检索结果-内蒙古大学图书馆

2021 China Automation Congress, CAC 2021

作者： Liu, Yang Wang, Congqing Zhou, Yongjun College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Science and Technology on Near-Surface Detection Laboratory Wuxi China

ISBN: (纸本)9781665426473

Catering the continuous development of intelligent technology and the wide application prospects of unmanned aerial vehicles (UAVs), the target tracking technology will be applied in future combat. In order to deal with the complex battlefield environment and the scale change of the target during tracking, an improved scale-adaptive correlation filter algorithm based on fusion features is proposed to realize the tracking of military personnel. First, the fast histogram of oriented gradient (FHOG) features and the local binary pattern (LBP) features are adaptively weighted and fused to achieve the target location. Then the translation filter of kernelized correlation filters(KCF) and the scale filter of discriminative scale space tracking(DSST) are combined to comprehensively improve the calculation speed and scale adaptation performance of the algorithm and track the target in time. The experimental results prove the robustness and practicability of the proposed method, which can accurately track military targets in real time. © 2021 IEEE

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Aerial Tracking of Camouflaged People in Woodlands Via Unsupervised Learning

SSRN

引用

SSRN 2023年

作者： Liu, Yang Wang, Congqing Xu, Bin Zhou, Yongjun College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing211106 China Science and Technology on Near-Surface Detection Laboratory Wuxi214000 China

With the widespread use of unmanned aerial vehicles (UAVs) and computer vision, much attention has been devoted to aerial tracking. Previous tracking methods were mostly implemented in clean and well-lit environments, making it challenging to track camouflaged people rapidly and accurately in woodlands. In this work, we develop a novel unsupervised learning framework for camouflaged people aerial tracking (named UCAT) based on transformer. Specifically, a camouflaged people discovery strategy is proposed to rapidly generate training samples from the unlabeled videos captured by the UAV. Dynamic programming is also employed to filter noises to generate smooth candidate frames. To make full use of multi-level feature information, a transformer fusion framework is designed to integrate shallow spatial information and in-depth semantic features. For reducing computing consumption, the spatial attention reduction mechanism is embedded to the multi-head attention for fast tracking. Further, we build a dataset for evaluating the effect of camouflaged people tracking called Cam235, which consists of 85 manually labeled test sequences and over 100k frames of the unlabeled training set. Comprehensive experiments on Cam235-test and popular tracking benchmarks show that the UCAT learned from unlabeled videos performs well in camouflaged people tracking, demonstrating the practical value of the tracker. © 2023, The Authors. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Microstructural analysis and nonlinear optical properties of PP/PA6/Clay composites: a comparative study with and without compatibilizer

引用

Optical and Quantum Electronics 2025年第5期57卷 1-27页

作者： Orshesh, Z. Dehghani, Z. Moghaddasi, M. Bagheri, R. Abrinaei, F. Department of Materials Science and Engineering Ahvaz Branch Islamic Azad University Ahvaz Iran Department of Materials Science and Engineering Central Tehran Branch Islamic Azad University Tehran Iran Department of Physics University of Neyshabur P. O. Box *** Neyshabur Iran National Key Laboratory on Near-Surface Detection School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Department of Materials Science and Engineering Sharif University of Technology P. O. Box 11365-9466 Tehran Iran Department of Physics Central Tehran Branch Islamic Azad University Tehran Iran Department of Physics East Tehran Branch Islamic Azad University Tehran Iran

Ternary polypropylene/polyamide6/organoclay composites were successfully synthesized through a melt-mixing process, with and without a compatibilizer. The chemical-bond, structural, and morphological characteristics of composites were thoroughly investigated utilizing Fourier-transform infrared spectroscopy, wide-angle X-ray diffraction, and scanning electron microscopy analyses. The morphological investigations showed that the addition of a compatibilizer to the composite leads to a reduction in the size of the dispersed PA6/clay domains and a decrease in the distance between them due to the formation of a PP-g-PA copolymer at the interface, which improves compatibility between the PP and PA6 phases. Furthermore, the differential scanning calorimetry technique was employed to assess the crystallization and thermal action of the composites. The results revealed that the addition of a compatibilizer resulted in a slight increase in the crystallization temperature of PP and a reduction in the overall crystallinity of the composite, attributed to the compatibilizer’s interaction with both the clay and PA6/clay islands, limiting PP chain mobility and hindering crystallization. The band gap energies were determined in a range of 4.17–4.34 eV by diffuse reflectance spectroscopy and utilizing the Tauc method. Notably, this study marks the first instance of exploring the nonlinear optical properties of these composites. This was achieved by employing Z-scan technique by subjecting the samples to a continuous-wave Nd:YAG laser functioning at a wavelength of 532 nm. A positive nonlinearity of the order of 10–8 cm2W−1 was observed across all samples studied. Particularly noteworthy was the significant enhancement in nonlinear refractive index and absorption coefficients for polypropylene/polyamide6/organoclay ternary composites upon the addition of the compatibilizer. These findings strongly indicate the potential of these composites for applications in nonlinear optical devic

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Multi-band Phase-Switched-Screen based on Artificial Magnetic Conductor surface 13

Reconfigurable Multi-band Phase-Switched-Screen based on Art...

引用

13th International Conference on Microwave and Millimeter Wave technology, ICMMT 2021

作者： Ling, Guoping Gong, Weijie Chang, Yumei Wang, Lin Science And Technology On Near-Surface Detection Laboratory Wuxi China Nanjing University Of Posts And Telecommunications College Of Electric And Optical Engineering Nanjing China

ISBN: (纸本)9781665434379

In this paper, by employing the PIN diodes to the ultra-thin Artificial Magnetic Conductor (AMC), a new kind of reconfigurable multi-band phase switched screen (PSS) was proposed. By control the switch sequences between "OFF"and "ON"states in different binary switch form (code "0"represents the state of "OFF", and code"1"represents "ON"state) on the PIN diodes in the PSS, the reflection phase from the AMC surface at the resonating frequencies could change between in-phase and out-of-phase alternatively. If the sequences were properly chosen, then the incident electromagnetic would be reflected after digital modulation. And therefore, most of the energy of the reflected wave would move out from the working band of the radar receiver, and only small amount of interference signal fall into the working band, and then lead to radar stealth. Meanwhile, the simulation results verify the feasibility of the proposed design. © 2021 IEEE.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Intelligent tailoring of a broadband orbital angular momentum comb towards efficient optical convolution

引用

Photonics Research 2025年第5期 1148-1157页

作者： SHIYUN ZHOU LANG LI YISHU WANG LILIANG GAO ZHICHAO ZHANG CHUNQING GAO SHIYAO FU School of Optics and Photonics Beijing Institute of Technology Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education Key Laboratory of Information Photonics Technology Ministry of Industry and Information Technology National Key Laboratory on Near-surface Detection

Due to the high-dimensional characteristics of photon orbital angular momentum (OAM), a beam can carry multiple OAMs simultaneously thus forming an OAM comb, which has been proved to show significant potential in both classical and quantum photonics. Tailoring broadband OAM combs on demand in a fast and accurate manner is a crucial basis for their application in advanced scenarios. However, obtaining phase-only gratings for the generation of arbitrary desired OAM combs still poses challenges. In this paper, we propose a multi-scale fusion learning U-shaped neural network that encodes a phase-only hologram for tailoring broadband OAM combs on-demand. Proof-of-principle experiments demonstrate that our scheme achieves fast computational speed, high modulation precision, and high manipulation dimensionality, with a mode range of-75 to+75,an average root mean square error of 0.0037, and a fidelity of 85.01%, all achieved in about 30 ***, we utilize the tailored broadband OAM combs in conducting optical convolution calculation,enabling vector convolution for arbitrary discrete functions, showcasing the extended capability of our *** work opens, to our knowledge, new insight for on-demand tailoring of broadband OAM combs, paving the way for further advancements in high-dimensional OAM-based applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-space-bandwidth product characterization of metalenses with Fourier ptychographic microscopy

arXiv

引用

arXiv 2024年

作者： Zheng, Chuanjian Wang, Wenli Ji, Yanfang Hu, Yao Zhang, Shaohui Hao, Qun School of Optics and Photonics Beijing Institute of Technology Beijing100081 China National Key Laboratory on Near-Surface Detection Beijing10012 China Tianjin H-Chip Technology Group Corporation Tianjin300480 China

Large numerical aperture (NA) and large aperture metalenses have shown significant performance and abundant applications in biomedical and astronomical imaging fields. However, the high space-bandwidth product (SBP) requirements for measuring the phase of these metalenses, characterized by small phase periods and large apertures, have resulted in no effective techniques for sufficient characterization. In this paper, we propose a high SBP phase characterization technique using Fourier ptychographic microscopy (FPM), enabling a high spatial resolution and wide field of view simultaneously. To demonstrate the feasibility and effectiveness of this technique, we achieve a high SBP (4.91 megapixels) measurement and characterization for focusing and focusing vortex metalenses, quantitatively displaying the effect of fabrication error on their typical optical performance. Furthermore, we characterize the aberration type and amount of wavefront deviations caused by fabrication. We also analyze compensation methods for different aberrations based on the wavefront characterization results, providing a targeted alignment strategy for optimizing overall optical system performance. We believe that our high SBP characterization technique cannot only help to improve metalens design but also optimize its fabrication processing, which will pave the way for the diversified applications of metalenses. Copyright © 2024, The Authors. All rights reserved.

关键词： Aberrations

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Water Ecological Carrying Capacity Based on Natural Resource Endowment Characteristics: A Case Study of Yicheng City 12

Evaluation of Water Ecological Carrying Capacity Based on Na...

引用

12th Academic Conference of Geology Resource Management and Sustainable Development, GRMSD 2024

作者： Jiang, Xingzheng Liu, Xiaojing Li, Xuanhui Zeng, Guanzhong Center for Geophysical Survey China Geological Survey Lang Fang065000 China Technology Innovation Center for Earth Near Surface Detection China Geological Survey Lang Fang065000 China Key Laboratory of Coupling Process and Effect of Natural Resources Elements MNR Beijing100055 China Comprehensive Observation and Research Station for Hubei Xiangyang Natural Resource Elements Xiangyang441000 China

ISBN: (纸本)9798331314545

Water is the source of life, the foundation of ecology and the key to production. In Yicheng City, a typical county city in China's watersheds, the concept of water ecological carrying capacity and the assessment method are proposed by combining the general situation of the study area and the relevant research bases at home and abroad, taking into account the whole elements of natural resources. Determination of factor weights using a combined hierarchical analysis-entropy weighting approach. Deriving water ecological carrying capacity evaluation results suitable for adoption in rural China. Results and analysis of water ecological carrying capacity zoning and grading in Yicheng City. There are 223 village units in Yicheng City, and considering the spatial scarcity of the indicator factors, the study area is divided into four categories of village-level evaluation units, namely, the ideal carrying, preferable carrying, critical overloading and overloading. The proportion of the area is 9.56%, 25.24%, 46.65% and 18.55% respectively, providing scientific reference and data support for the construction of the "Thousand Villages Demonstration and Ten Thousand Villages Improvement" project and the realization of rural revitalization and sustainable development. © 2024 Proceedings of the 12th Academic Conference of Geology Resource Management and Sustainable Development, GRMSD 2024. All rights reserved.

关键词： Sustainable city

来源：评论

学校读者我要写书评

暂无评论

Study on the Spatiotemporal Pattern of Land Use Change in Han River Basin 12

Study on the Spatiotemporal Pattern of Land Use Change in Ha...

引用

12th Academic Conference of Geology Resource Management and Sustainable Development, GRMSD 2024

作者： Yu, Peng Zeng, Guanzhong Liu, Xiaojing Li, Xuanhui Center for Geophysical Survey China Geological Survey Lang Fang065000 China Technology Innovation Center for Earth Near Surface Detection China Geological Survey Lang Fang065000 China Key Laboratory of Coupling Process and Effect of Natural Resources Elements MNR Beijing100055 China Comprehensive Observation and Research Station for Hubei Xiangyang Natural Resource Elements Xiangyang441000 China

ISBN: (纸本)9798331314545

In response to the frequent changes in land use and prominent conflicts between people and land in the Han River Basin, this study takes the Han River Basin as the research area, based on GIS technology, and uses the land use dataset from 2000 to 2022 to comprehensively utilize the land transfer matrix and standard deviation ellipse analysis to study the spatiotemporal characteristics of land use changes in the research area. The results show that from 2000 to 2022, the cropland area in the study area decreased the most, while the construction land area increased significantly;The spatial change of land use is inclined with the northwest to Dingnan direction as the main axis, concentrated in the southeast and central regions. The research results can provide scientific basis for the national spatial planning and sustainable development of central cities in the Han River Basin. © 2024 Proceedings of the 12th Academic Conference of Geology Resource Management and Sustainable Development, GRMSD 2024. All rights reserved.

关键词： Abiotic

来源：评论

学校读者我要写书评

暂无评论

Application of update lifting morphological wavelet and non-negative matrix factorization for wheeled and tracked vehicles classification 9

Application of update lifting morphological wavelet and non-...

引用

9th International Conference on Environmental and Engineering Geophysics, ICEEG 2020

作者： Ding, Kai Du, Kai Qi, Xiaogang Xu, Yuelin Cui, Junqi Science and Technology on Near -Surface Detection Laboratory Wuxi214035 China 31104 Troops Nanjing210007 China Xidian University Xi'an710071 China

This paper presents an available scheme based on update lifting morphological wavelet (ULMW) and Non-negative matrix factorization (NMF) for wheeled and tracked vehicles classification. The ULWM algorithm which utilizes the update operator, means the morphological filter to replace the linear filter can preserve the impulsive shape details in seismic signal. Meanwhile the NMF method can reduce the computation cost. The traditional linear wavelet analysis and statistical analysis are compared with the presented scheme. Experimental results demonstrate that the presented scheme achieves a promising performance on extracting impulsive features of seismic signal and recognizing ground moving target. © Published under licence by IOP Publishing Ltd.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Candidate Evaluation with Multimodal Data-Driven for Recruitment 27th

Candidate Evaluation with Multimodal Data-Driven for Recru...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wu, Xing Liu, Kehong Wang, Jianjia Yao, Junfeng Deng, Bin Lv, Rongqi Song, Jun School of Computer Engineering and Science Shanghai University Shanghai200444 China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai200444 China School of AI and Advanced Computing XJTLU Entrepreneur College Xi’an Jiaotong-Liverpool University Suzhou215412 China CSSC Seago System Technology Co. Ltd. Shanghai200010 China Science and Technology on Near-Surface Detection Laboratory Jangsu Wuxi214035 China Department of Geography Hong Kong Baptist University 999077 Hong Kong

ISBN: (纸本)9783031781858

In the field of intelligent recruitment, automated resume matching and non-contact interviews have significantly improved the efficiency of companies in finding suitable candidates. This corresponds to the techniques of person-job matching and AI interviews. However, current person-job matching methods lack substantial data support, while AI interview methods struggle to integrate deep information from multimodal data and provide comprehensive evaluations of candidates’ responses. To address these challenges, we propose a multimodal data-driven person-job evaluation model, comprising two key stages: a person-job matching method based on graph attention and a multimodal AI interview method. Using a dual-perspective graph neural network approach, we accomplish the screening of candidates and positions. In the second stage, we conduct a comprehensive evaluation of candidates’ interview performance based on text, audio, and image modalities, providing a more objective, consistent, and efficient interview assessment method. Experimental results demonstrate that our person-job matching method surpasses current popular techniques and effectively transfers features to the next stage. In our multimodal AI interview method, we achieve accurate scoring of candidate responses, assessment of intonation stress levels, and inference of their Big Five personality traits, comprehensively evaluating candidates from multiple perspectives. This confirms the superiority and efficiency of our approach. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Graph neural networks

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：