检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Jiang, Chenfanfu Qi, Siyuan Zhu, Yixin Huang, Siyuan Lin, Jenny Yu, Lap-Fai Terzopoulos, Demetri Zhu, Song-Chun SIG Center for Computer Graphics University of Pennsylvania UCLA Center for Vision Cognition Learning and Autonomy University of California Los Angeles United States Graphics and Virtual Environments Laboratory University of Massachusetts Boston UCLA Computer Graphics & Vision Laboratory University of California Los Angeles United States

We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms. In particular, we devise a learning-based pipeline of algorithms capable of automatically generating and rendering a potentially infinite variety of indoor scenes by using a stochastic grammar, represented as an attributed Spatial And-Or Graph, in conjunction with state-of-the-art physics-based rendering. Our pipeline is capable of synthesizing scene layouts with high diversity, and it is configurable inasmuch as it enables the precise customization and control of important attributes of the generated scenes. It renders photorealistic RGB images of the generated scenes while automatically synthesizing detailed, per-pixel ground truth data, including visible surface depth and normal, object identity, and material information (detailed to object parts), as well as environments (e.g., illuminations and camera viewpoints). We demonstrate the value of our synthesized dataset, by improving performance in certain machine-learning-based scene understanding tasks—depth and surface normal prediction, semantic segmentation, reconstruction, etc.—and by providing benchmarks for and diagnostics of trained models by modifying object attributes and scene properties in a controllable manner. Copyright © 2017, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Proposal of the Second Workshop on Physical and Social Scene Understanding 38

Proposal of the Second Workshop on Physical and Social Scene...

引用

38th Annual Meeting of the Cognitive Science Society: Recognizing and Representing Events, CogSci 2016

作者： Gao, Tao Jiang, Chenfanfu Zhu, Yixin Zhao, Yibiao Yu, Lap-Fai Department of Brain and Cognitive Sciences MIT Computer Graphics and Vision Lab UCLA United States Center for Vision Cognition Learning and Autonomy UCLA United States Graphics and Virtual Environments Lab University of Massachusetts Boston United States

来源：评论

学校读者我要写书评

暂无评论

Treatment of biased and dependent sensor data in graph-based SLAM

Treatment of biased and dependent sensor data in graph-based...

引用

International Conference on Information Fusion

作者： Benjamin Noack Simon J. Julier Uwe D. Hanebeck Intelligent Sensor-Actuator-Systems Laboratory (ISAS) Karlsruhe Institute of Technology (KIT) Germany Virtual Environments and Computer Graphics Group (VECG) University College London (UCL) United Kingdom

ISBN: (纸本)9781479974047

A common approach to attack the simultaneous localization and mapping problem (SLAM) is to consider factor-graph formulations of the underlying filtering and estimation setup. While Kalman filter-based methods provide an estimate for the current pose of a robot and all landmark positions, graph-based approaches take not only the current pose into account but also the entire trajectory of the robot and have to solve a nonlinear least-squares optimization problem. Using graph-based representations has proven to be highly scalable and very accurate as compared with traditional filter-based approaches. However, biased measurements as well as unmodeled correlations can lead to a sharp deterioration in the estimation quality and hence require careful consideration. In this paper, a method to incorporate biased or dependent measurement information is proposed that can easily be integrated into existing optimization algorithms for graph-based SLAM. For biased sensor data, techniques from ellipsoidal calculus are employed to compute the corresponding information matrices. Dependencies among noise terms are treated by a generalization of the covariance intersection concept. The treatment of both biased and correlated sensor data rest upon the inflation of the involved error matrices. Simulations are used to discuss and evaluate the proposed method.

关键词： Simultaneous localization and mapping Covariance matrices Joints Optimization Noise

来源：评论

学校读者我要写书评

暂无评论

A new probability distribution for simultaneous representation of uncertain position and orientation

A new probability distribution for simultaneous representati...

引用

International Conference on Information Fusion

作者： Igor Gilitschenski Gerhard Kurz Simon J. Julier Uwe D. Hanebeck Intelligent Sensor-Actuator-Systems Laboratory (ISAS) Karlsruhe Institute of Technology (KIT) Germany Department of Computer Science Virtual Environments and Computer Graphics Group

This work proposes a novel way to represent uncertainty on the Lie group of rigid-body motions in the plane. This is achieved by using dual quaternions for representation of a planar rigid-body motion and proposing a probability distribution from the exponential family of distributions that inherently respects the underlying structure of the representation. This is particularly beneficial in scenarios involving strong measurement noise. A relationship between the newly proposed distributional model and the Bingham distribution is discussed. The presented results involve formulas for computation of the normalization constant, the mode, parameter estimation techniques, and a closed-form Bayesian measurement fusion.

关键词： Quaternions Estimation Vectors Transmission line matrix methods Probability distribution Bayes methods Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Federated Filtering

Nonlinear Federated Filtering

引用

International Conference on Information Fusion

作者： Benjamin Noack Simon J. Julier Marc Reinhardt Uwe D. Hanebeck Intelligent Sensor-Actuator-Systems Laboratory (ISAS) Institute for Anthropomatics Karlsruhe Institute of Technology (KIT) Virtual Environments and Computer Graphics Group (VECG) Department of Computer Science University College London (UCL)

ISBN: (纸本)9781479902842

The federated Kalman filter embodies an efficient and easy-to-implement solution for linear distributed estimation problems. Data from independent sensors can be processed locally and in parallel on different nodes without running the risk of erroneously ignoring possible dependencies. The underlying idea is to counteract the common process noise issue by inflating the joint process noise matrix. In this paper, the same trick is generalized to nonlinear models and non-Gaussian process noise. The probability density of the joint process noise is split into an exponential mixture of transition densities. By this means, the process noise is modeled to independently affect the local system models. The estimation results provided by the sensor devices can then be fused, just as if they were indeed independent.

关键词： Federated Kalman Filter Nonlinear Estimation Distributed Estimation

来源：评论

学校读者我要写书评

暂无评论

SphereAvatar: A situated display to represent a remote collaborator 12

SphereAvatar: A situated display to represent a remote colla...

引用

30th ACM Conference on Human Factors in Computing Systems, CHI 2012

作者： Oyekoya, Oyewole Steptoe, William Steed, Anthony Virtual Environments and Computer Graphics Department of Computer Science University College London United Kingdom

ISBN: (纸本)9781450310154

An emerging form of telecollaboration utilizes situated or mobile displays at a physical destination to virtually represent remote visitors. An example is a personal telepresence robot, which acts as a physical proxy for a remote visitor, and uses cameras and microphones to capture its surroundings, which are transmitted back to the visitor. We propose the use of spherical displays to represent telepresent visitors at a destination. We suggest that the use of such 360° displays in a telepresence system has two key advantages: it is possible to understand the identity of the visitor from any viewpoint;and with suitable graphical representation, it is possible to tell where the visitor is looking from any viewpoint. In this paper, we investigate how to optimally represent a visitor as an avatar on a spherical display by evaluating how varying representations are able to accurately convey head gaze. Copyright 2012 ACM.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Recursive Estimation of Orientation Based on the Bingham Distribution

Recursive Estimation of Orientation Based on the Bingham Dis...

引用

International Conference on Information Fusion

作者： Gerhard Kurz Igor Gilitschenski Simon Julier Uwe D. Hanebeck Intelligent Sensor-Actuator-Systems Laboratory (ISAS) Institute of Anthropomatics Karlsruhe Institute of Technology (KIT) Virtual Environments and Computer Graphics Group Department of Computer Science University College London (UCL)

ISBN: (纸本)9781479902842

Directional estimation is a common problem in many tracking applications. Traditional filters such as the Kalman filter perform poorly in a directional setting because they fail to take the periodic nature of the problem into account. We present a recursive filter for directional data based on the Bingham distribution in two dimensions. The proposed filter can be applied to circular filtering problems with 180 degree symmetry, i.e., rotations by 180 degrees cannot be distinguished. It is easily implemented using standard numerical techniques and is suitable for real-time applications. The presented approach is extensible to quaternions, which allow tracking arbitrary three-dimensional orientations. We evaluate our filter in a challenging scenario and compare it to a traditional Kalman filtering approach.

关键词： Angular quantities Circular data Directional Statistics Recursive filtering

来源：评论

学校读者我要写书评

暂无评论

Short paper: Exploring the object relevance of a gaze animation model

Short paper: Exploring the object relevance of a gaze animat...

引用

3rd Joint virtual Reality Conference, JVRC 2011 of 17th Eurographics Symposium on virtual environments, EGVE 2011 and the 8th Conference of the European Association of virtual Reality and Augmented Reality, EuroVR 2011

作者： Oyekoya, O. Steed, A. Pan, X. Virtual Environments and Computer Graphics University College London United Kingdom

ISBN: (纸本)9783905674330

Models for animating the eyes of virtual characters often focus on making the face appear natural and believable. There has been relatively little work in computer graphics that investigates the relevance of the objects of interest (gaze targets). In this paper, a gaze animation model has been constructed that allocates visual attention to relevant targets from objects that are within the virtual character's field of view in an immersive 3D virtual environment. Relevance is determined by proximity, eccentricity, changes in orientation and velocity of objects in the virtual character's environment. In this paper, two tasks were designed to test the relevance of the objects selected by the gaze animation model during the tasks. Eye tracking data obtained from six human subjects provided benchmark data for measuring the efficiency of the model in picking relevant objects. The gaze animation model largely outperformed a random selection algorithm in predicting the real targets/objects of users' interests within the virtual environment. © The Eurographics Association 2011.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Practicing what we preach: IEEE VR 2009 virtual program committee meeting

Practicing what we preach: IEEE VR 2009 virtual program comm...

引用

作者： Lindeman, Robert W. Reiners, Dirk Steed, Anthony Human Interaction in Virtual Environments Lab Department of Computer Science Worcester Polytechnic Institute Worcester MA United States Center for Advanced Computer Studies University of Louisiana Lafayette LA United States Virtual Environments and Computer Graphics Group Department of Computer Science University College London London United Kingdom

This article reports on the experience of conducting the program committee (PC) meeting for the IEEE VR 2009 conference in Second Life. More than 50 PC members from around the globe met virtually over a two-day period to decide which papers to accept for presentation at the conference. Survey responses from 42 of the PC members indicate generally positive feelings toward this meeting format, although several alterations will help improve interaction between attendees in future meetings. © 2009 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Presence-enhancing real walking user interface for first-person video games

Presence-enhancing real walking user interface for first-per...

引用

2009 ACM SIGGRAPH Symposium on Video Games, Sandbox '09

作者： Steinicke, Frank Bruder, Gerd Hinrichs, Klaus Steed, Anthony Visualization and Computer Graphics Research Group Department of Computer Science University of Munster Einsteinstraße 62 48149 Munster Germany Virtual Environments and Computer Graphics Group Department of Computer Science University College London Gower Street London WC1E 6BT United Kingdom

ISBN: (纸本)9781605585147

For most first-person video games it is important that players have a high level of feeling presence in the displayed game environment. virtual reality (VR) technologies have enormous potential to enhance gameplay since players can experience the game immersively from the perspective of the player's virtual character. However, the VR technology itself, such as tracking devices and cabling, has until recently restricted the ability of users to really walk over long distances. In this paper we introduce a VR-based user interface for presence-enhancing gameplay with which players can explore the game environment in the most natural way, i. e., by real walking. While the player walks through the virtual game environment, we guide him/her on a physical path which is different from the virtual path and fits into the VR laboratory space. In order to further increase the VR experience, we introduce the concept of transitional environments. Such a transitional environment is a virtual replica of the laboratory environment, where the VR experience starts and which enables a gradual transition to the game environment. We have quantified how much humans can unknowingly be redirected and whether or not a gradual transition to a first-person game via a transitional environment increases the user's sense of presence. © 2009 ACM.

关键词： virtual reality

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：