检索结果-内蒙古大学图书馆

Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks

arXiv

引用

arXiv 2018年

作者： Yang, Xue Sun, Hao Fu, Kun Yang, Jirui Sun, Xian Yan, Menglong Guo, Zhi Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing

Ship detection has been playing a significant role in the field of remote sensing for a long time but it is still full of challenges. The main limitations of traditional ship detection methods usually lie in the complexity of application scenarios, the difficulty of intensive object detection and the redundancy of detection region. In order to solve such problems above, we propose a framework called Rotation Dense Feature Pyramid Networks (R-DFPN) which can effectively detect ship in different scenes including ocean and port. Specifically, we put forward the Dense Feature Pyramid Network (DFPN), which is aimed at solving the problem resulted from the narrow width of the ship. Compared with previous multi-scale detectors such as Feature Pyramid Network (FPN), DFPN builds the high-level semantic feature-maps for all scales by means of dense connections, through which enhances the feature propagation and encourages the feature reuse. Additionally, in the case of ship rotation and dense arrangement, we design a rotation anchor strategy to predict the minimum circumscribed rectangle of the object so as to reduce the redundant detection region and improve the recall. Furthermore, we also propose multi-scale ROI Align for the purpose of maintaining the completeness of semantic and spatial information. Experiments based on remote sensing images from Google Earth for ship detection show that our detection method based on RDFPN representation has a state-of-The-Art performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Design of an Ultra-Wideband Low-Profile Directional Bowtie Antenna for Ground-Penetrating Radars

Design of an Ultra-Wideband Low-Profile Directional Bowtie A...

引用

International Conference on Microwave and Millimeter Wave technology Proceedings

作者： Jin Wu Jing Ma Bin Shi Kun-Shan Mo Lin Peng The Key Laboratory of Microwave and Optical Wave Application Technology Guilin University of Electronic Technology Guilin Guangxi China The Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing China School of Electronic Information and Automation Guilin University of Aerospace Technology Guilin Guangxi China

ISBN: (数字)9798350389968

ISBN: (纸本)9798350389975

In this paper, An elliptical patch dipole antenna with resistive loading and parasitic structure is proposed. By loading the parasitic structure, the height of the antenna is reduced. The overall dimensions of the antenna are $0.16\lambda_{0}\times 0.08\lambda_{0}\times 0.03\lambda_{0}$ , and $\lambda_{0}$ is the free-space wavelength at the lowest frequency. By loading large reflective floors, the proposed antenna achieves a good unidirectional radiation performance in the whole frequency band from 0.18 GHz to 2 GHz with a $\text{VSWR} < 2$ , and an in-band peak gain of up to 7.41 dBi is obtained. It is a good candidate antenna for ground-penetrating radar.

关键词： Microwave antennas Ground penetrating radar Dipole antennas Loading Bandwidth Millimeter wave radar Radar antennas

来源：评论

学校读者我要写书评

暂无评论

Beyond triplet loss: Meta prototypical N-tuple loss for person re-identification

arXiv

引用

arXiv 2020年

作者： Zhang, Zhizheng Lan, Cuiling Zeng, Wenjun Chen, Zhibo Chang, Shih-Fu The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Anhui Hefei China Microsoft Research Asia Beijing China Columbia University New YorkNY United States

Person Re-identification (ReID) aims at matching a person of interest across images. In convolutional neural network (CNN) based approaches, loss design plays a vital role in pulling closer features of the same identity and pushing far apart features of different identities. In recent years, triplet loss achieves superior performance and is predominant in ReID. However, triplet loss considers only three instances of two classes in per-query optimization (with an anchor sample as query) and it is actually equivalent to a two-class classification. There is a lack of loss design which enables the joint optimization of multiple instances (of multiple classes) within per-query optimization for person ReID. In this paper, we introduce a multi-class classification loss, i.e., N-tuple loss, to jointly consider multiple (N) instances for per-query optimization. This in fact aligns better with the ReID test/inference process, which conducts the ranking/comparisons among multiple instances. Furthermore, for more efficient multi-class classification, we propose a new meta prototypical N-tuple loss. With the multi-class classification incorporated, our model achieves the state-of-the-art performance on the benchmark person ReID datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Mid-infrared Q-switch performance of ZrC

引用

Photonics Research 2020年第12期8卷 1857-1861页

作者： YANGYANG LIANG TAO LI WENCHAO QIAO TIANLI FENG SHENGZHI ZHAO YUEFENG ZHAO YUZHI SONG CHRISTIAN KRÄNKEL China Key Laboratory of Laser&Infrared System(Shandong University) Ministry of EducationQingdao 266237China School of Information Science and Engineering and Shandong Provincial Key Laboratory of Laser Technology and ApplicationShandong UniversityQingdao 266237China Collaborative Innovation Center of Light Manipulations and Applications Shandong Normal UniversityJinan 250358China School of Physics and Electronics Shandong Normal UniversityJinan 250358China Leibniz-lnstitut fur Kristallzuchtung 12489 BerlinGermany

Zirconium carbide(ZrC)with layered structure and nanoparticle morphology was prepared by sonication in an ethyl alcohol *** morphology and saturable absorption properties of the ZrC were systematically *** using ZrC nanoparticle coated substrates as saturable absorbers,stable Q-switched 3μm Er:Lu_(2)O_(3) lasers were *** durations of 50 ns with pulse energies of 20μJ and peak power of 0.4 kW are the shortest obtained with novel-material-based Q-switched lasers in the 3μm wavelength range.

关键词： switched absorber shortest

来源：评论

学校读者我要写书评

暂无评论

A modified wind vector retrieval algorithm for polarimetric scatterometer

A modified wind vector retrieval algorithm for polarimetric ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xuetong Xie Mingsen Lin Zhou Huang Juhong Zou Dongxuan Tian Lixia Liu Xiaoning Wang Shiwei Dong ATR State Key Laboratory National University of Defense Technology Changsha China National Satellite Ocean Application Service Beijing China Institute of Remote Sensing and Geographic Information System Peking University Beijing China Institute of Space Radio Technology National Key Laboratory of Space Microwave Technology Xi'an China

Experiments and theoretical analysis demonstrate that the polarimetric scatterometer has the potential in enhancing the accuracy of the wind vector retrieval. However, currently, there is no special wind vector retrieval algorithm for the polarimetric scatterometer. Based on the distribution characteristic of the objective function, a modified wind vector retrieval algorithm was designed for the conically scanning polarimetric scatterometer in this paper. Simulation experiments indicated that this algorithm could further improve the retrieval precision of the polarimetric scatterometer in comparison with the traditional algorithm, especially in the nadir- and outer-swath. By extending the wind direction range for the first and second ambiguity in the nadir- and outer-swath, the algorithm can effectively reduce the uncertainty of the wind direction solutions with error magnitude of 0° to 15°. Up to 2° improvement in wind direction retrieval can be achieved in the nadir track.

关键词： Radar measurements Spaceborne radar Wind speed Algorithm design and analysis Oceans Filtering algorithms Accuracy

来源：评论

学校读者我要写书评

暂无评论

Design of UHF Low-profile Monopole Antenna for Ground Penetrating Radar

Design of UHF Low-profile Monopole Antenna for Ground Penetr...

引用

International Conference on Microwave and Millimeter Wave technology Proceedings

作者： Jia-Jia Huang Jing Ma Zhi-Hao Li Yong-Han Lu Li-Wei Guo Lin Peng Key Laboratory of Cognitive Radio and Information Processing (Ministry of Education) Guilin University of Electronic Technology Guangxi China Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Microwave and Optical Wave Application Technology Guilin University of Electronic Technology Guangxi China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing China

A low-profile and ultra-wideband unidirectional monopole antenna with absorbing material loading is proposed for ground-penetrating radar (GPR) applications in the UHF band. The overall dimensions of the antenna is 0.472λ 0 × 0.152λ 0 ×0.006λ 0 , where λ 0 is the free-space wavelength at the lowest frequency of 0.38GHz. The monopole antenna with low profile operates in the 0.38GHz-3GHz band with standing-wave ratio<2, a realized gain between -8.13 and 0.04 dBi. Good unidirectional radiation patterns were obtained in the whole band. The composed array antenna can be applied to the transmit signal and receive signal modules of the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Miniaturization Design of TEM Horn Antenna for Ground-Penetrating Radar

Miniaturization Design of TEM Horn Antenna for Ground-Penetr...

引用

International Conference on Microwave and Millimeter Wave technology Proceedings

作者： Zhi-Hao Li Jing Ma Jin Wu Jia-Jia Huang Yong-Han Lu Lin Peng Key Laboratory of Cognitive Radio and Information Processing (Ministry of Education) Guilin University of Electronic Technology Guilin China Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Microwave and Optical Wave Application Technology (Guilin University of Electronic Technology) Guilin China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing China

This paper presents a miniaturized TEM horn antenna for ground penetrating radar (GPR). First, an exponential gradient horn antenna is designed with a low cut-off frequency of 0.45 GHz. Then, the low cut-off frequency is decreased to 0.19 GHz through curve structural loading and lens loading without increasing the size of the horn. The antenna size is 378.49 mm × 359.07 mm × 386.06 mm, corresponding to 0.226 λ 1 × 0.238 λ 1 × 0.243 λ 1 ( λ 1 is the wavelength corresponding to the lowest frequency of the antenna). The results show that the working bandwidth of the antenna is 0.19-3GHz, and it has a good radiation pattern in the band, with a peak gain of 12.4dBi, which would be a good candidate for GPR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A W-band All-Dielectric Lens Antenna with Flat-Top Radiation Pattern

A W-band All-Dielectric Lens Antenna with Flat-Top Radiation...

引用

International Conference on Microwave and Millimeter Wave technology Proceedings

作者： Yong-Han Lu Jing Ma Zhi-Hao Li Jia-Jia Huang Kun-Shan Mo Lin Peng Key Laboratory of Cognitive Radio and Information Processing (Ministry of Education) Guilin University of Electronic Technology Guilin China Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Microwave and Optical Wave Application Technology (Guilin University of Electronic Technology) Guilin China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing China

This paper proposes a W-band all-dielectric lens antenna with the characteristic flat-top beam. The lens loaded on the horn is composed of 10 concentric elliptical rings and a tapered matching layer. Its geometries are optimized by the non-dominated sorting genetic algorithm II (NSGA-II). The lens antenna designed at 92-97 GHz achieves a beamwidth of 40° with ripple level less than 1 dB in E-plane and H-plane. In addition, the proposed antenna can be prototyped easily using 3D-printing technology with low cost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional Graph Linear Canonical Transform

arXiv

引用

arXiv 2024年

作者： Li, Na Zhang, Zhichao Han, Jie Chen, Yunjie Cao, Chunzheng School of Mathematics and Statistics Center for Applied Mathematics of Jiangsu Province Jiangsu International Joint Laboratory on System Modeling and Data Analysis Nanjing University of Information Science and Technology Nanjing210044 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China Key Laboratory of Computational Science and Application of Hainan Province Haikou571158 China School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Nanjing210044 China

Many multi-dimensional (M-D) graph signals appear in the real world, such as digital images, sensor network measurements and temperature records from weather observation stations. It is a key challenge to design a transform method for processing these graph M-D signals in the linear canonical transform domain. This paper proposes the two-dimensional graph linear canonical transform based on the central discrete dilated Hermite function (2-D CDDHFs-GLCT) and the two-dimensional graph linear canonical transform based on chirp multiplication-chirp convolution-chirp multiplication decomposition (2-D CM-CC-CM-GLCT). Then, extending 2-D CDDHFs-GLCT and 2-D CM-CC-CM-GLCT to M-D CDDHFs-GLCT and M-D CM-CC-CM-GLCT. In terms of the computational complexity, additivity and reversibility, M-D CDDHFs-GLCT and M-D CM-CC-CM-GLCT are compared. Theoretical analysis shows that the computational complexity of M-D CM-CC-CM-GLCT algorithm is obviously reduced. Simulation results indicate that M-D CM-CC-CM-GLCT achieves comparable additivity to M-D CDDHFs-GLCT, while M-D CM-CC-CM-GLCT exhibits better reversibility. Finally, M-D GLCT is applied to data compression to show its application advantages. The experimental results reflect the superiority of M-D GLCT in the algorithm design and implementation of data compression. Copyright © 2024, The Authors. All rights reserved.

关键词： Chirp modulation

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Simulation Aided SAR Target Classification Via Deep Domain Adaptation

Electromagnetic Simulation Aided SAR Target Classification V...

引用

IEEE International Conference on Radar

作者： Xiaoling Lv Xiaolan Qiu Wenming Yu Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Suzhou Aerospace Information Research Institute Suzhou China State key Laboratory of Millimeter Waves Southeast University Nanjing China

ISBN: (纸本)9781665468893

Convolutional neural networks (CNNs) have made tremendous success in optical images classification recently. However, in synthetic aperture radar (SAR) target classification, it is difficult to annotate a large amount of real SAR images to train CNNs. Sufficient annotated images can be easily obtained through simulation, but the disparity between the simulated images and the real images makes them difficult to directly apply to the real images classification. In this paper, we propose a model that integrates multi-kernel maximum mean discrepancy (MK-MMD) and domain-adversarial training to alleviate this problem. Simulated SAR images with annotation and unlabeled real SAR images are used to train our model. First, we use domain-adversarial training to prompt the model to extract domain-invariant features. Then, the MK-MMD between the hidden representations of simulated images and real images is reduced to narrow domain discrepancy. Experimental results on the real SAR dataset demonstrate that our method effectively solves the domain shift problem and improves the classification accuracy.

关键词： Training Adaptation models Optical fiber networks Feature extraction Optical imaging Radar polarimetry Data models

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：