检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Dan Xu Xinyu Wu Dezhen Song Nannan L Yen-Lun Chen Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Computer Science and Engineering Texas A&M University USA

ISBN: (纸本)9781479923427

In this paper, we present a novel approach for video anomaly detection in crowded and complicated scenes. The proposed approach detects anomalies based on a hierarchical activity pattern discovery framework comprehensively considering both global and local spatio-temporal contexts. The discovery is a coarse-to-fine learning process with unsupervised ways for automatically constructing normal activity patterns at different levels. An unified anomaly energy function is designed based on these discovered activity patterns to identify the abnormal level of an input motion pattern. We demonstrate the efficiency of the proposed method on the UCSD anomaly detection datasets (Ped1 and Ped2) and compare the performance with existing work.

关键词： Visual surveillance video anomaly detection hierarchical discovery energy function Visual surveillance Activity patterns anomaly Videotapes anomaly detection Crowding

来源：评论

学校读者我要写书评

暂无评论

Scaled Minimum Unscented Multiple Hypotheses Mixing Filter

Scaled Minimum Unscented Multiple Hypotheses Mixing Filter

引用

American Control Conference

作者： Henrique M. Menegaz Pedro Henrique R.Q.A. Santana Jo?o Y. Ishihara Geovany A. Borges Laboratory of Robotics and Automation (LARA) at the Department of Electrical Engineering University of Brasilia Brasilia DF Brasil Computer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA 02139 USA

ISBN: (纸本)9781479901777

This work brings two new contributions. First, it introduces the Scaled Minimum Unscented Multiple Hypotheses Mixing Filter, a novel filter for hybrid dynamical systems that 1) uses a new minimum set of sigma points along with the scaled unscented transform in a hybrid framework;2) can estimate the Markovian Transition Probability Matrix in real-time;3) features a pruning step that reduces the filter's computational effort and prevents its estimates from being degraded by very unlikely hypotheses;and 4) has a mixing step with merging depth greater than one. Second, we present a result revealing the conservativeness of one of the scaled unscented transform forms.

关键词： hybrid dynamical systems sigma points along scaled unscented transform

来源：评论

学校读者我要写书评

暂无评论

Active landmark configuration for accurate nano-positioning

Active landmark configuration for accurate nano-positioning

引用

6th IFAC Symposium on Mechatronic Systems, MECH 2013

作者： Yuan, Shuai Liu, Lianqing Wang, Zhidong Xi, Ning Wang, Yuechao Dong, Zaili State Key Lab. Robot. SIA. Chinese Academy of Sciences Shenyang 110016 China Shenyang Jianzhu University Shenyang 110168 China Graduate University of the Chinese Academy of Sciences Beijing 100039 China Dept. of Advanced Robotics Chiba Institute of Technology Chiba 275-0016 Japan Dept. of Electrical and Computer Engineering Michigan State University United States

ISBN: (纸本)9783902823311

The spatial uncertainties of atom force microscopy (AFM) tip position hinder the AFM based nano-manipulation. Although the landmark based tip localization can be applied to improve the tip position accuracy in the task space, the PZT nonlinearity and system drift are still a challenge to compensation performance when the tip is positioned far from the landmark. Therefore this paper proposes an active landmark configuration. This method first estimates the nearby area called as the landmark domain around the target position, and then actively manipulates the landmark into the landmark domain by using virtual hand to improve the positioning accuracy. Simulation and experiment illustrate the validity of the proposed method. © 2013 IFAC.

关键词： Nanotechnology

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling and bio-inspired LQR approach for off-road robotic vehicle path tracking

Dynamic modeling and bio-inspired LQR approach for off-road ...

引用

International Conference on Advanced robotics (ICAR)

作者： Rafael A. Cordeiro José R. Azinheira Ely C. de Paiva Samuel S. Bueno School of Electrical and Computer Engineering of the University of Campinas Instituto Superior Técnico Universidade de Lisboa (IST/VL) Lisbon Portugal Faculty of Mechanical Engineering University of Campinas (FEM/UNICAMP) Campinas SP Brazil Robotics and Computer Vision Lab Center for Information Technology Renato Archer (DRVC/CTI) Campinas SP Brazil

Ground robotic vehicles have received special research attention in recent years. Application scenarios range from advanced driver assistance systems (ADAS) in urban vehicles up to autonomous navigation strategies on field environments. This work focuses on common subjects for these applications: Dynamic modeling and path tracking control of off-road robotic vehicles. Firstly, a nonlinear 3D dynamic model of a four wheels vehicle was conceived and used to simulate the vehicle motion behavior. An LQR path tracking controller was obtained from a linearized 2D vehicle model. Finally, a bio-inspired reference shaping approach is introduced to enhance the lateral tracking performance. The overall methodology and simulation results are presented.

关键词： Vehicles Mathematical model Wheels Tires Vehicle dynamics Torque Equations

来源：评论

学校读者我要写书评

暂无评论

Active Landmark Configuration for Accurate Nano-Positioning

引用

IFAC Proceedings Volumes 2013年第5期46卷 594-599页

作者： Shuai Yuan Lianqing Liu Zhidong Wang Ning Xi Yuechao Wang Zaili Dong State Key Lab. Robot. SIA. Chinese Academy of Sciences Shenyang 110016 China Shenyang Jianzhu University Shenyang110168 Chinae Graduate University of the Chinese Academy of Sciences Beijing 100039 China Dept. of Advanced Robotics Chiba Institute of Technology Chiba 275-0016 Japan Dept. of Electrical and Computer Engineering Michigan State University US

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bayesian fusion of thermal and visible spectra camera data for region based tracking with rapid background adaptation

Bayesian fusion of thermal and visible spectra camera data f...

引用

2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2012

作者： Stolkin, Rustam Rees, David Talha, Mohammed Florescu, Ionut Intelligent Robotics Lab Of the School of Computer Science University of Birmingham United Kingdom Department of Mathematical Science Stevens Institute of Technology United States

ISBN: (纸本)9781467325110

This paper presents a method for optimally combining pixel information from an infra-red thermal imaging camera, and a conventional visible spectrum colour camera, for tracking a moving target. The tracking algorithm rapidly re-learns its background models for each camera modality from scratch at every frame. This enables, firstly, automatic adjustment of the relative importance of thermal and visible information in decision making, and, secondly, a degree of camouflage target tracking by continuously re-weighting the importance of those parts of the target model that are most distinct from the present background at each frame. Furthermore, this very rapid background adaptation ensures robustness to large, sudden and arbitrary camera motion, and thus makes this method a useful tool for robotics, for example visual servoing of a pan-tilt turret mounted on a moving robot vehicle. The method can be used to track any kind of arbitrarily shaped or deforming object, however the combination of thermal and visible information proves particularly useful for enabling robots to track people. The method is also important in that it can be readily extended for data fusion of an arbitrary number of statistically independent features from one or arbitrarily many imaging modalities. © 2012 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Design and development of a wearable rehabilitation robot

引用

4th International Conference on Social robotics, ICSR 2012

作者： He, Wei Ge, Shuzhi Sam Guo, Weian Zhao, Zhen Zhang, Jie Xiao, Shengtao Nuraisha, Fon Ping Quek Robotics Institute School of Automation Engineering University of Electronic Science and Technology of China Chengdu 611731 China Robotics Institute School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611731 China Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Singapore Social Robotics Lab. Interactive Digital Media Institute National University of Singapore Singapore 119613 Singapore

ISBN: (纸本)9783642341021

In this paper, we present the design and development of a wearable robot for the lower limb rehabilitation including the mechanical, electrical system, software implementation, etc. To make the robot wearable and portable and simplify the mechanism structure, servo motors are used as robot's joints. A friendly human robot interface is designed to make the robot easy to use. The dynamics of the robot is described by a 2-link rigid robotic manipulator in the joint space. The simulation results are given to demonstrate the feasibility and effectiveness of the designed lower limb rehabilitation robot-assisted system. © 2012 Springer-Verlag.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Towards AER VITE: Building spike gate signal

Towards AER VITE: Building spike gate signal

引用

2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012

作者： Perez-Pena, Fernando Morgado-Estevez, Arturo Rioja-Del-Rio, Carlos Linares-Barranco, Alejandro Jimenez-Fernandez, Angel Lopez-Coronado, Juan Munoz-Lozano, Jose Luis Applied Robotics Lab High School of Engineering University of Cadiz Spain Automatic and System Engineering Department University Polytechnics of Cartagena Spain Department of Computer Architecture and Technology ETSI Computer Science University of Seville Spain

ISBN: (纸本)9781467312615

Neuromorphic engineers aim to mimic the precise and efficient mechanisms of the nervous system to process information using spikes from sensors to actuators. There are many available works that sense and process information in a spike-based way. But there are still several gaps in the actuation and motor control field in a spike-based way. Spike-based Proportional-Integrative- Derivative controllers (PID) are present in the literature. On the other hand, neuro-inspired control models as VITE (Vector Integration To End point) and FLETE (Factorization of muscle Length and muscle Tension) are also present in the literature. This paper presents another step toward the spike implementation of those neuro-inspired models. We present a spike-based ramp multiplier. VITE algorithm generates the way to achieve a final position targeted by a mobile robotic arm. The block presented is used as a gate for the way involved and it also puts the incoming movement on speed with a variable slope profile. Only spikes for information representation were used and the process is in real time. The software simulation based on Simulink and Xilinx System Generator shows the accurate adjust to the traditional processing for short time periods and the hardware tests confirm and extend the previous simulated results for any time. We have implemented the spikes generator, the ramp multiplier and the low pass filter into the Virtex-5 FPGA and connected this with an USB-AER (Address Event Representation) board to monitor the spikes. © 2012 IEEE.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

OUR-CVFH - Oriented, unique and repeatable clustered viewpoint feature histogram for object recognition and 6DOF pose estimation

OUR-CVFH - Oriented, unique and repeatable clustered viewpoi...

引用

Joint 34th Symposium of the German Association for Pattern Recognition, DAGM 2012 and 36th Symposium of the Austrian Association for Pattern Recognition, OAGM 2012

作者： Aldoma, Aitor Tombari, Federico Rusu, Radu Bogdan Vincze, Markus Vision4Robotics Group ACIN Vienna University of Technology Austria Computer Vision Lab. DEIS - ARCES University of Bologna Italy Open Perception Inc. United States

ISBN: (纸本)9783642327162

We propose a novel method to estimate a unique and repeatable reference frame in the context of 3D object recognition from a single viewpoint based on global descriptors. We show that the ability of defining a robust reference frame on both model and scene views allows creating descriptive global representations of the object view, with the beneficial effect of enhancing the spatial descriptiveness of the feature and its ability to recognize objects by means of a simple nearest neighbor classifier computed on the descriptor space. Moreover, the definition of repeatable directions can be deployed to efficiently retrieve the 6DOF pose of the objects in a scene. We experimentally demonstrate the effectiveness of the proposed method on a dataset including 23 scenes acquired with the Microsoft Kinect sensor and 25 full-3D models by comparing the proposed approach with state-of-the-art global descriptors. A substantial improvement is presented regarding accuracy in recognition and 6DOF pose estimation, as well as in terms of computational performance. © 2012 Springer-Verlag.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Impedance control of a rehabilitation robot for interactive training

引用

4th International Conference on Social robotics, ICSR 2012

作者： He, Wei Ge, Shuzhi Sam Li, Yanan Chew, Effie Ng, Yee Sien Robotics Institute School of Automation Engineering University of Electronic Science and Technology of China Chengdu 611731 China Robotics Institute School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611731 China Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Singapore Social Robotics Lab. Interactive Digital Media Institute National University of Singapore Singapore 119613 Singapore Division of Neurology National University Hospital Singapore 119074 Singapore Department of Rehabilitation Medicine Singapore General Hospital Singapore 169608 Singapore

ISBN: (纸本)9783642341021

In this paper, neural networks based impedance control is developed for a wearable rehabilitation robot in interactions with humans and the environments. The dynamics of the robot are represented by an n-link rigid robotic manipulator. To deal with the system uncertainties and improve the robustness of the system, the adaptive neural networks are used to approximate the unknown model of the constrained robot. With the proposed control, uniform ultimate boundedness of the closed loop system is achieved based on the Lyapunov method. The states of the system converge to a small neighborhood of zero by properly choosing control gains. Extensive simulations are conducted to verify the proposed control. © 2012 Springer-Verlag.

关键词： Lyapunov methods

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：