检索结果-内蒙古大学图书馆

6D pose annotation and pose estimation method for weak-corner objects under low-light conditions

Science China(Technological Sciences) 2023年第3期66卷 630-640页

作者： JIANG ZhiHong CHEN JinHong JING YaMan HUANG Xiao LI Hui School of Mechatronic Engineering Beijing Institute of TechnologyBeijing 100081China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing 100081China Key Laboratory of Biomimetic Robots and Systems Ministry of EducationBeijing 100081China

In unstructured environments such as disaster sites and mine tunnels,it is a challenge for robots to estimate the poses of objects under complex lighting backgrounds,which limit their *** to the shadows produced by a point light source,the brightness of the operation scene is seriously unbalanced,and it is difficult to accurately extract the features of *** is especially difficult to accurately label the poses of objects with weak corners and *** study proposes an automatic pose annotation method for such objects,which combine 3D-2D matching projection and rendering technology to improve the efficiency of dataset annotation.A 6D object pose estimation method under low-light conditions(LP_TGC)is then proposed,including(1)a light preprocessing neural network model based on a low-light preprocessing module(LPM)to balance the brightness of a picture and improve its quality;and(2)a 6D pose estimation model(TGC)based on the keypoint *** typical datasets are constructed to verify our method,the experimental results validated and demonstrated the effectiveness of the proposed LP_TGC *** estimation model based on the preprocessed image can accurately estimate the pose of the object in the mentioned unstructured environments,and it can improve the accuracy by an average of~3%based on the ADD metric.

关键词： 6D object pose estimation 6D pose annotation low-light conditions

来源：评论

学校读者我要写书评

暂无评论

Time-Varying Formation Tracking Control of Heterogeneous Multi-Agent systems With Intermittent Communications and Directed Switching Networks

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 294-296页

作者： Yuhan Wang Zhuping Wang Hao Zhang Huaicheng Yan the Shanghai Research Institute for Intelligent Autonomous Systems Tongji University the National Key Laboratory of Autonomous Intelligent Unmanned Systems the Frontiers Science Center for Intelligent Autonomous System of Ministry of Education the College of Electronic and Information Engineering the Department of Control Science and Engineering Tongji University the Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education the School of Information Science and Engineering East China University of Science and Technology

Dear Editor,This letter is concerned with the problem of time-varying formation tracking for heterogeneous multi-agent systems(MASs) under directed switching networks. For this purpose, our first step is to present so... 详细信息

关键词： Switches Topology Observers Formation control Event detection Switched systems Multi-agent systems Control theory Autonomous systems Stability

来源：评论

学校读者我要写书评

暂无评论

Voltage Balance Control of Five-Level Cascaded H-Bridge Rectifier-Based Smart Transformer 13

Voltage Balance Control of Five-Level Cascaded H-Bridge Rect...

引用

13th International Renewable Energy Congress, IREC 2022

作者： Helali, Hiba Khedher, Adel Universite de Sousse Ecole Nationale d'Ingenieurs de Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia

ISBN: (纸本)9781665488976

The Smart Distribution Grid (SDG) applications have a high potential to improve the power system performance under the high penetration of distributed energy resources. Nevertheless, the conventional transformer (CT), which is the most important component of the distribution system, cannot fulfill the SDG requirement. In this regard, the modular smart transformer (ST) has emerged as a promising alternative to CT in the SDG. The structure of this transformer includes power conversion stages and multiple DC buses on the Medium Voltage (MV) and Low Voltage (LV) sides. This paper proposes an ST model based on a five-level Cascaded H-Bridge (CHB) rectifier in the MV AC-DC power conversion stage, six dual active bridge converters in the high-frequency DC-DC power conversion stage, a three-phase four-leg inverter in the LV DC-AC power conversion stage, and six DC buses on the MV and LV side, for SDG applications. The use of the four-leg inverter in the ST model enables to improve the quality of the grid voltage, minimize the neutral current and provide power supply for a three-phase or single-phase load. Moreover, a voltage balance control for the CHB rectifier is presented in this paper to eliminate the voltage unbalance problems in DC buses and improve the ST performance. Finally, the simulation results verify the good performance of the proposed control system. © 2022 IEEE.

关键词： Power quality

来源：评论

学校读者我要写书评

暂无评论

A Novel Feature Combination Approach For Driver Fatigue Detection 19

A Novel Feature Combination Approach For Driver Fatigue Dete...

引用

19th IEEE International Multi-Conference on systems, Signals and Devices, SSD 2022

作者： Trimech, Imen Hamrouni Messaoudi, Nada Ben Amara, Najoua Essoukri Université de Sousse Ecole Nationale d'Ingenieurs de Sousse LATIS-Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

Driver drowsiness is one of the major causes of traffic accidents. For instance, according to the National High Way Traffic Safety Organisation in Tunisia, 39.84% of accidents are caused by somnolence, in 2022. In that context, various state of the art methods were developed to detect distracting driving and hence prevent traffic accidents. In this paper, we propose a novel approach for driver drowsiness detection based on a new set of combined features (HOG-SURF and HOG-HARRIS). We start by an effective detection, from each frame, of the driver face. Then, we extract a Region Of Interest (ROI) containing the main expressive facial parts. Once the ROI are delimited, we extract the HOG descriptors from both HARRIS and SURF key points. The developed method was evaluated on the YAWDD database. Experimental results show the performance and competitivenes of the proposed approach. We reach an average rate of 99.15%. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Integrated Cross-Scale Manipulation and Modulable Encapsulation of Cell-Laden Hydrogel for Constructing Tissue-Mimicking Microstructures

引用

Research 2025年第1期2024卷 704-717页

作者： Yanfeng Zhao Xinyi Dong Yang Li Juan Cui Qing Shi Hen-Wei Huang Qiang Huang Huaping Wang Intelligent Robotics Institute School of Mechatronical EngineeringBeijing Institute of TechnologyBeijing 100081China Peking University First Hospital Xicheng DistrictBeijing 100034China Key Laboratory of Instrumentation Science and Dynamic Measurement Ministry of EducationNorth University of ChinaTaiyuan 030051China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of TechnologyBeijing 100081China Laboratory for Translational Engineering Harvard Medical SchoolCambridgeMA 02139USA Key Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Ministry of EducationBeijing 100081China

Engineered microstructures that mimic in vivo tissues have demonstrated great potential for applications in regenerative medicine,drug screening,and cell behavior ***,current methods for engineering microstructures that mimic the multi-extracellular matrix and multicellular features of natural tissues to realize tissue-mimicking microstructures in vitro remain ***,we propose a versatile method for constructing tissue-mimicking heterogeneous microstructures by orderly integration of macroscopic hydrogel exchange,microscopic cell manipulation,and encapsulation ***,various cell-laden hydrogel droplets are manipulated at the millimeter scale using electrowetting on dielectric to achieve efficient hydrogel ***,the cells are manipulated at the micrometer scale using dielectrophoresis to adjust their density and arrangement within the hydrogel ***,the photopolymerization of these hydrogel droplets is triggered in designated regions by dynamically modulating the shape and position of the excitation ultraviolet ***,heterogeneous microstructures with different extracellular matrix geometries and components were constructed,including specific cell densities and *** resulting heterogeneous microstructure supported long-term culture of hepatocytes and fibroblasts with high cell viability(over 90%).Moreover,the density and distribution of the 2 cell types had significant effects on the cell proliferation and urea *** propose that our method can lead to the construction of additional biomimetic heterogeneous microstructures with unprecedented potential for use in future tissue engineering applications.

关键词： cell behavior explorationhowevercurrent tissue mimicking microstructures cell laden hydrogel electrowetting dielectric regenerative medicinedrug screeningand heterogeneous microstructures engineered microstructures orderly integration

来源：评论

学校读者我要写书评

暂无评论

Group Hybrid Coordination Control of Multi-Agent systems With Time-Delays and Additive Noises

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 737-748页

作者： Chuanjian Li Xiaofeng Zong School of Automation China University of GeosciencesWuhan 430074 Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074 the Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of EducationWuhan 430074China IEEE

A new kind of group coordination control problemgroup hybrid coordination control is investigated in this *** group hybrid coordination control means that in a whole multi-agent system(MAS)that consists of two subgroups with communications between them,agents in the two subgroups achieve consensus and containment,*** MASs with both time-delays and additive noises,two group control protocols are proposed to solve this problem for the containment-oriented case and consensus-oriented case,*** developing a new analysis idea,some sufficient conditions and necessary conditions related to the communication intensity betw een the two subgroups are obtained for the following two types of group hybrid coordination behavior:1)Agents in one subgroup and in another subgroup achieve weak consensus and containment,respectively;2)Agents in one subgroup and in another subgroup achieve strong consensus and containment,*** is revealed that the decay of the communication impact betw een the two subgroups is necessary for the consensus-oriented ***,the validity of the group control results is verified by several simulation examples.

关键词： Additive noises consensus control containment control group hybrid coordination control multi-agent systems(MASs) time-delays

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of a PV System Controlled through a Hybrid INC-PSO Algorithm using XSG Tool 9

Design and Simulation of a PV System Controlled through a Hy...

引用

9th IEEE International Conference on Sciences of Electronics, Technologies of Information and Telecommunications, SETIT 2022

作者： Amri, Akram Moussa, Intissar Khedher, Adel Universite de Sousse Ecole Nationale d'Ingenieurs de Sousse LATIS-Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia

ISBN: (数字)9781728184425

ISBN: (纸本)9781728184425

This paper details the development of a hybrid algorithm for maximum power point tracking (MPPT) used for large PV systems under real conditions. In this algorithm, the incremental conductance algorithm (INC) is used in the initial phase of tracking, and the particle swarm optimization method (PSO) in the second phase. The methodology was simulated using the Xilinx System Generator (XSG) tool. The integration of artificial intelligence into the INC algorithm allows for faster convergence to the global maximum power point (GMPP). Simulation results prove that the proposed algorithm increases the efficiency, corrects the tracking direction and quickly reaches the steady state without oscillations. © 2022 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

U-Net based Deep Learning Architectures for Latent Fingerprint Segmentation 19

U-Net based Deep Learning Architectures for Latent Fingerpri...

引用

19th IEEE International Multi-Conference on systems, Signals and Devices, SSD 2022

作者： Jaafar, Roua Walhazi, Hajer Maalej, Ahmed Ben Amara, Najoua Essoukri Universite de Sousse Ecole Nationale d'Ingenieurs de Sousse LATiS-Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

In this paper we propose to train different CNN-based encoder-decoder models for latent fingerprint segmentation. Model selection is conducted through hyper-parameters tweaking, and per-formance assessment, of individual models. Qualitative and quantitative evaluations, involving standard metrics, learning curves, and mask prediction versus ground truth, are reported using the NIST SD27 and NIST SD301 databases. The best deep learning model producing the lowest generalisation error on the segmentation task is highlighted. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A comparative study of geometric primitives fitting to 3D point clouds 6

A comparative study of geometric primitives fitting to 3D po...

引用

6th International Conference on advanced Technologies for Signal and Image Processing, ATSIP 2022

作者： Makhlouf, Aicha Ben Jallouli, Malika Mahjoub, Mohamed Ali Latis Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Ecole Nationale d'Ingénieurs de Sousse Sousse4023 Tunisia

ISBN: (纸本)9781665451161

The rapid development of scanning technologies has led to new challenges in Computer Aided Design (CAD) such as the reconstruction of the geometric model from a set of 3D points cloud. In fact, this model is the geometric support in various activities such as the analysis activity and the computer aided manufacturing activity. The CAD model is used in order to visualize scanned 3D objects by the approximation of the adequate shape using different mathematical equations. Thus, the most difficult stage in reconstructing a CAD model is 3D surface fitting. There are two sorts of 3D surfaces: simple geometric primitives (sphere, cylinder, cone, torus, etc.) and complex 3D surfaces (Bezier, B-Spline, NURBS, etc.). In this paper, we focus on the reconstruction of simple geometric primitives. These primitives can be found in a variety of settings, from home to industrial. The aim of this work is to select the appropriate algorithm that facilitates the approximation of geometric primitives given 3D point clouds. The following three strategies are proposed for a comparative study: the Levenberg Marquardt algorithm, the Spherical Harmonic method and the Trust-Region Reflective method. Based on the results of these algorithms, designers, manufacturers, and inspectors can choose the best method to reconstruct their final CAD model based on their specific needs. © 2022 IEEE.

关键词： Computer aided design

来源：评论

学校读者我要写书评

暂无评论

Time-varying formation-containment control for heterogeneous multi-agent systems with communication and output delays via observer-based feedback protocol

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 15435-15448页

作者： Yang, Yi He, Yong China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China

In this article, the time-varying formation-containment control problem of heterogeneous multi-agent systems (MASs) with an observer-based state feedback protocol is studied, where both communication delays and output delays are taken into consideration. By introducing an augmented Lyapunov-Krasovskii functionals (LKFs) candidate and employing less conservative methods to estimate its derivative, an improved quasi-formation-containment criterion is derived. On this basis, some observers and controllers are designed to allow for a larger maximum upper bound (MUB) of time delays on the premise of guaranteeing the fulfillment of the time-varying formation of leaders and the bounded convergence of followers. The estimation of the MUB determines the allowable delay range for system stability under the designed observers and controllers. Moreover, a distributed algorithm is developed to calculate the MUB of time delays, the observer gains, and the controller gains. Finally, two simulation experiments are implemented to demonstrate the obtained results, which verify the superiority and practicability of the criterion and algorithm. © 2004-2012 IEEE.

关键词： State feedback

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：