资源类型

期刊论文 119

会议视频 1

年份

2023 10

2022 12

2021 13

2020 9

2019 5

2018 9

2017 7

2016 7

2015 10

2014 5

2013 4

2012 4

2011 1

2010 2

2009 1

2008 3

2007 5

2006 4

2004 5

2002 1

展开 ︾

关键词

跟踪 2

轨迹跟踪 2

4-adj模型 1

CCD影像 1

DPP）；分布式功率转换器；开关电容转换器 1

Hilare 机器人 1

MCDB 1

MPPT）；差分功率处理（Differential power processing 1

MSJPDA 1

OFDM 1

S频段 1

Voronoi图 1

三维过程；三元数；最小均方；卡尔曼滤波器 1

中国探月工程 1

主动物品检测；深度Q学习网络；训练算法；服务机器人 1

二分追踪；多智能体系统；异步脉冲；一致性 1

二肽基肽酶4 1

人-机交互 1

仿射编队；固定翼无人机；多智能体系统 1

展开 ︾

检索范围：

排序： 展示方式：

基于RGBD和稀疏学习的鲁棒目标跟踪 Article

Zi-ang MA, Zhi-yu XIANG

《信息与电子工程前沿（英文）》 2017年 第18卷 第7期   页码 989-1001 doi: 10.1631/FITEE.1601338

摘要： 鲁棒目标跟踪近年来成为计算机视觉领域一项重要的且极具挑战性的研究方向。随着深度传感器的普及，深度信息因其对光照变化与遮挡表现出一定的鲁棒性而被广泛应用于视觉目标跟踪算法中。本文提出了一种基于RGBD和稀疏学习的跟踪算法，从三个方面将深度信息应用到稀疏学习跟踪框架。首先将深度图像特征结合现有的基于彩色图像的视觉特征用于目标外观的鲁棒特征描述。为了适应跟踪过程中的各种遮挡情况，我们设计了一种特殊的遮挡物模板用于增广现有的超完备字典。最后，我们进一步提出了一种基于深度信息的遮挡物检测方法用于有效地指示模板更新。基于KITTI和Princeton数据集的大量实验证明了所提出算法的跟踪效果优于时下最先进的多种跟踪器，包括基于稀疏学习的跟踪以及基于RGBD的跟踪。

关键词： 目标跟踪；稀疏学习；深度视角；遮挡物模板；深度图像特征    

HTML PDF 收藏

基于可靠特征点分配算法的鲁棒性跟踪框架 Article

Rong-feng ZHANG, Ting DENG, Gui-hong WANG, Jing-lun SHI, Quan-sheng GUAN

《信息与电子工程前沿（英文）》 2017年 第18卷 第4期   页码 545-558 doi: 10.1631/FITEE.1601464

摘要： 最后，将所提出的RPA与卡尔曼滤波器集成到跟踪–学习–检测（Tracking–learning–detection, TLD）算法框架中，提高了跟踪精度，且降低了误检率。

关键词： 局部最大小波系数；可靠特征点分配；目标跟踪；跟踪-学习-检测（TLD）；卡尔曼滤波器    

HTML PDF 收藏

Construction Activity Analysis of Workers Based on Human Posture Estimation Information

Xuhong Zhou,Shuai Li,Jiepeng Liu,Zhou Wu,Yohchia Frank Chen,

《工程（英文）》 doi: 10.1016/j.eng.2023.10.004

摘要： Identifying workers’ construction activities or behaviors can enable managers to better monitor labor efficiency and construction progress. However, current activity analysis methods for construction workers rely solely on manual observations and recordings, which consumes considerable time and has high labor costs. Researchers have focused on monitoring on-site construction activities of workers. However, when multiple workers are working together, current research cannot accurately and automatically identify the construction activity. This research proposes a deep learning framework for the automated analysis of the construction activities of multiple workers. In this framework, multiple deep neural network models are designed and used to complete worker key point extraction, worker tracking, and worker construction activity analysis. The designed framework was tested at an actual construction site, and activity recognition for multiple workers was performed, indicating the feasibility of the framework for the automated monitoring of work efficiency.

关键词： Pose estimation     Activity analysis     Object tracking     Construction workers     Automatic systems    

HTML PDF 收藏

Actor-Critic强化学习算法及其在开发基于计算机视觉的界面跟踪中的应用 Article

Oguzhan Dogru, Kirubakaran Velswamy, 黄彪

《工程（英文）》 2021年 第7卷 第9期   页码 1248-1261 doi: 10.1016/j.eng.2021.04.027

摘要：

本文通过将对象跟踪形式化为序列决策过程，使控制理论与计算机视觉实现同步。强化学习（RL）智能体成功跟踪了两种液体之间的界面，这通常是化学、石化、冶金和石油行业中跟踪的关键变量。该方法使用少于100 张图像来创建环境，智能体无需专家知识即可从中生成自己的数据。与依赖大量参数的监督学习（SL）方法不同，这种方法需要的参数少得多，这自然降低了维护成本。除了经济性外，该智能体还对环境不确定性（如遮挡、强度变化和过度噪声）具有鲁棒性。在闭环控制情境下，基于界面位置的偏差被选作训练阶段的优化目标。该方法展示了RL方法在油砂行业中的实时对象跟踪应用。本文除了介绍界面跟踪问题外，还详细回顾了最有效的RL方法之一——actor-critic策略。

关键词： 界面跟踪     对象跟踪     遮挡     强化学习     均匀流形逼近和投影    

HTML PDF 收藏

面向多目标跟踪的关联相似度神经网络学习 Research Articles

马良,钟巧勇,张营营,谢迪,浦世亮

《信息与电子工程前沿（英文）》 2021年 第22卷 第9期   页码 1194-1206 doi: 10.1631/FITEE.2000272

摘要： 为解决视频多目标跟踪问题，提出一种特征和度量联合学习的深度神经网络架构，称为关联相似度网络。关联相似度网络以端到端的方式学习跟踪轨迹和检测结果之间的关联相似度。针对有缺陷的检测结果，关联相似度网络同时学习矩形框回归、目标分类和相似度回归3个任务。不同于现有基于对比排序思想的方法，我们直接训练一个二分类器来学习跟踪轨迹与检测结果的关联相似度，同时设计了损失函数来约束匹配集合元素的个数。得益于上述设计，关联相似度网络不仅能够解决多目标跟踪问题中的匹配问题，还可以进行单目标跟踪。基于提出的关联相似度网络，设计了一个简单的多目标跟踪算法，在MOT16和MOT17测试集上的实验结果表明其有效性。

关键词： 多目标跟踪；深度神经网络；相似度学习    

HTML PDF 收藏

Creating technical heritage object replicas in a virtual environment

Olga EGOROVA,Dmitry SHCHERBININ

《机械工程前沿（英文）》 2016年 第11卷 第1期   页码 108-115 doi: 10.1007/s11465-016-0363-4

摘要：

The paper presents innovative informatics methods for creating virtual technical heritage replicas, which are of significant scientific and practical importance not only to researchers but to the public in general. By performing 3D modeling and animation of aircrafts, spaceships, architectural-engineering buildings, and other technical objects, the process of learning is achieved while promoting the preservation of the replicas for future generations. Modern approaches based on the wide usage of computer technologies attract a greater number of young people to explore the history of science and technology and renew their interest in the field of mechanical engineering.

关键词： 3D document     history of science and technology     technical knowledge     popularization     virtual environment     replica     mechanism and machine science (MMS)    

HTML PDF 收藏

Output tracking control of mobile manipulators based on dynamical sliding-mode control

WUYuxiang, FENG Ying, HU Yueming

《机械工程前沿（英文）》 2007年 第2卷 第1期   页码 110-115 doi: 10.1007/s11465-007-0019-5

摘要： A dynamical sliding-mode controller is devised to track the output of mobile manipulators. During the investigation, firstly a reduced dynamic model considering the dynamics of the driving motor is developed for mobile manipulators. Then, the system is decomposed into four lower-dimensional subsystems by means of diffeomorphism and nonlinear input transformation. Moreover, a design method of the dynamical sliding-mode controller that is applied to the output tracking of mobile manipulators is proposed. The simulation results indicate that the dynamical sliding-mode controller can not only track the given trajectory correctly but also reduce the chattering of sliding-mode control system considerably.

关键词： lower-dimensional     nonlinear     trajectory     tracking     diffeomorphism    

HTML PDF 收藏

modeling on improved performance of an innovative method of using heave response of a non-floating object

Srinivasan CHANDRASEKARAN, Arunachalam AMARKARTHIK, Karuppan SIVAKUMAR, Dhanasekaran SELVAMUTHUKUMARAN, Shaji SIDNEY

《能源前沿（英文）》 2013年 第7卷 第3期   页码 279-287 doi: 10.1007/s11708-013-0268-4

摘要： To convert wave energy into usable forms of energy by utilizing heaving body, heaving bodies (buoys) which are buoyant in nature and float on the water surface are usually used. The wave exerts excess buoyancy force on the buoy, lifting it during the approach of wave crest while the gravity pulls it down during the wave trough. A hydraulic, direct or mechanical power takeoff is used to convert this up and down motion of the buoy to produce usable forms of energy. Though using a floating buoy for harnessing wave energy is conventional, this device faces many challenges in improving the overall conversion efficiency and survivability in extreme conditions. Up to the present, no studies have been done to harness ocean waves using a non-floating object and to find out the merits and demerits of the system. In the present paper, an innovative heaving body type of wave energy converter with a non-floating object was proposed to harness waves. It was also shown that the conversion efficiency and safety of the proposed device were significantly higher than any other device proposed with floating buoy. To demonstrate the improvements, experiments were conducted with non-floating body for different dimensions and the heave response was noted. Power generation was not considered in the experiment to observe the worst case response of the heaving body. The device was modeled in artificial neural network (ANN), the heave response for various parameters were predicted, and compared with the experimental results. It was found that the ANN model could predict the heave response with an accuracy of 99%.

关键词： ocean wave energy     point absorbers     heaving body     non-floating object     heave response ratio     artificial neural network (ANN)    

HTML PDF 收藏

基于多表征声呐数据特征融合的水下目标检测方法 Research Article

王非1,李婉玉1,刘淼2,周景春1,张维石1

《信息与电子工程前沿（英文）》 2023年 第24卷 第6期   页码 828-843 doi: 10.1631/FITEE.2200429

摘要： 现有水下目标检测方法多基于物体的几何形状从声呐数据中识别物体，这些方法几乎忽略数据采集和数据表征过程所产生的形状畸变问题。为此，本文对声呐数据的不同表示形式进行了对比分析，在此基础上，提出了一个特征融合框架，以充分利用从极坐标图像中提取的强度特征和从点云表示形式中学习的几何特征。该框架中设计了三种特征融合策略，以分析特征融合对检测器不同模块的影响。同时，这些融合策略可以直接集成到其他检测器中，如YOLO系列。通过公开水下实景声呐数据集上的一系列对比实验，验证了所提框架和特征融合策略的有效性。实验结果表明，所提特征融合方法对检测器中候选区域模块和分类模块的结果都有所增益。

关键词： 水下目标检测；声呐数据表示形式；特征融合    

HTML PDF 收藏

Dynamic Target Tracking of Unmanned Aerial Vehicles Under Unpredictable Disturbances

Yanjie Chen,Yangning Wu,Limin Lan,Hang Zhong,Zhiqiang Miao,Hui Zhang,Yaonan Wang,

《工程（英文）》 doi: 10.1016/j.eng.2023.05.017

摘要： This study proposes an image-based visual servoing (IBVS) method based on a velocity observer for an unmanned aerial vehicle (UAV) for tracking a dynamic target in Global Positioning System (GPS)-denied environments. The proposed method derives the simplified and decoupled image dynamics of underactuated UAVs using a constructed virtual camera and then considers the uncertainties caused by the unpredictable rotations and velocities of the dynamic target. A novel image depth model that extends the IBVS method to track a rotating target with arbitrary orientations is proposed. The depth model ensures image feature accuracy and image trajectory smoothness in rotating target tracking. The relative velocities of the UAV and the dynamic target are estimated using the proposed velocity observer. Thanks to the velocity observer, translational velocity measurements are not required, and the control chatter caused by noise-containing measurements is mitigated. An integral-based filter is proposed to compensate for unpredictable environmental disturbances in order to improve the anti-disturbance ability. The stability of the velocity observer and IBVS controller is analyzed using the Lyapunov method. Comparative simulations and multistage experiments are conducted to illustrate the tracking stability, anti-disturbance ability, and tracking robustness of the proposed method with a dynamic rotating target.

关键词： Unmanned aerial vehicle     Visual servoing     Velocity observer     Target tracking    

HTML PDF 收藏

Wheel tracking methods to evaluate moisture sensitivity of hot-mix asphalt mixtures

Jie HAN,Harihar Shiwakoti

《结构与土木工程前沿（英文）》 2016年 第10卷 第1期   页码 30-43 doi: 10.1007/s11709-016-0318-1

摘要： Existing test methods to determine moisture sensitivity in hot-mix asphalt (HMA) mixtures are time consuming and inconsistent. This research focused on wheel tracking devices to evaluate moisture sensitivity. The Asphalt Pavement Analyzer (APA) and the Hamburg Wheel Tracking Device (HWTD) were used for this research. Compacted cylindrical samples were fabricated using a Superpave Gyratory compactor. This study selected two most commonly used mixtures, SM-12.5A with PG 64-22 binder in overlay projects and SM-19A mixtures with PG 64-22 binder for major modification projects at Kansas Department of Transportation. Test results show that APA tests could induce stripping in most samples without any anti-stripping agent, which could be identified visually. However, APA results did not indicate any stripping inflection point while the HWTD results showed stripping inflection points, which are important to identify stripping potential of mixtures. The APA results show that wet tests are severe at lower temperatures. The HWTD results show improvement in the performance using anti-stripping agents at later stage. The HWTD test is more effective as a rapid test method in case of determining moisture sensitivity. Laboratory results from this study should be verified and correlated with field performance.

关键词： hot-mix asphalt     moisture sensitivity     rutting     wheel tracking test    

HTML PDF 收藏

Fractional order extremum seeking approach for maximum power point tracking of photovoltaic panels

Ammar NEÇAIBIA,Samir LADACI,Abdelfatah CHAREF,Jean Jacques LOISEAU

《能源前沿（英文）》 2015年 第9卷 第1期   页码 43-53 doi: 10.1007/s11708-014-0343-5

摘要： Due to the high interest in renewable energy and diversity of research regarding photovoltaic (PV) array, a great research effort is focusing nowadays on solar power generation and its performance improvement under various weather conditions. In this paper, an integrated framework was proposed, which achieved both maximum power point tracking (MPPT) and minimum ripple signals. The proposed control scheme was based on extremum-seeking (ES) combined with fractional order systems (FOS). This auto-tuning strategy was developed to maximize the PV panel output power through the regulation of the voltage input to the DC/DC converter in order to lead the PV system steady-state to a stable oscillation behavior around the maximum power point (MPP). It is shown that fractional order operators can improve the plant dynamics with respect to time response and disturbance rejection. The effectiveness of the proposed controller scheme is illustrated with simulations using measured solar radiation data.

关键词： extremum seeking (ES)     fractional order control (FOC)     fractional calculus     photovoltaic (PV) panel     maximum power point tracking (MPPT)    

HTML PDF 收藏

Time-varying formation tracking for uncertain second-order nonlinearmulti-agent systems

Mao-peng RAN, Li-hua XIE, Jun-cheng LI

《信息与电子工程前沿（英文）》 2019年 第20卷 第1期   页码 76-87 doi: 10.1631/FITEE.1800557

摘要：

Our study is concerned with the time-varying formation tracking problem for second-order multi-agent systems that are subject to unknown nonlinear dynamics and external disturbance, and the states of the followers form a predefined time-varying formation while tracking the state of the leader. The total uncertainty lumps the unknown nonlinear dynamics and the external disturbance, and is regarded as an extended state of the agent. To estimate the total uncertainty, we design an extended state observer (ESO). Then we propose a novel ESO based time-varying formation tracking protocol. It is proved that, under the proposed protocol, the ESO estimation error and the time-varying formation tracking error can be made arbitrarily small. An application to the target enclosing problem for multiple unmanned aerial vehicles (UAVs) verifies the effectiveness and superiority of the proposed approach.

关键词： Multi-agent system     Time-varying formation     Formation tracking     Nonlinear dynamics     Extended state observer (ESO)    

HTML PDF 收藏

A comprehensive simulator for assessing the reliability of a photovoltaic panel peak power tracking system

Nabil KAHOUL,Mourad HOUABES,Ammar NEÇAIBIA

《能源前沿（英文）》 2015年 第9卷 第2期   页码 170-179 doi: 10.1007/s11708-015-0353-y

摘要： When designing a maximum power point tracking (MPPT) algorithm, it is often difficult to correctly predict, before field testing, the behavior of this MPPT under varying solar irradiation on photovoltaic (PV) panels. A solution to this problem is to design a maximum power point trackers simulator of a PV system used to test MPPT algorithms. This simulator must have the same role as the MPPT card of the PV panel and thus will fully emulate the response of a real MPPT card of the PV panel. Therefore, it is a good substitute to help to test the peak power trackers of the PV system in the laboratory. This paper describes a simple peak power trackers simulator of the PV system which has a short response time thus, can be used to test MPPT algorithms under very rapid variation condition. The obtained results and the theoretical operation confirm the reliability and the superior performance of the proposed model.

关键词： photovoltaic module     DC-DC converter     design     maximum power point tracking (MPPT) card     microprocessor    

HTML PDF 收藏

Task-space position/attitude tracking control of FAST fine tuning system

QI Lin, ZHANG Hui, DUAN Guanghong

《机械工程前沿（英文）》 2008年 第3卷 第4期   页码 392-399 doi: 10.1007/s11465-008-0056-8

摘要： This paper addresses the task-space position/attitude tracking control of a suspended parallel robot, which is being developed in the framework of a five-hundred meter aperture spherical radio telescope (FAST) project. Based on the quaternion algebra, a novel model-independent task-space PD controller that ensures end-effector position and attitude tracking is presented. The simulation and experimental results show that the new controller has better control effects than the traditional joint-space controller.

关键词： telescope     five-hundred     end-effector     controller     simulation    

HTML PDF 收藏

标题 作者 时间 类型 操作

基于RGBD和稀疏学习的鲁棒目标跟踪

Zi-ang MA, Zhi-yu XIANG

期刊论文

基于可靠特征点分配算法的鲁棒性跟踪框架

Rong-feng ZHANG, Ting DENG, Gui-hong WANG, Jing-lun SHI, Quan-sheng GUAN

期刊论文

Construction Activity Analysis of Workers Based on Human Posture Estimation Information

Xuhong Zhou,Shuai Li,Jiepeng Liu,Zhou Wu,Yohchia Frank Chen,

期刊论文

Actor-Critic强化学习算法及其在开发基于计算机视觉的界面跟踪中的应用

Oguzhan Dogru, Kirubakaran Velswamy, 黄彪

期刊论文

面向多目标跟踪的关联相似度神经网络学习

马良,钟巧勇,张营营,谢迪,浦世亮

期刊论文

Creating technical heritage object replicas in a virtual environment

Olga EGOROVA,Dmitry SHCHERBININ

期刊论文

Output tracking control of mobile manipulators based on dynamical sliding-mode control

WUYuxiang, FENG Ying, HU Yueming

期刊论文

modeling on improved performance of an innovative method of using heave response of a non-floating object

Srinivasan CHANDRASEKARAN, Arunachalam AMARKARTHIK, Karuppan SIVAKUMAR, Dhanasekaran SELVAMUTHUKUMARAN, Shaji SIDNEY

期刊论文

基于多表征声呐数据特征融合的水下目标检测方法

王非1,李婉玉1,刘淼2,周景春1,张维石1

期刊论文

Dynamic Target Tracking of Unmanned Aerial Vehicles Under Unpredictable Disturbances

Yanjie Chen,Yangning Wu,Limin Lan,Hang Zhong,Zhiqiang Miao,Hui Zhang,Yaonan Wang,

期刊论文

Wheel tracking methods to evaluate moisture sensitivity of hot-mix asphalt mixtures

Jie HAN,Harihar Shiwakoti

期刊论文

Fractional order extremum seeking approach for maximum power point tracking of photovoltaic panels

Ammar NEÇAIBIA,Samir LADACI,Abdelfatah CHAREF,Jean Jacques LOISEAU

期刊论文

Time-varying formation tracking for uncertain second-order nonlinearmulti-agent systems

Mao-peng RAN, Li-hua XIE, Jun-cheng LI

期刊论文

A comprehensive simulator for assessing the reliability of a photovoltaic panel peak power tracking system

Nabil KAHOUL,Mourad HOUABES,Ammar NEÇAIBIA

期刊论文

Task-space position/attitude tracking control of FAST fine tuning system

QI Lin, ZHANG Hui, DUAN Guanghong

期刊论文