检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Jiang, Bo Zhou, Zitai Wang, Xiao Tang, Jin Key Laboratory of Intelligent Computing Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China

Image salient object detection (SOD) is an active research topic in computer vision and multimedia area. Fusing complementary information of RGB and depth has been demonstrated to be effective for image salient object detection which is known as RGB-D salient object detection problem. The main challenge for RGB-D salient object detection is how to exploit the salient cues of both intra-modality (RGB, depth) and cross-modality simultaneously which is known as cross-modality detection problem. In this paper, we tackle this challenge by designing a novel cross-modality Saliency Generative Adversarial Network (cmSalGAN). cmSalGAN aims to learn an optimal view-invariant and consistent pixel-level representation for RGB and depth images via a novel adversarial learning framework, which thus incorporates both information of intra-view and correlation information of cross-view images simultaneously for RGB-D saliency detection problem. To further improve the detection results, the attention mechanism and edge detection module are also incorporated into cmSalGAN. The entire cmSalGAN can be trained in an end-to-end manner by using the standard deep neural network framework. Experimental results show that cmSalGAN achieves the new state-of-the-art RGB-D saliency detection performance on several benchmark datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

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

signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Yuekun Wang Zheng Lu Feng Tian Zhiyong Suo Zhenfang Li Yu Zhu 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: (数字)9781728123455

ISBN: (纸本)9781728123462

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble Margin Based Semi-Supervised Random Forest for the Classification of Hyperspectral Image with Limited Training Data

Ensemble Margin Based Semi-Supervised Random Forest for the ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Wei Feng Wenjiang Huang Gabriel Dauphin Junshi Xia Yinghui Quan Huichun Ye Yingying Dong Key laboratory of Digital Earth Science Chinese Academy of Sciences Beijing China Laboratory of Information Processing and Transmission University Paris XIII France Geoinformatics Unit RIKEN Center for Advanced Intelligence Project Tokyo Japan Key Laboratory for Radar Signal Processing Xidian University Shaanxi China

In this paper, we propose a novel ensemble margin based semi-supervised random forest (EMRF) algorithm for the classification of the hyperspectral image with limited training data. The proposed method tries to improve the effectiveness of the ensemble model via adaptively labeling the unlabeled instances with high classification probability then adding them into the training set. The classification probability of a training instance is reflected by the unsupervised margin value of this instance. The higher ensemble margin of an instance, the higher probability the instance being classified correctly and added into to the training set in the next iteration.

关键词： Training Radio frequency Hyperspectral imaging Training data

来源：评论

学校读者我要写书评

暂无评论

Facial emotion detection using thermal and visual images based on deep learning techniques

引用

The Journal of Photographic science 2024年第2期72卷

作者： Richa Rashmi U. Snekhalatha Anela L. Salvador Alex Noel Joseph Raj a Department of Biomedical Engineering College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur 603203 Tamil Nadu India a Department of Biomedical Engineering College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur 603203 Tamil Nadu Indiab College of Engineering Architecture and Fine Arts Batangas State University The National Engineering University Alangilan Campus Batangas City Batangas Philippines 4200 b College of Engineering Architecture and Fine Arts Batangas State University The National Engineering University Alangilan Campus Batangas City Batangas Philippines 4200 c Key laboratory of Digital Signal and Image Processing of Guangdong Province Department of Electronic Engineering College of Engineering Shantou University People’s Republic of China

ABSTRACTThe main objectives of this study are (i) to determine the different emotions, such as happy, anger, neutral, and sad, based on the visual and thermal images for facial expression recognition of healthy individuals; (ii) to train the modified pre-trained models, such as DenseNet-121, ResNet-50, and VGG-19 based on transfer learning technique, using the visual and thermal image dataset, and (iii) to compare the three different customize model with that of three pre-trained models in terms of accuracy. The customized CNN models were proposed to classify the four classes of emotions with high efficiency. Among thermal and visual image dataset, the thermal images have produced highest classification accuracy of 95.8% using the Customized Net-3 model and have outperformed the three modified pre-trained models while classifying the four facial expressions. Thus, the proposed customized CNN model is proven effective for facial emotion recognition based on thermal imaging using deep learning techniques.

关键词： Facial expression emotion recognition thermal imaging deep neural network convolution neural network Facial thermal image Visual image Pre-trained models

来源：评论

学校读者我要写书评

暂无评论

Features of multi-fractal structure of high-altitude lightning discharges in the ionosphere: Elves, jets, sprites

Features of multi-fractal structure of high-altitude lightni...

引用

IET International radar Conference 2018, IRC 2018

作者： Potapov, Alexander A. Cerman, Vitality A. V.A. Kotel'nikov Institute of Radio Engineering and Electronics Russian Academy of Sciences Moscow Russia JNU-IREE Joint Laboratory of Fractal Method and Signal Processing Department of Electronic Engineering College of Information Science and Technology JiNan University Guangzhou China

Physical properties of elves, jets and sprites, which are the most interesting types of high-attitude discharges in the atmosphere, are considered in the work. The results of researches of its fractal characteristics are presented. The obtained results give grounds for a deeper insight of development, relaxation of such atmosphere processes and taking into account of their action on radio systems. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Fractals

来源：评论

学校读者我要写书评

暂无评论

Design of New Miniaturized Broadband Bandpass Filter Based on SIR

Design of New Miniaturized Broadband Bandpass Filter Based o...

引用

Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL)

作者： Kaiyue Duan Pingjuan Zhang Dongya Cheng Yawen Song Lichang Huang Minquan Li Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Science and Technology University Hefei China

ISBN: (数字)9781728153049

ISBN: (纸本)9781728153056

In this paper, a compact and miniaturized wideband bandpass filter based on resonant ring loading stepped impedance resonator is designed. The filter designed in this paper uses the resonant ring as the basic resonator unit. By loading the SIR, the passband width of the filter is improved. The 3 dB bandwidth of this filter is 300 MHz, and the relative fractional bandwidth is 15%. Etching a complementary open resonant ring defected ground structure (DGS) on the floor that changes the current distribution on the floor and creates a band gap with passband characteristics, making the filter compact and compact. The size of filter is 3.5 cm * 4.0 cm. The simulation results show that the filter center frequency is 2.0 GHz, the return loss is 29 dB, and the insertion loss is 1.1 dB. The filter introduces two transmission zero points of 1.3 GHz and 2.6 GHz on both sides of the passband, which improves the out-of-band rejection of the filter. The filter structure designed in this paper has the advantages of small size, wide bandwidth and strong stop band rejection, which verifies the feasibility of the filter design.

关键词： Bandwidth Broadband communication Impedance Passband Resonant frequency Microstrip Filtering theory

来源：评论

学校读者我要写书评

暂无评论

A Multiband High Gain Grooves Antenna

A Multiband High Gain Grooves Antenna

引用

Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL)

作者： Ping-Juan Zhang Yawen Song Lichang Huang Minquan Li Anhui Science and Technology University Bengbu China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9781728153049

ISBN: (纸本)9781728153056

In this paper, we present a novel high-gain multiband surface-wave antenna base on extraordinary optical transmission. In order to make the performance of antenna more better we introduced metal wall structure, it can improve the gain of antenna and the half-power beamwidth also have a good embodiment in the E-plane and H-plane. Simulation results show that the gain of proposed antenna can reach more than 12 dB.

关键词： Metals Antenna measurements Gain Surface waves Electromagnetics Transmitting antennas

来源：评论

学校读者我要写书评

暂无评论

Broadband Circular Polarized Composite Spiral Antenna Using Two-layer AMC

Broadband Circular Polarized Composite Spiral Antenna Using ...

引用

Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL)

作者： Yawen Song Pingjuan Zhang Yanyang Liu Kaiyue Duan Lichang Huang Minquan Li Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Science and Technology University Hefei China

ISBN: (数字)9781728153049

ISBN: (纸本)9781728153056

In this paper, a broadband circular polarized (CP) composite spiral antenna using two-layer artificial magnetic conductor (AMC) is designed. The broadband circularly polarized radiation of the antenna in free space is realized by combining Archimedes spiral and equiangular spiral. At the same time, a new two-layer AMC structure is designed to improve the degradation of axial ratio and bandwidth caused by unidirectional antenna radiation in some frequency bands. The two-layer AMC is designed to operate with 90° reflection-phase bandwidth of 4.3-6 GHz (33%). Three different reflector surfaces: perfect electric conductor (PEC), traditional single-layer AMC surface and two-layer AMC surface are used and compared. The axial ratio performance of the antenna loaded with two-layer AMC is significantly better than that of the traditional AMC in the band of 5-6.5 GHz. The axial ratio and bandwidth was further improved by removing the central patch on the two-layer AMC surface and adding a high dielectric substrate underneath. The simulation results show that in the 2.5-10 GHz working band, the VSWR

关键词： Spirals Broadband antennas Bandwidth Loaded antennas Periodic structures Helical antennas

来源：评论

学校读者我要写书评

暂无评论

Compact Dual-wideband Bandpass Filter Using Stub Loaded Zero-degree Feed Coupling Structure

Compact Dual-wideband Bandpass Filter Using Stub Loaded Zero...

引用

Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL)

作者： Lichang Huang Pingjuan Zhang Minquan Li Yawen Song Kaiyue Duan Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Science And Technology University Hefei China

ISBN: (数字)9781728153049

ISBN: (纸本)9781728153056

A novel compact dual-wideband bandpass filter is proposed in this paper, by employing stub loaded ring-shape Uniform Impedance Resonator (UIR) and embed-inside T-shape resonator which contributes to reducing circuit size. Odd-even mode method can be used to analyze the resonance characteristic, since the structure is symmetrical. The stub-load UIR can produce two resonant frequencies of f odd1 and f even1 , and the T-shape resonator can also introduce two resonant frequencies of f odd2 and f even2 . By adjusting the position of odd-even mode resonant frequencies and the coupling degree between UIR and T-shape resonator, two wide passbands can be realized. In design, a pair of zero-degree feed coupling structure is utilized to generate two transmission zeroes at the lower and upper of the first passband, improving the frequency selectivity of the first. The 3 dB frequency bands range of the first passband and the second are 2.5 GHz-3.3 GHz and 5.1 GHz-6.2 GHz, and the fractional bandwidths are 29% and 19%, corresponding to center frequencies at 2.8 GHz, 5.8 GHz, respectively. Comparing with the previous works, the proposed dual-wideband bandpass filter has a compactness of 12 × 10.45 mm 2 and has lower insertion loss of 0.1 dB and 0.12 dB, corresponding to the first and the second pass-band.

关键词： Band-pass filters Resonant frequency Passband Feeds Couplings Microwave antennas Dual band

来源：评论

学校读者我要写书评

暂无评论

An Improved Pilot-free De-spreading Algorithm for Underwater Acoustic Orthogonal Frequency Division Multiplexing Spread Spectrum Communication

An Improved Pilot-free De-spreading Algorithm for Underwater...

引用

OCEANS - Europe

作者： Zhanqing Pu Wei Wang Yu Li Danyang Hong Shuqiu Li Haining Huang Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

Underwater acoustic (UA) communication channel in the shallow water is fast time-varying and selective fading. Proper de-spreading method is needed for the orthogonal frequency division multiplexing spread spectrum UA communication system to reconstruct the information. The conventional de-spreading algorithm decrease the communication rate due to the using of the pilot for channel estimation. To accurately estimate the channel response without much loss in communication efficiency, an improved pilot-free spread spectrum de-spreading (IPSSD) method is proposed in this paper. This algorithm first recognizes the spread spectrum signal in frequency domain using the sparseness of the underwater acoustic channel. Then a decision feedback estimation of the channel impulse response is achieved according to the recognition results. The least square method is utilized to decrease the estimation complexity, and channel puncturing technique is exploited to correct the estimation error, thus realizing the robust performance of the communication system. The results obtained by Monte Carlo simulation and lake-trial are provided, demonstrating that the new pilot-free algorithm can significantly improve the performance of de-spreading algorithm under the circumstance of limited spreading length, and hence, increase the communication efficiency.

关键词： OFDM Channel estimation Matching pursuit algorithms Feedback loop Demodulation Dictionaries Underwater acoustics

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：