检索结果-内蒙古大学图书馆

2018 2nd International Symposium on Resource Exploration and Environmental science, REES 2018

作者： Ren, Zhiwei Wu, Lingda Department of Graduate Management Space Engineering University Beijing101416 China Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing101416 China

Because hyperspectral images have the characteristics of high correlation between bands and strong information redundancy, the reduction in dimension of hyperspectral images is an important step in the pre-processing of hyperspectral images. Band selection can preserve the physical meaning of the original data while reducing dimension and has application in many aspects. Affinity Propagation Clustering (AP) is a clustering method proposed by Fray et al. in 2007. AP clusters based on the correlation between data points and treats all data points as potential cluster centers. This paper proposes a band selection method based on AP clustering, which introduces wavelet transform into the calculation of similarity and preference value in clustering algorithm. The dimensionality reduction results are input into the minimum distance classifier for classification, and the classification accuracy was calculated. The dataset is validated by the Indiana Pines dataset. The experimental results verify the effectiveness of the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Mechanical Analysis and Performance Optimization for the Lunar Rover’s Vane-Telescopic Walking Wheel

引用

Engineering 2020年第8期6卷 936-943页

作者： Lu Yang Bowen Cai Ronghui Zhang Kening Li Zixian Zhang Jiehao Lei Baichao Chen Rongben Wang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical EngineeringTianjin University of TechnologyTianjin 300384China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of TechnologyTianjin 300384China Guangdong Key Laboratory of Intelligent Transportation System School of Intelligent Systems EngineeringSun Yat-sen UniversityGuangzhou 510275China College of Transportation Jilin UniversityChangchun 130025China Department of Mechanical Science and Engineering Tokyo Institute of TechnologyTokyo 152-8550Japan Armour College of Engineering Illinois Institute of TechnologyChicagoIL 60616USA China Academy of Space Technology Beijing 100029China

It is well-known that optimizing the wheel system of lunar rovers is ***,this is a difficult task due to the complex terrain of the moon and limited resources onboard lunar *** this study,an experimental prototype was set up to analyze the existing mechanical design of a lunar rover and improve its ***,a new vane-telescopic walking wheel was proposed for the lunar rover with a positive and negative quadrangle suspension,considering the complex terrain of the ***,the performance was optimized under the limitations of preserving the slope passage and minimizing power *** was achieved via analysis of the wheel force during ***,the effectiveness of the proposed method was demonstrated by several simulation *** newly designed wheel can protrude on demand and reduce energy consumption;it can be used as a reference for lunar rover development engineering in China.

关键词： Intelligent vehicle Vane-telescopic walking wheel Performance optimization Vane spring Lunar rover

来源：评论

学校读者我要写书评

暂无评论

An Approach on Visual Detecting Multi-Targets in the Unstructured and Complex Scenes Based on RGB-D Images

An Approach on Visual Detecting Multi-Targets in the Unstruc...

引用

Automation, Control and Robotics Engineering (CACRE), International Conference on

作者： Qimeng Tan Yikun Sun Pengfei Xin Yimin Lin Chao Ma Xinyu Wang Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing Institute of Spacecraft System Engineering Propellant Injection Laboratory Beijing Special Engineering Design and Research Institute Institute of Optical Communication &Optoelectronics Beijing University of Posts &Telecommunications School of Instrument Science and Optoelectronic Engineering Beijing Information Science and Technology University

ISBN: (数字)9781728198880

ISBN: (纸本)9781728198897

The technology of detecting and identifying multitarget is of significance for robotic visual navigation within the unknown, unstructured, complex scenes, whose result could be considered as important references of 3 D map building and path planning for mobile robot. Traditional algorithms of target detection can be applied to 2 D images without depth information generally, which is disturbed by few factors such as illumination, view and scale easily. Therefore, an approach on visual detecting multi-target of unstructured and complex scenes based on RGBD images is proposed in this article to solve the above problem, which is composed of extracting descriptor of rotation and scale invariance feature, local encoding of targets, random ferns classifier training, Hough map generation, Hough voting theoretical model and local maximum search. Experimental results have shown that the proposed approach reduce the calculation of extracting and matching local feature, improve the accuracy of object recognition and detection in unknown complex environments, be capable of well robust against few disturbing factors i.e. rotation, scale, illumination, occlusion and non-rigid body deformation.

关键词： Robotic Visual Navigation RGB-D Image Target Detection RFC(Random Ferns Classifier) RSI-LBF(Rotation and Scale Invariance-Local Binary Feature)

来源：评论

学校读者我要写书评

暂无评论

DPNet: Dynamic Pooling Network for Accurate and Efficient Size-Aware Tiny Object Detection

引用

IEEE Internet of Things Journal 2025年

作者： Gong, Luqi Chen, Haotian Chen, Yikun Yao, Tianliang Li, Chao Zhao, Shuai Han, Guangjie Beijing University of Posts and Telecommunications School of Computer Science Beijing China Zhejiang Lab Research Center for Space Computing System Hangzhou China Southwest Jiaotong University SWJTU-LEEDS Joint School Chengdu China LTD Guangdong Zhiyun City construction Technology Co Zhuhai China Tongji University College of Electronic and Information Engineering Department of Control Science and Engineering Shanghai China Hohai University Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education China

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed down-sampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which will be used to decrease the resolution of feature map in backbone. Thus, we achieve input-aware down-sampling. We design an Adaptive Normalization Module (ANM) to make a unified detector well compatible with different dfs. At the same time, we also design a guidance loss to supervise the predictor’s training. DPNet realizes the dynamic allocation of computing resources to trade off detection accuracy and efficiency through this. Experiments on the TinyCOCO and TinyPerson datasets show that our DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection *** code will be made publicly available. © 2014 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

DPNet: Dynamic Pooling Network for Tiny Object Detection

arXiv

引用

arXiv 2025年

作者： Gong, Luqi Chen, Haotian Chen, Yikun Yao, Tianliang Li, Chao Zhao, Shuai Han, Guangjie School of Computer Science Beijing University of Posts and Telecommunications Beijing China Research Center for Space Computing System Zhejiang Lab Hangzhou China SWJTU-LEEDS Joint School Southwest Jiaotong University Chengdu China Guangdong Zhiyun City construction Technology Co. LTD Zhuhai China Department of Control Science and Engineering College of Electronic and Information Engineering Tongji University Shanghai China Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education Hohai University China

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed downsampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which will be used to decrease the resolution of feature map in backbone. Thus, we achieve input-aware downsampling. We design an Adaptive Normalization Module (ANM) to make a unified detector well compatible with different dfs. At the same time, we also design a guidance loss to supervise the predictor’s training. DPNet realizes the dynamic allocation of computing resources to trade off detection accuracy and efficiency through this. Experiments on the TinyCOCO and TinyPerson datasets show that our DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection *** code will be made publicly available. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Ray Tracing Based Sub-6 GHz Wireless Channel Characteristics Analysis in Underground Garage Environments

Ray Tracing Based Sub-6 GHz Wireless Channel Characteristics...

引用

IEEE International Conference on Electronics and Communication Engineering (ICECE)

作者： Xiaole Li Cuiping Zhang Jian Sun Wensheng Zhang Cheng-Xiang Wang Shandong Provincial Key Lab of Wireless Communication Technologies School of Information Science and Engineering Shandong University Qingdao China Shandong Provincial Key Lab of Wireless Communication Technologies Shandong University Qingdao China The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics Nanjing China National Mobile Communications Research Laboratory School of Information Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories Nanjing China

ISBN: (纸本)9781728188577

Indoor hot spots is a major deployment scenario of the fifth generation (5G) network. In the indoor scenario, the radio wave propagation characteristics of underground garages are still not fully understood. In addition, Sub-6 GHz band is the main frequency band used in domestic 5G networks recently. This paper mainly uses ray tracing to study the wireless channel characteristics in the scenario of underground garage under Sub6 GHz frequency band. Firstly, a three-dimensional (3D) simulation scenario is built, and the channel simulation is carried out at 3.5 GHz frequency band. According to the simulation data, the results shows that the path loss index is smaller than that in the 3GPP indoor scenario. Then, the channel data of Sub-6 GHz continuous frequency band is simulated at 500 MHz interval, the influence of material properties on channel characteristics is studied. We find that the path loss increases while the distance between the transmitter (Tx) and receiver (Rx) increases, and the change is obvious at a long distance with increasing frequency.

关键词： Wireless communication Solid modeling Three-dimensional displays 5G mobile communication Radio transmitters Receivers Ray tracing

来源：评论

学校读者我要写书评

暂无评论

Erratum: Strong evidence of low levels of solar activity during the Maunder Minimum

引用

Monthly Notices of the Royal Astronomical Society 2022年第4期512卷 5715-5716页

作者： Carrasco, V M S Hayakawa, H Kuroyanagi, C Gallego, M C Vaquero, J M Departamento de Física Universidad de Extremadura E-06006 Badajoz Spain Instituto Universitario de Investigación del Agua Cambio Climático y Sostenibilidad (IACYS) Universidad de Extremadura E-06006 Badajoz Spain Institute for Advanced Researches Nagoya University Nagoya 4648601 Japan Institute for Space-Earth Environmental Research Nagoya University Nagoya 4648601 Japan UK Solar System Data Centre Space Physics and Operations Division RAL Space Science and Technology Facilities Council Rutherford Appleton Laboratory Harwell Oxford Didcot Oxfordshire OX11 0QX UK Nishina Centre Riken Wako 3510198 Japan Graduate School of Arts and Sciences University of Tokyo Tokyo 1538902 Japan Departamento de Física Universidad de Extremadura E-06800 Mérida Spain

来源：评论

学校读者我要写书评

暂无评论

The Architecture of Digital system Model for systems-of-systems Engineering

The Architecture of Digital System Model for Systems-of-Syst...

引用

Chinese Automation Congress (CAC)

作者： Xinghai Gao Yaqi Zhang Zhuoqi Wang Institute of Unmanned System Beihang University Beijing China Science and Technology on Complex Systems Simulation Laboratory Beijing China

The rapid increasing challenges of modeling and simulation for systems-of-systems Engineering (SoSE) is to deal with their large-scale and complexity of heterogeneous and inter-dependent constituent systems. Typically, the method of structural modeling provides a thorough understanding of the composition and operation of different elements, but loses sight of the dynamic characteristics of the systems or components. To make a comprehensive analysis of the system-of-systems (SoS), the solution of behavior modeling will be more important to adapt to the evolving of the SoS, which focus on understanding the constituent systems and their relationships, and evaluating changes of the constituent system, and continuously responding to the new requirements and options of SoS. This paper discusses how to support the application of modeling and simulation (M&S) based on the framework of SysML to describe the architecture and capability of SoS, and combined with the process and activities of model-based system engineering (MBSE).

关键词： Unified modeling language Object oriented modeling Analytical models Digital systems Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Direct Measurements of Synchrotron-Emitting Electrons at Near-Sun Shocks

arXiv

引用

arXiv 2024年

作者： Jebaraj, Immanuel Christopher Agapitov, O.V. Gedalin, M. Vuorinen, L. Miceli, M. Vainio, R. Cohen, C.M.S. Voshchepynets, A. Kouloumvakos, A. Dresing, N. Marmyleva, A. Krasnoselskikh, V. Balikhin, M. Mitchell, J.G. Labrador, A.W. Wijsen, N. Palmerio, E. Colomban, L. Pomoell, J. Kilpua, E.K.J. Pulupa, M. Mozer, F.S. Raouafi, N.E. McComas, D.J. Bale, S.D. Department of Physics and Astronomy University of Turku Turku20500 Finland Space Sciences Laboratory University of California BerkeleyCA94720 United States Astronomy and Space Physics Department National Taras Shevchenko University of Kyiv Kyiv03127 Ukraine Department of Physics Ben Gurion University of the Negev Beer-Sheva84105 Israel Department of Physics and Astronomy Queen Mary University of London LondonE1 4NS United Kingdom Dipartimento di Fisica e Chimica E. Segrè Università degli Studi di Palermo Palermo90134 Italy California Institute of Technology PasadenaCA91125 United States Department of System Analysis and Optimization Theory Uzhhorod National University Uzhhorod88000 Ukraine The Johns Hopkins University Applied Physics Laboratory LaurelMD20723 United States University of Helsinki Helsinki00014 Finland LPC2E CNRS UMR 7328 Orléans45071 France University of Sheffield SheffieldS10 2TN United Kingdom Heliophysics Science Division NASA Goddard Space Flight Center GreenbeltMD20771 United States Centre for mathematical Plasma Astrophysics KU Leuven Leuven3001 Belgium Predictive Science Inc. San DiegoCA92121 United States Department of Astrophysical Sciences Princeton University PrincetonNJ08544 United States Physics Department University of California BerkeleyCA94720 United States

In this study, we present the first-ever direct measurements of synchrotron-emitting heliospheric traveling shocks, intercepted by the Parker Solar Probe (PSP) during its close encounters. Given that much of our understanding of powerful astrophysical shocks is derived from synchrotron radiation, these observations by PSP provide an unprecedented opportunity to explore how shocks accelerate relativistic electrons and the conditions under which they emit radiation. The probe’s unparalleled capabilities to measure both electromagnetic fields and energetic particles with high precision in the near-Sun environment has allowed us to directly correlate the distribution of relativistic electrons with the resulting photon emissions. Our findings reveal that strong quasi-parallel shocks emit radiation at significantly higher intensities than quasi-perpendicular shocks due to the efficient acceleration of ultra-relativistic electrons. These experimental results are consistent with theory and recent observations of supernova remnant shocks and advance our understanding of shock physics across diverse space environments. © 2024, CC BY-SA.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Accuracy vs. Efficiency: Achieving both Through Hardware-Aware Quantization and Reconfigurable Architecture with Mixed Precision

Accuracy vs. Efficiency: Achieving both Through Hardware-Awa...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Libo Chang Shengbing Zhang Huimin Du Shiyu Wang Meikang Qiu Jihe Wang School of Computer Science Northwestern Polytechnical University and National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an China School of Electronic Engineering Xi'an University of Posts and Telecommunication Xi'an China School of Computer Science Northwestern Polytechnical University and Engineering Research Center of Embedded System Integration Ministry of Education Xi'an China Texas A&M University-Commerce Texas USA

We propose a hardware/software co-design framework, which leverages hardware-aware quantization and a reconfigurable processor to improve the computational efficiency of convolutional neural networks (CNNs) on tiny IoT devices based on reconfigurable platforms. Firstly, we proposed a multi-objective optimization value function that can weigh accuracy, the size of CNN models, and computational delay, to improve the efficiency of the mixed- precision quantization algorithm based on deep reinforcement learning. Secondly, we propose a reconfigurable CNN processor that can adapt to the computing characteristics of various quantized CNN models, as well as a reconfigurable computing array and an on-chip elastic buffer, to improve the performance and computing efficiency on edge equipment. Finally, we demonstrate the effectiveness of the proposed co-design method through an extensive evaluation of the Ultra96-V2 platform. With respect to the well-known CNNs—VGG-16, ResNet-50, and MobileNet-V2, the experimental result shows that the throughput of 216.6 GOPS, 214.0 GOPS, and 53.6 GOPS, the computing efficiency of 0.63GOPS/DSP, 0.64GOPS/DSP, and 0.24 GOPS/DSP, respectively. In addition, achieving a better optimized trade-off between the computing efficiency and accuracy compared with the recently proposed CNN processor with fixed bit-width and mixed-precision.

关键词： Adaptation models Quantization (signal) Computational modeling Reinforcement learning Throughput system-on-chip Reconfigurable architectures

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：