检索结果-内蒙古大学图书馆

IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)

作者： Shay Englander Bendor Daniela Esteves Madalena Valente Patricia Figueiredo Athanasios Vourvopoulos Institute for Systems and Robotics (ISR-Lisboa) Lisbon Portugal Department of Neuroscience Bar Ilan University (BIU) Ramat Gan Israel Faculdade de Ciências da Universidade de Lisboa Instituto de Biofísica e Engenharia Biomédica Lisbon Portugal Bioengineering Department Institute for Systems and Robotics (ISR-Lisboa) Instituto Superior Técnico (IST) Lisbon Portugal

ISBN: (数字)9798331521578

ISBN: (纸本)9798331521585

Brain-Computer Interfaces (BCIs) enable direct communication between the brain and external devices, offering significant potential for rehabilitation and assistive technologies. A major challenge is the performance gap between BCI training and real-time control due to the variability of the underlying brain signals measured using EEG and user mental strategies. Virtual Reality (VR) plays a crucial role in BCI training by providing immersive, embodied feedback, enhancing user engagement, and potentially improving performance. This study investigates how closed-loop BCI systems, based on motor imagery (MI) of left and right-hand movements, with different VR feedback modalities-comparing true vs. positive feedback-impact EEG features like Event-Related Desynchronization (ERD) and BCI performance. Fifteen participants performed MI BCI training and control, in a VR environment, designed to induce increased sense of embodiment. Our results show consistent classification accuracy and ERD levels across both feedback conditions, indicating that VR feedback, when embodying a virtual body, whether true or positive, supports stable BCI performance. Additionally, key discriminative features emerged outside conventional ERD regions, highlighting the value of exploring non-traditional EEG features for MI task differentiation. This study underscores the importance of VR in optimizing closed-loop BCI systems and improving understanding of neurophysiological responses during MI tasks.

关键词： Training Solid modeling Accuracy Virtual reality Motors Brain modeling Electroencephalography Real-time systems Brain-computer interfaces Reliability

来源：评论

学校读者我要写书评

暂无评论

A Dataset for Robot Navigation in GNSS-Disrupted Environments Using Low-Cost Sensors

A Dataset for Robot Navigation in GNSS-Disrupted Environment...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Tomás Barata Bruno Damas Vítor Viegas Vítor Conceição CINAV - Centro de Investigação Naval Escola Naval Almada Portugal Institute for Systems and Robotics (ISR) Instituto Superior Técnico Lisbon Portugal Instituto de Telecomunicações (IT) Instituto Superior Técnico Lisbon Portugal

ISBN: (数字)9798331538606

ISBN: (纸本)9798331538613

Global Navigation Satellite systems (GNSS) have significantly improved the accuracy and availability of Positioning, Navigation, and Timing (PNT) systems; however, this has also exposed vulnerabilities in critical infrastructures due to their dependence on these systems. The emergence of autonomous vehicles further intensifies the criticality of this dependence, particularly in military scenarios where robust and resilient navigation and positioning data are essential. This paper addresses the resilience of PNT systems in unknown and dynamic environments with compromised GNSS signals. We propose a novel dataset to test navigation algorithms in scenarios with intermittent GNSS availability, where the remaining available signals consist of IMU data and wheel odometry. This dataset comprises different data acquired in trials with increasing degrees of difficulty with respect to the localization procedure, and we employ an Extended Kalman Filter to provide some localization results using these data.

关键词： Location awareness Global navigation satellite system Wheels Sensor fusion Timing Sensors Odometry Kalman filters Vehicle dynamics Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Uncrewed Ground Vehicles in Military Operations: Lessons Learned from Experimental Exercises

Uncrewed Ground Vehicles in Military Operations: Lessons Lea...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Bruno Cândido Nuno Pessanha Santos Alexandra Moutinho João-Vitor Zacchi IDMEC Instituto Superior Técnico (IST) Universidade de Lisboa Lisbon Portugal Portuguese Military Research Center (CINAMIL) Portuguese Military Academy Lisbon Portugal Institute for Systems and Robotics (ISR) Instituto Superior Técnico (IST) Lisbon Portugal Portuguese Navy Research Center (CINAV) Portuguese Naval Academy Almada Portugal Fraunhofer IKS Munich Germany

ISBN: (数字)9798331538606

ISBN: (纸本)9798331538613

The ongoing evolution of modern warfare demands innovative solutions to enhance operational effectiveness and gain a competitive edge on the battlefield. Integrating Uncrewed Ground Vehicles (UGVs) transforms military operations by efficiently performing various tasks while minimizing risks to human life. Developing a UGV architecture that adapts to different mission profiles is essential, though accessing military information and conducting tests can pose challenges. Nonethe-less, military experimentation exercises are crucial for ensuring optimal system performance and fostering collaboration between academia, industry, and the military, ultimately leading to more effective systems with direct military applications. This article shares lessons learned obtained through participation in the military experimentation exercises conducted by the Portuguese Army (PoA) and the Portuguese Navy (PoN) in 2024, aiming to accelerate future developments in UGV technology and promote their efficient use in military operations. Future work will focus on enhancing the platform by improving the algorithms used to boost its performance on the identified mission profiles and enabling its autonomous execution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hand gesture recognition using color and depth images enhanced with hand angular pose data

Hand gesture recognition using color and depth images enhanc...

引用

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

作者： Trindade, Pedro Lobo, Jorge Barreto, Joao P. ISR - Institute of Systems and Robotics University of Coimbra Portugal ISR - Institute of Systems and Robotics and the Department of Electrical and Computer Engineering University of Coimbra Portugal

ISBN: (纸本)9781467325110

In this paper we propose a hand gesture recognition system that relies on color and depth images, and on a small pose sensor on the human palm. Monocular and stereo vision systems have been used for human pose and gesture recognition, but with limited scope due to limitations on texture, illumination, etc. New RGB-Depth sensors, that reply on projected light such as the Microsoft Kinect, have overcome many of those limitations. However, the point clouds for hand gestures are still in many cases noisy and partially occluded, and hand gesture recognition is not trivial. Hand gesture recognition is much more complex than full body motion, since we can have the hands in any orientation and can not assume a standing body on a ground plane. In this work we propose to add a tiny pose sensor to the human palm, with a minute accelerometer and magnetometer that combined provide 3D angular pose, to reduce the search space and have a robust and computationally light recognition method. Starting with the full depth image point cloud, segmentation can be performed by taking into account the relative depth and hand orientation, as well as skin color. Identification is then performed by matching 3D voxel occupancy against a gesture template database. Preliminary results are presented for the recognition of Portuguese Sign Language alphabet, showing the validity of the approach. © 2012 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Interactive Demonstration of an Energy Efficient YOLOv3 Implementation in Reconfigurable Logic 5

Interactive Demonstration of an Energy Efficient YOLOv3 Impl...

引用

5th Experiment at International Conference, exp.at 2019

作者： Oliveira, Bruno G. Lobo, Jorge ISR-Institute of Systems and Robotics University of Coimbra Portugal

ISBN: (纸本)9781728136370

In this interactive demonstration we present the usage of a state-of-The-Art object detector, YOLOv3, in a CPU+GPU+FPGA heterogeneous platform for embedded systems. Profiles of each function were analysed in order to achieve the most energy efficient solution in the design space. A camera is used to collect the frames, a board runs the algorithm and a monitor shows the labels of the detected objects attached to the image. The main purpose of this demo is to demonstrate to the conference attendees a functional version of an object detector in a low-power platform. In addition, we also intend to encourage the development of applications in this type of devices. © 2019 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Mission impossible?

引用

IEEE SPECTRUM 2003年第4期40卷 26-31页

作者： Kumagai, J SIPG-Signal and Image Processing Group Instituto Superior Técnico (IST) Institute for Systems and Robotics (ISR) Lisboa Portugal

With a new computer network automated investigative tools, and more channels for sharing information, the FBI hopes to finally know what it knows. The fall of 2001 saw the start of an ambitious program of modernization, which seems to recognize that the barriers that prevent the FBI from analyzing and sharing data are as much cultural as technological. These include accelerating a bureau-wide overhaul of basic computer hardware, software, and network infrastructure and replacing the FBI's ancient DOS-based Automated Case Support (ACS) database with a more user-friendly Windows-based system that can search on not just text but also photos, video and audio records, known as the Virtual Case File system.

关键词： government data processing FBI computer network automated investigative tools data sharing data analysis computer hardware computer software network infrastructure DOS-based Automated Case Support database Windows-based system Virtual Case computer software Government data processing Computer hardware computer programs computer network Data analysis Statistical analysis Data Sharing Modernization

来源：评论

学校读者我要写书评

暂无评论

Assessing the performance of SDM-based robot navigation with different image processing techniques

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2012年第4期39卷 349-356页

作者： Mendes, Mateus Coimbra, A. Paulo Crisóstomo, Manuel M. ISR - Institute of Systems and Robotics Dept. of Electrical and Computer Engineering University of Coimbra Portugal ESTGOH Polytechnic Institute of Coimbra Portugal

Vision is one of the preferred sources of perceptions to implement intelligent robot navigation: it is biologically inspired, requires inexpensive hardware and a single image does contain huge amounts of information. However, problems such as illumination changes, scenario changes and electric noise in the image sensors pose challenges which are difficult to overcome. In previous work the authors developed algorithms to navigate a robot based on sequences of visual memories stored into a Sparse Distributed Memory - a kind of associative memory suitable to work with high-dimensional binary vectors, which also exhibits behaviours in many aspects similar to those of the human brain. This paper analyses the impact of using different image processing techniques to minimise the impact of noise in the images used: histogram equalisation, contrast normalisation and smoothing using a Gaussian filter. The results show that equalisation and smoothing have a positive effect on the performance of the system.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Multi-object tracking using an adaptive transition model particle filter with region covariance data association

Multi-object tracking using an adaptive transition model par...

引用

作者： Palaio, Hélio Batista, Jorge ISR-Institute of Systems and Robotics University of Coimbra DEEC-FCTUC Portugal

ISBN: (纸本)9781424421756

We present an approach for detection, labelling and tracking multiple objects through both temporally and spatially significant occlusions. The proposed method builds on the idea of multiple objects scenario where grouping and occlusions are a reality. To this end, the objects are represented by covariance matrices and particle filters perform the object tracking. We propose a different measurement for the particles weights and a new update for the objects descriptor in a Riemannian framework. The results show the effectiveness of the approach hereby proposed in very clutter scenes. © 2008 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

A real-time driver visual attention monitoring system

A real-time driver visual attention monitoring system

引用

Second Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005

作者： Batista, Jorge P. ISR-Institute of Systems and Robotics DEEC/FCT University of Coimbra Coimbra Portugal

This paper describes a framework for analyzing video sequences of a driver and determining his level of attention. The proposed system deals with the computation of eyelid movement parameters and head (face) orientation estimation. The system relies on pupil detection to robustly track the driver's head pose and monitoring its level of fatigue. Visual information is acquired using a specially designed solution combining a CCD video camera with an NIR illumination system. The system is fully automatic and classifies rotation in all-view direction, detects eye blinking and eye closure and recovers the gaze of the eyes. Experimental results using real images demonstrates the accuracy and robustness of the proposed solution. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Multiple-model adaptive estimators: Open problems and future directions 9

Multiple-model adaptive estimators: Open problems and future...

引用

2007 9th European Control Conference, ECC 2007

作者： Aguiar, A. Pedro ISR/IST Institute for Systems and Robotics Instituto Superior Técnico Lisbon Portugal

ISBN: (纸本)9783952417386

Over the past decades there have been a considerable research effort on the subject of adaptive observers. In simple terms, an adaptive observer or estimator can be defined as a process that provides in real time the estimate of the state (or some function of it) of the plant from partial and possibly noise measurements of the inputs and outputs, inexact knowledge of the initial condition and in the presence of unknown parameters in the description of the plant1. In many cases, adaptive observers also identifies the unknown parameters. © 2007 EUCA.

关键词：

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：