground Moving Target Imaging Based on MSOKT and KT for Synth...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jun Wan Zhanye Chen Yu Zhou Dong Li Yan Huang Linrang Zhang Chongqing Key Laboratory of Space Information Network and Intelligent Information Fusion Chongqing University Chongqing P. R. China National Laboratory of Radar Signal Processing Xidian University Xi'an P. R. China Purple Mountain Laboratory Nanjing P. R. China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

The synthetic aperture radar (SAR) image of ground moving targets will be typical smeared given the range migration (RM) and Doppler frequency migration (DFM). To deal with these issues, a new SAR ground moving target imaging method based on modified second-order keystone transform (MSOKT) and keystone transform (KT) is developed in this paper. Firstly, the time reversing process is utilized to separate the second-order phase. Secondly, the range curvature migration and DFM are removed by MSOKT, and then the second-order phase is estimated. Finally, the moving target is finely focused after eliminating residual RWM by KT. The main contributions of this paper are listed as follows: 1) the proposed method can effectively focus moving targets without residual errors; 2) the effects of Doppler ambiguity and blind speed sidelobe are further handled. The effectiveness of the proposed method is confirmed by the simulation and real data-processing results.

关键词： Doppler effect Synthetic aperture radar Imaging Transforms radar imaging Azimuth Time-frequency analysis

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：