检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation

作者： Banglei Guan Pascal Vasseur Cedric Demonceaux Friedrich Fraundorfer College of Aerospace Science and Engineering National University of Defense Technology China LITIS Université de Rouen France Le2i Université Bourgogne Franche-Comté France Institute of Computer Graphics and Vision TU Graz Austria and with the Remote Sensing Technology Institute Germany

In this paper we present minimal solutions for two-view relative motion estimation based on a homography formulation. By assuming a known vertical direction (e.g. from an IMU) and assuming a dominant ground plane we demonstrate that rotation and translation estimation can be decoupled. This result allows us to reduce the number of point matches needed to compute a motion hypothesis. We then derive different algorithms based on this decoupling that allow an efficient estimation. We also demonstrate how these algorithms can be used efficiently to compute an optimal inlier set using exhaustive search or histogram voting instead of a traditional RANSAC step. Our methods are evaluated on synthetic data and on the KITTI data set, demonstrating that our methods are well suited for visual odometry in road driving scenarios.

关键词： Estimation Visual odometry Mathematical model Cameras Histograms Gravity Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Solid model edit distance: a multi-application and multi-level schema for CAD model retrieval

引用

computer Aided Drafting,Design and Manufacturing 2017年第1期27卷 22-38页

作者： Wang Bin Hu Kaimo Li Dong Zhang Hui School of Software Tsinghua University Tsinghua National Laboratory for Information Science and Technology Department of Computer Graphics Technology Purdue University

We present the solid model edit distance(SMED),a powerful and flexible paradigm for exploiting shape similarities amongst CAD *** is designed to measure the magnitude of distortions between two CAD models in boundary representation(B-rep).We give the formal definition by analogy with graph edit distance,one of the most popular graph matching *** avoid the expensive computational cost potentially caused by exact computation,an approximate procedure based on the alignment of local structure sets is provided in *** order to verify the flexibility,we make intensive investigations on three typical applications in manufacturing industry,and describe how our method can be adapted to meet the various ***,a multilevel method is proposed to make further improvements of the presented algorithm on both effectiveness and efficiency,in which the models are hierarchically segmented into the configurations of *** results show that SMED serves as a reasonable measurement of shape similarity for CAD models,and the proposed approach provides remarkable performance on a real-world CAD model database.

关键词： CAD model retrieval solid model edit distance graph edit distance boundary representation

来源：评论

学校读者我要写书评

暂无评论

Monocular LSD-SLAM integration within AR system: Building a system similar to the HoloLens by integrating LSD-SLAM into our AR Oculus Rift stereo engine for realworld camera tracking

arXiv

引用

arXiv 2017年

作者： Höll, Markus Lepetit, Vincent Inst. for Computer Graphics and Vision Graz University of Technology Austria

In this paper, we cover the process of integrating Large-Scale Direct Simultaneous Localization and Mapping (LSD-SLAM) [1] algorithm into our existing AR stereo engine, developed for our modified "Augmented Reality Oculus Rift". With that, we are able to track one of our realworld cameras which are mounted on the rift, within a complete unknown environment. This makes it possible to achieve a constant and full augmentation, synchronizing our 3D movement (x, y, z) in both worlds, the real world and the virtual world. The development for the basic AR setup using the Oculus Rift DK1 and two fisheye cameras is fully documented in our previous paper [2]. After an introduction to image-based registration, we detail the LSD-SLAM algorithm and document our code implementing our integration. The AR stereo engine with Oculus Rift support can be accessed via the GIT repository https: //***/MaXvanHeLL/*** and the modified LSD-SLAM project used for the integration is available here https://***/MaXvanHeLL/***. Copyright © 2017, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Robot Localisation and 3D Position Estimation Using a Free-Moving Camera and Cascaded Convolutional Neural Networks

arXiv

引用

arXiv 2018年

作者： Mišeikis, Justinas Knöbelreiter, Patrick Brijacak, Inka Yahyanejad, Saeed Glette, Kyrre Elle, Ole Jakob Torresen, Jim Department of Informatics University of Oslo Oslo Norway Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Joanneum Research - Robotics Klagenfurt am Wörthersee Austria Intervention Centre Oslo University Hospital Oslo Norway

— Many works in collaborative robotics and human-robot interaction focuses on identifying and predicting human behaviour while considering the information about the robot itself as given. This can be the case when sensors and the robot are calibrated in relation to each other and often the reconfiguration of the system is not possible, or extra manual work is required. We present a deep learning based approach to remove the constraint of having the need for the robot and the vision sensor to be fixed and calibrated in relation to each other. The system learns the visual cues of the robot body and is able to localise it, as well as estimate the position of robot joints in 3D space by just using a 2D color image. The method uses a cascaded convolutional neural network, and we present the structure of the network, describe our own collected dataset, explain the network training and achieved results. A fully trained system shows promising results in providing an accurate mask of where the robot is located and a good estimate of its joints positions in 3D. The accuracy is not good enough for visual servoing applications yet, however, it can be sufficient for general safety and some collaborative tasks not requiring very high precision. The main benefit of our method is the possibility of the vision sensor to move freely. This allows it to be mounted on moving objects, for example, a body of the person or a mobile robot working in the same environment as the robots are operating in. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Search and retrieval in CAD databases a user-centric state-of-the-art overview 12

Search and retrieval in CAD databases a user-centric state-o...

引用

12th International Joint Conference on computer Vision, Imaging and computer graphics Theory and Applications, VISIGRAPP 2017

作者： Schinko, Christoph Vosgien, Thomas Prante, Thorsten Schreck, Tobias Ullrich, Torsten Fraunhofer Austria Research GmbH Visual Computing Graz Graz Austria Institute of Computer Graphics and Knowledge Visualization Graz University of Technology Graz Austria V-Research GmbH Dornbirn Austria

ISBN: (纸本)9789897582240

This article presents a state-of-the-art overview on shape, information and design retrieval systems in the context of CAD engineering. In contrast to existing surveys, we classify the different approaches from a CAD application user point of view. As a consequence, we focus on features of surveyed techniques such as: Supported shape data types, handling of geometric invariances, support of metadata, supported query types, quality of retrieval results, and the availability of implementations. © 2017 by SCITEPRESS - Science and technology Publications, Lda.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

Unified models for second-order TV-type regularisation in imaging: A new perspective based on vector operators

arXiv

引用

arXiv 2018年

作者： Brinkmann, Eva-Maria Burger, Martin Grah, Joana Sarah Applied Mathematics: Institute for Analysis and Numerics Westfälische Wilhelms-Universität Münster Germany Department Mathematik Friedrich-Alexander Universität Erlangen-Nürnberg Germany Institute for Computer Graphics and Vision Graz University of Technology Austria

We introduce a novel regulariser based on the natural vector field operations gradient, divergence, curl and shear. For suitable choices of the weighting parameters contained in our model it generalises well-known firstand second-order TV-type regularisation methods including TV, ICTV and TGV2 and enables interpolation between them. To better understand the influence of each parameter, we characterise the nullspaces of the respective regularisation functionals. Analysing the continuous model, we conclude that it is not sufficient to combine penalisation of the divergence and the curl to achieve high-quality results, but interestingly it seems crucial that the penalty functional includes at least one component of the shear or suitable boundary conditions. We investigate which requirements regarding the choice of weighting parameters yield a rotational invariant approach. To guarantee physically meaningful reconstructions, implying that conservation laws for vectorial differential operators remain valid, we need a careful discretisation that we therefore discuss in detail. Copyright © 2018, The Authors. All rights reserved.

关键词： Mathematical operators

来源：评论

学校读者我要写书评

暂无评论

Efficient lossy compression of ultrasound data

Efficient lossy compression of ultrasound data

引用

IEEE International Symposium on Signal Processing and Information technology (ISSPIT)

作者： Petr Kleparnik Pavel Zemcik Jiri Jaros Department of Computer Graphics and Multimedia Department of Computer Systems Brno University of Technology Brno Czech Republic

Large-scale numerical simulations of high-intensity focused ultrasound (HIFU), important for model-based treatment planning, generate large amounts of data. Typically, it is necessary to save hundreds of gigabytes during simulation. We propose a novel algorithm for time varying simulation data compression specialized for HIFU. Our approach is especially focused on the on-the-fly parallel data compression during simulations. Now, we are able to compress 3D pressure time series of linear and nonlinear simulations with very acceptable compression ratios and errors (over 80 % of the space can be saved with an acceptable error). The proposed compression will be helpful for significant reduction of resources, such as storage space, network bandwidth, CPU time, etc., enabling better treatment planning using fast volume data visualizations. The paper describes the proposed method, its experimental evaluation, and comparison to the state of the art.

关键词： Harmonic analysis Ultrasonic imaging Data models Computational modeling Three-dimensional displays Acoustics Microsoft Windows

来源：评论

学校读者我要写书评

暂无评论

Web-Based Augmented Reality with Natural Feature Tracking and Advanced Rendering

Web-Based Augmented Reality with Natural Feature Tracking an...

引用

International Conference on New Trends in Computing Sciences (ICTCS)

作者： Mohammed A. Al-Zoube Department of Computer Graphics Princess Sumaya University for Technology (PSUT) Amman Jordan

ISBN: (纸本)9781538605288

Despite the existence of many well-designed augmented reality (AR) applications, most of these apps target specific hardware and platform, and few of them render virtual objects which are coherent with the real world. This paper presents an AR application with rendering effects that would increase the consistency between virtual and real world. The application adopts web-based technologies which enables it to run on different machines (mobile, PC) and platforms (windows, android, iOS) without modifications. The virtual objects are rendered with techniques such as cube mapping, and GLSL shaders to model various materials without the need for special setup or extra offline computations. Furthermore, the application uses natural feature tracking for image registration which makes it applicable for both indoor and outdoor scenarios. The results show that the application runs at real-time rates on PC browsers with significant improvement in the visual coherence of the final rendered scene, and at interactive rates on the mobile device.

关键词： Rendering (computer graphics) Feature extraction Cameras Augmented reality Three-dimensional displays Visualization

来源：评论

学校读者我要写书评

暂无评论

A secure contact protocol for delay tolerant networks

A secure contact protocol for delay tolerant networks

引用

International Conference on computer and Information Science (ACIS)

作者： Manghui Tu Kyle W. Riordan Geyang Xie Shuhui Yang Dept. Computer Information Technology & Graphics Purdue University Northwest Hammond IN USA

ISBN: (纸本)9781509055081

Current DTN systems are vulnerable to malicious attacks by compromised nodes taking advantage of the DTN protocols that control how nodes join and leave the backbone. Without addressing such security issues, DTN systems could result in performance degrade, the compromise of message confidentiality and integrity, and denial of service. Thus, effective mechanisms to identify and fix this vulnerability are urgently needed. The objective of this research is to address these issues by identifying DTN system vulnerabilities and potential threats, and providing potential countermeasures. We first illustrate vulnerabilities of the epidemic based contact history propagation protocol and then identify the potential threats to system performance, availability, and integrity as well as countermeasures to prevent such threats existing in DTN networks. A secure contact protocol is developed for DTN network with epidemic based contact history propagation protocol and simulations are conducted to assess its effectiveness on attack detection.

关键词： Peer-to-peer computing History Routing protocols Delays Security System performance

来源：评论

学校读者我要写书评

暂无评论

Simulation-assisted teaching of graduate students in transport: A case study of the application of acausal freeware *** to solution of Sakawa's open-loop optimal control problem for payload motion during crane boom rotation

引用

International Journal of Mechanical Engineering Education 2017年第1期45卷 3-27页

作者： Kostikov, Alexander A. Perig, Alexander V. Lozun, Ruslan R. Informatics and Engineering Graphics Department Donbass State Engineering Academy Donetsk Region Ukraine Manufacturing Processes and Automation Engineering Department Donbass State Engineering Academy Shkadinova 72 Kramatorsk Donetsk Region84313 Ukraine Computer and Information Technology Department Donbass State Engineering Academy Donetsk Region Ukraine

The present article is focused on the improvement of the quality of engineering education of graduate students with a major in transport and mechanical engineering through the derivation of a numerical solution of the optimal control problem for payload swaying during crane boom slewing, formulated by Sakawa et al. For the first time, a numerical solution of Sakawa's problem has been derived with an application of *** freeware. The fundamental difference between this solution and Sakawa's is the imposition of a restrictive constraint on the allowable value of payload swaying during boom-driven payload motion. The solution derived by the authors for Sakawa's problem takes exact account of the restrictive constraints on the phase variables in contrast to Sakawa's model, where the restriction constraints on the phase variables have been approximated. The complex of authors-proposed computational algorithms was implemented with ***. The proposed open-code algorithms derive numerical data and computational plots, which enhance and expand students' knowledge about the dynamics of guided boom-driven payload swaying during rotary crane boom slewing. © SAGE Publications.

关键词： Engineering education

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：