检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Zhang, Wenchao Fu, Chong Zhu, Mai Cao, Lin Tie, Ming Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China Science and Technology on Space Physics Laboratory Beijing100076 China School of Computer Science University of Auckland New Zealand

The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the object edge information. Inspired by the human annotation process when making instance segmentation datasets, in this paper, we propose Mask Point R-CNN aiming at promoting the neural network’s attention to the object boundary. Specifically, we innovatively extend the original human keypoint detection task to the contour point detection of any object. Based on this analogy, we present an contour point detection auxiliary task to Mask R-CNN, which can boost the gradient flow between different tasks by effectively using feature fusion strategies and multi-task joint training. As a consequence, the model will be more sensitive to the edges of the object and can capture more geometric features. Quantitatively, the experimental results show that our approach outperforms vanilla Mask R-CNN by 3.8% on Cityscapes dataset and 0.8% on COCO dataset. Copyright © 2020, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A class of elliptic mixed boundary value problems with (p,q)-Laplacian: existence, comparison and optimal control

arXiv

引用

arXiv 2023年

作者： Zeng, Shengda Migórski, Stanislaw Tarzia, Domingo A. Zou, Lang Nguyen, Van Thien Guangxi Colleges Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal University Yulin537000 China Department of Mathematics Nanjing University Jiangsu Nanjing210093 China Jagiellonian University in Krakow Faculty of Mathematics and Computer Science ul. Lojasiewicza 6 Krakow30348 Poland College of Applied Mathematics Chengdu University of Information Technology Sichuan Province Chengdu610225 China Jagiellonian University in Krakow Chair of Optimization and Control ul. Lojasiewicza 6 Krakow30348 Poland Depto. Matemática FCE Universidad Austral Paraguay 1950 RosarioS2000FZF Argentina CONICET Argentina School of Mathematics and Computational Science Xiangtan University Hunan Province Xiangtan City210000 China Department of Mathematics FPT University Education zone Hoa Lac High Tech Park Km29 Thang Long Highway Thach That ward Hanoi Viet Nam

The paper deals with two nonlinear elliptic equations with (p, q)-Laplacian and the Dirichlet-Neumann-Dirichlet (DND) boundary conditions, and Dirichlet-Neumann-Neumann (DNN) boundary conditions, respectively. Under mild hypotheses, we prove the unique weak solvability of the elliptic mixed boundary value problems. Then, a comparison and a monotonicity results for the solutions of elliptic mixed boundary value problems are established. We examine a convergence result which shows that the solution of (DND) can be approached by the solution of (DNN). Moreover, two optimal control problems governed by (DND) and (DNN), respectively, are considered, and an existence result for optimal control problems is obtained. Finally, we provide a result on asymptotic behavior of optimal controls and system states, when a parameter tends to *** Codes 35J25, 35J66, 35J92, 49J20, 35Bxx © 2023, CC BY.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Observability Enhancement of the Target Tracking Model Based on Infrared Semi-strapdown Seeker

Observability Enhancement of the Target Tracking Model Based...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Peng Siting Zhao Qian Ma Yichao Xu Cheng Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory The Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781728137933

As an important device for target interception, The seeker is used to search, recognize and track the target autonomously. Infrared semi-strapdown seekers are widely used in applications due to their low cost and small size. However, one non-negligible disadvantage of semi-strapdown infrared seekers is that the observability of target tracking model is poor, especially for the interception of high-speed maneuvering weapons. In this paper, the target tracking model ( i.e., the filtering estimation model) based on the infrared simi-strapdown seeker is established. The observability of the target tracking model is analyzed and the evaluation method of the observability is studied. Simulation results show that the observability of the filtering estimation model can be improved by increasing the relative motion between missile and target which results in faster changes of the line-of-sight (LOS) angle. According to the results on the observability analysis, the desired trajectory is obtained through the design of proper guidance law. Nonlinear filtering algorithm is also introduced for the trajectory design. Simulation experiments are conducted for the integrated filtering and guidance, and simulation results illustrate the effectiveness of the proposed observability enhancement method.

关键词： Observability Missiles Filtering Estimation Mathematical model Target tracking Navigation

来源：评论

学校读者我要写书评

暂无评论

Motion Parallax Estimation for Ultra Low Altitude Obstacle Avoidance

Motion Parallax Estimation for Ultra Low Altitude Obstacle A...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Changqing Wang Xinkai Liang Shan Zhang Chao Shen Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781728137933

By making full use of the curvature of the earth and ground clutter, the ultra-low altitude flight technique can significantly increase the difficulty of detecting and intercepting unmanned aerial vehicles (UAVs), and improve their penetration probabilities. However, unpredicted static/dynamic obstacles seriously threaten the flight safety of the ultra-low altitude UAVs. Therefore, fine autonomous spatial perception capability is essential for ultra-low altitude UAVs with limited loads and computing resources to avoid obstacles. To solve the difficult problem of spatial perception for ultra-low altitude obstacle avoidance, a motion parallax estimation algorithm is proposed by combing the deep learning and the epipolar geometry in this paper. By utilizing the deep neural network, the end-to-end mapping relationship from sequence images to depth values of pixels is constructed for spatial perception. At the same time, to overcome the interference caused by the image consistency hypothesis, the loss function is constructed based on the 3D geometric information of the scene rather than the re-projection error between images. Finally, the proposed algorithm is evaluated on the KITTI dataset and infrared image dataset to verify its effectiveness and generalization.

关键词： Motion parallax Deep learning Epipolar geometry component Motion Parallax Space Perception flight safety Unmanned Aerial Vehicle Obstacle avoidance Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

A survey of few shot learning based on intelligent perception

引用

Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica 2020年 41卷

作者： Song, Chuang Zhao, Jiajia Wang, Kang Liang, Xinkai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China School of Computer and Technique Fudan University Shanghai200433 China

Few-shot learning refers to using only a small amount of supervision information of the target class to train the machine learning model. Due to its practical values, recent advances in few-shot learning by academia and industry have made significant contributions. However, there were few reviews on this issue in China. This paper systematically summarizes and explores the few-shot learning algorithms and the object detection algorithms based on few-shot learning. Firstly, the problem definition of few-shot learning is given, and its connections with other classic machine learning problems are also enumerated. Meanwhile, the theoretical challenges of the problem of few-shot learning are explained. Then, we summarize the image classification based on few-shot learning, and analyze its representative works. Based on this, we focus on the problem of few-shot object detection, especially the problem of zero-shot object detection, and analyze the existing research works in detail. Finally, we look forward to the future development of few-shot learning in terms of problem setting, theoretical research, implementation technology, and application scenarios based on the advantages and disadvantages of the existing methods. It is expected to provide inspirations for the subsequent research works in this field. © 2020, Beihang University Aerospace Knowledge Press. All right reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Development of Sheet Palletizing Manipulator Based on Multi-link Mechanism

Research Square

引用

Research Square 2020年

作者： Chen, Zhihua Wang, Shoukun Liu, Quan Wang, Junzheng Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Key Laboratory of Servo Motion System Drive and Control Ministry of Industry and Information Technology School of Automation Beijing Institute of Technology Beijing100081 China New Energy Laboratory College of Mechanical and Electrical Engineering Beijing Information Science and Technology University Beijing100192 China

In view of the disadvantages of Traditional tandem joint type thin-plate palletizing robots using push-down adsorption sorting, such as moving path complexity, large occupied space, joint error stack and low end control precision, a novel multi-link mechanism thin-plate palletizing robot is developed. The kinematics analysis is carried out based on the analysis of the overall structure for the manipulator, a genetic algorithm based on the stroke speed ratio K, the transmission angle γ and the four-bar size is proposed to realize the optimal design of the four-link rocker arm mechanism. Secondly, a finite element based overall structure analysis method is proposed, which obtains the most affected part of the vibration process of a manipulator and performs load verification to prevent early warning and reference of faults caused by mechanical resonance. To solve the control problem of nonlinear strongly coupled dynamic systems, an iterative learning fuzzy adaptive control algorithm is proposed to achieve the smooth running of the manipulator and the high-precision tracking of the end centroid trajectory. The experimental results verify the feasibility and effectiveness of the proposed multi-link controllable thin-plate palletizing manipulator's overall structural design and iterative learning control method, which is well applied in practical engineering. © 2020, CC BY.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Brøsted acidic pyridinium-based ILs catalyzed the selective dimerization of isobutene: Performance and in-situ NMR study

引用

Molecular Catalysis 2020年 482卷

作者： Yu, Xiaojia Liu, Ying Wang, Hui Cheng, Weiguo Wu, Youqing Zhang, Suojiang CAS Key Laboratory of Green Process and Engineering State Key Laboratory of Multiphase Complex System Beijing Key Laboratory of Ionic Liquids Clean Process Institute of Process Engineering Chinese Academy of Sciences Beijing100190 China Department of Chemical Engineering for Energy Resources East China University of Science and Technology Shanghai200237 China

Brøsted acidic pyridinium-based ILs of [NS][CF3SO3] and [NS][HSO4] have been synthesized for oligomerization of isobutene with the excellent conversion of 92.8% and the good selective dimerization at the temperature of below 100 °C. Hydroxyl-containing materials, especially ethanol, could facilitate catalytic activities to excellent conversions of isobutene and 84.2% selectivity of diisobutene. [NS][CF3SO3] could be recovered by a simple liquid-to-liquid separation and reused more than ten times without obvious loss of catalytic activities. The formation process of oligomers has been examined by in-situ NMR spectroscopy, and a step-by-step generation process of carbonium ions varying from C4+, C8+ to C12+ was proposed. The work behaves the significance of constructing a better catalysis system for highly selective dimerization of isobutene, and potential being scaled-up for industrialization. © 2019 Elsevier B.V.

关键词： Dimerization

来源：评论

学校读者我要写书评

暂无评论

Time-resolved arpes of excitons in an atomically thin semiconductor 22

Time-resolved arpes of excitons in an atomically thin semico...

引用

22nd International Conference on Ultrafast Phenomena, UP 2020

作者： Madéo, Julien Man, Michael K.L. Sahoo, Chakradhar Campbell, Marshall Pareek, Vivek Wong, E. Laine Al Mahboob, Abdullah Chan, Nicholas S. Karmakar, Arka Mariserla, Bala Murali Krishna Li, Xiaoqin Heinz, Tony F. Cao, Ting Dani, Keshav M. Femtosecond Spectroscopy Unit Okinawa Institute of Science and Technology 1919-1 Tancha Onna-son Okinawa904-0495 Japan Physics Department Center for Complex Quantum System The University of Texas at Austin AustinTX78712 United States Department of Physics Indian Institute of Technology Jodhpur Rajasthan342037 India Department of Applied Physics Stanford University 348 Via Pueblo Mall StanfordCA94305 United States Slac National Accelerator Laboratory Menlo ParkCA94720 United States Department of Materials Sciences and Engineering University of Washington SeattleWA98195 United States

We use a table-top time-resolved ARPES based on a MHz XUV source to directly observe direct and momentum-forbidden excitons in the full first Brillouin zone of WSe2 monolayer and measure their ultrafast dynamics. ... 详细信息

ISBN: (纸本)9781557528209

关键词： Excitons

来源：评论

学校读者我要写书评

暂无评论

Generating infrared image from visible image using Generative Adversarial Networks

Generating infrared image from visible image using Generativ...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Lei An Jiajia Zhao Huijun Di School of Computer Science & Technology Beijing Institute of Technology Beijing China Science and Technology on Complex System Control and Intelligent Agent Coorperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781728137933

Infrared images have properties that are unaffected by illumination compared to visible images, object can be clearly recognized at day or night. Therefore, it is a better choice to use infrared images when training deep learning algorithms in unmanned systems. However, how to obtain a large number of infrared images makes it possible to train deep learning algorithm, which is the focus of our attention. In contrast to difficulties in direct shooting, computer simulations can generate large infrared images from visible images. But models that are trained on simulated data usually do not translate well to real scenarios. To bridge the domain gap between simulated and real infrared images, we exploit recent advances in paired image-to-image translation. We extend Pixel2Pixel to generate infrared image from visible image and propose a novel way of multilayer semantic information fusion, which significantly improves the quality of generated images. Finally, the image generated by our proposed PixelPro network is almost consistent with the real image distribution, achieved the purpose of expanding the dataset.

关键词： Image translation Infrared image Generative adversarial networks Infrared imaging Visible Imagery images Infrared radiation Information fusion

来源：评论

学校读者我要写书评

暂无评论

Dynamic Phase Enabled Topological Mode Steering in Composite Su-Schrieffer-Heeger Waveguide Arrays

arXiv

引用

arXiv 2024年

作者： Tang, Min Pang, Chi Saggau, Christian N. Dong, Haiyun Lee, Ching Hua Thomale, Ronny Klembt, Sebastian Fulga, Ion Cosma Van Den Brink, Jeroen Vaynzof, Yana Schmidt, Oliver G. Wang, Jiawei Ma, Libo Leibniz Institute for Solid State and Materials Research Dresden Helmholtzstraße 20 Dresden01069 Germany Key Laboratory of Photochemistry Institute of Chemistry Chinese Academy of Sciences Beijing100190 China Department of Physics National University of Singapore Singapore117551 Singapore Institut für Theoretische Physik und Astrophysik Universität Würzburg Würzburg97074 Germany Technische Physik Physikalisches Institut Wilhelm Conrad Roentgen-Research Center for Complex Material System Universität Würzburg Würzburg D-97074 Germany Institute for Theoretical Physics Technische Universität Dresden Dresden01069 Germany Technical University of Dresden Nöthnitzer Str. 61 Dresden01187 Germany TU Chemnitz Chemnitz09126 Germany TU Chemnitz Chemnitz09107 Germany School of Science TU Dresden Dresden01062 Germany School of Electronic and Information Engineering Harbin Institute of Technology Guangdong Shenzhen518055 China

Topological boundary states localize at interfaces whenever the interface implies a change of the associated topological invariant encoded in the geometric phase. The generically present dynamic phase, however, which is energy and time dependent, has been known to be non-universal, and hence not to intertwine with any topological geometric phase. Using the example of topological zero modes in composite Su-Schrieffer-Heeger (c-SSH) waveguide arrays with a central defect, we report on the selective excitation and transition of topological boundary mode based on dynamic phase-steered interferences. Our work thus provides a new knob for the control and manipulation of topological states in composite photonic devices, indicating promising applications where topological modes and their bandwidth can be jointly controlled by the dynamic phase, geometric phase, and wavelength in on-chip topological devices. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

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：