检索结果-内蒙古大学图书馆

Unsupervised Feature Enrichment and Fidelity Preservation Learning Framework for Skeleton-based Action Recognition

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Li, Chuankun Li, Shuai Gao, Yanbo Gao, Xingyu Chen, Ping Li, Jian Li, Wanqing North University of China State Key Laboratory of Dynamic Testing Technology School of Information and Communication Engineering Taiyuan030051 China Shandong University School of Control Science and Engineering School of Software Jinan250100 China Chinese Academy of Sciences Institute of Microelectronics Beijing100029 China University of Wollongong Advanced Multimedia Research Lab WollongongNSW2522 Australia

Unsupervised skeleton-based action recognition has achieved remarkable progress recently. Existing unsupervised learning methods suffer from severe overfitting problem, and thus small networks are used, significantly reducing the representation capability. To address this problem, the overfitting mechanism behind the unsupervised learning for skeleton-based action recognition is first investigated. It is observed that skeleton is already a relatively high-level and low-dimension feature, but not in the same manifold as the features for action recognition. Simply applying the existing unsupervised learning method tends to produce features that discriminate the different samples rather than action classes, resulting in the overfitting problem. To address this problem, this paper proposes an Unsupervised spatial-temporal Feature Enrichment and Fidelity Preservation (U-FEFP) learning framework to generate rich distributed features that contain all the information of a skeleton sample. A spatial-temporal feature transformation subnetwork is developed using channel-wise topology refinement graph convolutional block and graph convolutional gated recurrent unit block as the basic feature extraction network. The unsupervised Bootstrap Your Own Latent-based learning is utilized to generate rich distributed features, and the unsupervised pretext task-based learning is employed to preserve the information contained in the skeleton. The two unsupervised learning ways are collaborated as U-FEFP to produce robust and discriminative representations. Experimental results on four widely used benchmarks, namely NTU-RGB+D-60, PKU-MMD, NTU-RGB+D-120 and UAV-Human dataset, demonstrate that the proposed U-FEFP obtains the best result compared with the state-of-the-art unsupervised learning methods. © 1991-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

CapUBS: Capsule Network-Based Band Selection for Underwater Hyperspectral Imagery

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Li, Qi Wang, Junwen Zu, Xingyuan Chen, Dan Zhang, Ke Li, Jinghua Northwestern Polytechnical University School of Electronics and Information Xi’an710072 China Xi’an University of Technology School of Automation and Information Engineering Xi’an710048 China Science and Technology on Electromechanical Dynamic Control Laboratory Xi’an China

Underwater hyperspectral imagery (HSI) finds extensive applications in critical domains such as marine target detection. However, spectral offset caused by underwater light propagation presents significant challenges for existing hyperspectral band selection methods, which often fail to capture inter-band correlations in underwater environments effectively. To address this issue, this paper proposes a novel underwater hyperspectral band selection method based on capsule network (CapUBS) designed to mitigate spectral offset variations and reduce redundancy in band selection for underwater HSI. Especially, the dual-stream latent variable encoding module takes the original and averaged spectra as inputs and employs deep feature extraction blocks to capture local details and global semantic features, thereby alleviating spectral variability. The capsule network-based band characterization module utilizes a dynamic routing mechanism to generate digital capsules representing joint multiband features. This module characterizes the multi-dimensional spectral attributes via vector directions and quantifies the relative importance of spectral bands using vector norms. The feature separation factor evaluation module computes the initial band importance ranking to refine the selection process further. It evaluates a feature separation factor to identify key bands with minimal redundancy and high representativeness, resulting in an optimal subset of spectral bands. Finally, the key band feature reconstruction module leverages these selected bands to reconstruct the full-band spectrum accurately. Comprehensive quantitative and qualitative analyses conducted on four classical hyperspectral datasets and underwater hyperspectral experimental datasets demonstrate the superior performance of the proposed method compared to state-of-the-art techniques. © 1980-2012 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

A Point-to-distribution Degeneracy Detection Factor for LiDAR SLAM using Local Geometric Models

A Point-to-distribution Degeneracy Detection Factor for LiDA...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Sehua Ji Weinan Chen Zerong Su Yisheng Guan Jiehao Li Hong Zhang Haifei Zhu Biomimetic and Intelligent Robotics Lab (BIRL) School of Electromechanical Engineer Guangdong University of Technology Guangzhou China JT-Innovation (Guangdong) Intelligent Technology Co. Ltd. Guangdong Key Laboratory of Modern Control Technology Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangzhou China College of Engineering South China Agricultural University China Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Limited by the working principles, LiDAR-SLAM systems suffer from the degeneration phenomenon in environments such as long corridors and tunnels, due to the lack of sufficient geometric features for frame-to-frame matching. The accuracy and sensitivity of existing degeneracy detection methods need to be further improved. In this paper, we propose a novel method for degeneracy detection using local geometric models based on point-to-distribution matching. To obtain an accurate description of local geometric models, an adaptive adjustment of voxel segmentation according to the point cloud distribution and density is designed. The codes of the proposed method is open-source and available at https://***/jisehua/***. Experiments with public datasets and self-build robots were conducted to evaluate the methods. The results exhibit that our proposed method achieves higher accuracy than the other existing approaches. Applying our proposed method is beneficial for improving the robustness of the LiDAR-SLAM systems.

关键词： Point cloud compression Accuracy Simultaneous localization and mapping Sensitivity Laser radar Geometric modeling Noise

来源：评论

学校读者我要写书评

暂无评论

GPIO Based Iterative Learning control for Manipulators with Time-Varying Disturbances

GPIO Based Iterative Learning Control for Manipulators with ...

引用

Chinese control Conference (CCC)

作者： Huangyuwei Lu Zuo Wang Jiankun Sun Xi Xiao Shihua Li School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex systems of Engineering Ministry of Education Nanjing China Shenzhen Research Institute Southeast University Shenzhen China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration Nanjing China

To improve the disturbance rejection ability and repetitive tracking accuracy of manipulators, a composite iterative learning control (ILC) scheme via generalized proportional integral observer (GPIO) is proposed. A high-order polynomial is first employed to model the time-varying disturbances that include unmodeled dynamics, parameter uncertainties and load fluctuations. A GPIO is then designed to estimate the disturbances and high-order time derivatives. By introducing estimations into a PD-type ILC at each iteration, a composite control scheme is obtained, such that the undesirable influence of time-varying disturbances can be effectively attenuated in the repetitive tracking process of manipulators. In this paper, the rigorous stability analysis of the closed-loop system is presented to guarantee that the tracking error exponentially converges to zero as the iteration number tends to infinity. The effectiveness of the proposed control scheme is finally verified by simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Terminal Impact-angle-constrained Guidance Law of Miniature Munition Based on High-order Fully Actuated System Approach

Terminal Impact-angle-constrained Guidance Law of Miniature ...

引用

Chinese Automation Congress (CAC)

作者： Shiwei Chen Junfang Fan Wei Wang Yi Ji Ning Liu School of Aerospace Engineering Beijing Institute of Technology Beijing China Beijing Key Laboratory of UAV Autonomous Control Beijing Institute of Technology Beijing China Beijing Key Laboratory of High Dynamic Navigation Technology Beijing Information Science & Technology University Beijing China

Aiming at the terminal impact-angle constraint in the interception of large maneuvering targets by munition, this paper proposes a three-dimensional(3D) maneuvering target interception guidance law combined with the high-order fully-actuated (HOFA) system theory based on biased proportional navigation guidance (BPNG). First, a complete second-order nonlinear model with fully-actuation is built for munition-target relative motion without the small-angle assumption. Second, the nonlinear system of the munition-target relative motion is transformed into a quasi-feedback system, and a HOFA model is developed for the system. A BPNG law with the linear relationship of the line-of-sight angle is introduced to transform the closed-loop system into a linear time-invariant closed-loop system with the expected characteristic structure. Finally, target maneuver information is taken as the model compensation and adopted as the external input of the closed-loop system together with the remainder of the guidance law; thus, the channel coupling of the nonlinear three-dimensional system is eliminated. The effectiveness of the proposed method is verified by simulation results.

关键词： Couplings Solid modeling Three-dimensional displays Navigation Weapons Simulation Line-of-sight propagation

来源：评论

学校读者我要写书评

暂无评论

Short-Range Detection of Ferromagnetic Target Based on Tunneling Magnetoresistance Sensor

Short-Range Detection of Ferromagnetic Target Based on Tunne...

引用

2019 IEEE International Conference on Unmanned Systems, ICUS 2019

作者： Fan, Qiang Deng, Jiahao Duan, Zuodong Wei, Xiaowei Xu, Sha Beijing Institute of Technology Science and Technology on Electromechanical Dynamic Control Laboratory School of Mechatronical Engineering Beijing China

ISBN: (纸本)9781728137926

In order to improve the accuracy of short-range ferromagnetic target location and distance-determination, the short-range detection technology of ferromagnetic target based on tunneling magnetoresistance (TMR) sensor is studied in this paper. Based on the analysis of the tunneling magneto-resistance effect principle and the understanding of the relevant magnetic field detecting components, a suitable signal conditioning and signal processing circuit is designed to constitute the TMR magnetic detector. Two kinds of ferromagnetic targets with regular shapes are measured at different distances and orientations, and the measured data are analyzed by curve fitting method. The results show that the output signal amplitude value of the detector is inversely proportional to the cubic power of the relative distance between the detector and the measured target when it is in the near field (no more than 5 meters in this paper). And the influence of the measured target material and detection orientation on the relationship between the two also shows a certain correlation. On the basis of the short-range static detection of general ferromagnetic targets, dynamic tests were carried out with the aim of household cars, the results indicate that the detection distance of dynamic vehicles can reach 7 meters. © 2019 IEEE.

关键词： Ferromagnetic materials

来源：评论

学校读者我要写书评

暂无评论

Localization of Pallets in Narrow Aisles for Unmanned Forklifts

Localization of Pallets in Narrow Aisles for Unmanned Forkli...

引用

Computer technology and Information science (ISCTIS), International Symposium on

作者： Peng Sun Wei Ding Mingchang Lian Hao Chen Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou Fujian P. R. China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou China

As the application of unmanned forklifts becomes more and more widespread, logistics scenarios are constantly evolving. This paper focuses on a scenario where the pick-up of pallets perpendicular to forklift in narrow aisles is required. The narrow aisles only allow the forklift to complete the turning, performing pallet localization in front of it will be difficult. We proposes a method for localizing pallets in narrow aisles for unmanned forklifts. By installing the camera at an oblique angle above the pallet, the collected images are uploaded to the image processing system. The YOLOv5 is used to detect the pallet and extract the bounding boxes of the pallet class. Based on the bounding box coordinates, the original image is cropped. Convert the cropped image to grayscale for Canny edge detection, and then perform Hough line detection to extract the right edge of the pallet. This right edge will be compared with the reference pallet edge to obtain the relative localization between the pallet and the unmanned forklift.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallel Multi-Extended State Observers based ADRC with Application to High-Speed Precision Motion Stage

arXiv

引用

arXiv 2023年

作者： Tang, Guojie Xue, Wenchao Peng, Hao Zhao, Yanlong Yang, Zhijun The Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The School of Mathematical Sciences University of Chinese Academy of Sciences Beijing100049 China The School of Electromechanical Engineering Guangdong University of Technology Guangdong Guangzhou510006 China

In this paper, the parallel multi-extended state observers (ESOs) based active disturbance rejection control approach is proposed to achieve desired tracking performance by automatically selecting the estimation values leading to the least tracking error. First, the relationship between the estimation error of ESO and the tracking error of output is quantitatively studied for single ESO with general order. In particular, the algorithm for calculating the tracking error caused by single ESO’s estimation error is constructed. Moreover, by timely evaluating the least tracking error caused by different ESOs, a novel switching ADRC approach with parallel multi-ESOs is proposed. In addition, the stability of the algorithm is rigorously proved. Furthermore, the proposed ADRC is applied to the high-speed precision motion stage which has large nonlinear uncertainties and elastic deformation disturbances near the dead zone of friction. The experimental results show that the parallel multi-ESOs based ADRC has higher tracking performance than the traditional single ESO based ADRC. Copyright © 2023, The Authors. All rights reserved.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

A C-Band Reconfigurable Pixel Antenna for Anti-Jamming Fuze

A C-Band Reconfigurable Pixel Antenna for Anti-Jamming Fuze

引用

International Conference on Microwave and Millimeter Wave technology Proceedings

作者： Yiming Wang Wentao Li Xiaowei Shi Science and Technology on Electromechanical Dynamic Control Laboratory China School of Electronic Engineering Xidian University Xi’an China

ISBN: (数字)9781728157337

ISBN: (纸本)9781728157344

Radio fuze devices are used to detect the location of targets on the battlefield. With the continuous development of electronic technology, their ability to resist external interference has received increasing attention. In this letter, a reconfigurable pixel antenna working in the C-band is proposed. The antenna consists of a driving patch and a parasitic pixel surface that is divided into two layers, the inner and outer layers. By changing the connection of the inner and outer pixel surfaces, the antenna's operating frequency, polarization, and radiation pattern can be controlled in real time, the reconfigurable performance of two frequency and polarization states and three pattern modes for each operating state are obtained. Both operating states are in the C-band, and the antenna gain is about 5dB and 4dB, respectively. This antenna can be used in anti-jamming fuze. Compared with the traditional microstrip fuze antenna, the designed antenna is suitable for more working scenarios, and the flexible reconfigurable performance is more conducive to the realization of anti-jamming performance.

关键词： Microwave antennas Time-frequency analysis Microstrip antennas Resists Real-time systems Frequency control Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

Efficient Path-Following for Urban Logistics: A Fuzzy control Strategy for Consumer UAVs under Disturbance Constraints

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Shao, Xingling Du, Jun Xia, Yi Zhang, Zekai Hou, Xiangwang Debbah, Merouane North University of China School of Electrical and Control Engineering Taiyuan030051 China State Key Laboratory of Extreme Environment Optoelecronic Dynamic Measurement Technology and Instrument Taiyuan030051 China Tsinghua University Department of Electronic Engineering Beijing100084 China Tsinghua University State Key laboratory of Space Network and Communications Beijing100084 China National University of Defense Technology College of Intelligence Science and Technology Hunan Changsha410073 China Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518055 China Khalifa University of Science and Technology KU6G Research Center Abu Dhabi127788 United Arab Emirates

The adoption of consumer unmanned aerial vehicles (UAVs) for logistics transportation is a key aspect of the emerging low-altitude economy, yet it faces significant challenges. Urban environments introduce complex obstacles, including dense buildings and unpredictable wind disturbances, while existing control methods struggle to balance path-following accuracy, disturbance rejection, and communication efficiency. To meet these demands, this paper proposes a quantized fuzzy learning path-following control for consumer UAVs. Firstly, a hysteresis quantized fuzzy disturbance observer (HQFDO) is proposed where the disturbances are approximately estimated by a neural network. Notably, a hysteresis quantizer is employed to reduce the communication bandwidth occupation by discretizing disturbance observations. Subsequently, a distributed velocity controller and a heading angle controller are designed to tackle the geometric and dynamic tasks separately. Specifically, the velocity controller introduces a projective arc length error to mitigate inefficiencies and safety risks associated with frequent acceleration and deceleration switches. Compared to conventional techniques, the proposed approach improves transient performance, enhances path attractivity, and optimizes communication resource utilization. Theoretical stability analysis is provided, and simulations validate the effectiveness of the proposed control strategy. © 1975-2011 IEEE.

关键词： Target drones

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：