检索结果-内蒙古大学图书馆

UKF‐MOT:An unscented Kalman filter‐based 3D multi‐object tracker

CAAI Transactions on Intelligence technology 2024年第4期9卷 1031-1041页

作者： Meng Liu Jianwei Niu Yu Liu Collective Intelligence&Collaboration Laboratory China North Artificial Intelligence and Innovation Research InstituteBeijingChina China North Vehicle Research Institute BeijingChina State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijingChina State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijingChina School of Computer Science and Engineering Beihang UniversityBeijingChina

Multi‐object tracking in autonomous driving is a non‐linear *** better address the tracking problem,this paper leveraged an unscented Kalman filter to predict the object's *** the association stage,the Mahalanobis distance was employed as an affinity metric,and a Non‐minimum Suppression method was designed for *** the detections fed into the tracker and continuous‘predicting‐matching’steps,the states of each object at different time steps were described as their own continuous *** conducted extensive experiments to evaluate tracking accuracy on three challenging datasets(KITTI,nuScenes and Waymo).The experimental results demon-strated that our method effectively achieved multi‐object tracking with satisfactory ac-curacy and real‐time efficiency.

关键词： autonomous vehicle transportation

来源：评论

学校读者我要写书评

暂无评论

Tracking dynamic flow: Decoding flow fluctuations through performance in a fine motor control task

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 891-902页

作者： Tian, Bohao Zhang, Shijun Chen, Sirui Zhang, Yuru Peng, Kaiping Zhang, Hongxing Wang, Dangxiao Tsinghua University Department of Psychology Beijing100084 China Beijing Institute of Life Omics Beijing102206 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Beihang University School of Mechanical Engineering and Automation Beijing100191 China Peng Cheng Laboratory Shenzhen518000 China

Flow, an optimal mental state merging action and awareness, significantly impacts our emotion, performance, and well-being. However, capturing its swift transitions on a fine timescale is challenging due to the sparsity of the existing flow detecting tools. Here we present a fine fingertip force control (F3C) task to induce flow, wherein the task challenge is set at a compatible level with personal skill, and to quantitatively track the flow state variations from synchronous motor control performance. We select eight performance metrics from fingertip force sequence and reveal their significant differences under distinct self-reported flow states. Further, we built a machine learning-based decoder that aims to predict the continuous flow intensity during the user experiment through the performance metrics, taking the self-reported flow as the label. Cross-validation shows that the predicted flow intensity reaches significant correlation with the self-reported flow intensity (r = 0.81). Based on the decoding results, we can capture the flow fluctuations during the intervals between sparse self-reporting probes. This study showcases the feasibility of tracking intrinsic flow variations with high temporal resolution using task performance measures and may serve as foundation for future work aiming to take advantage of flow's dynamics to enhance performance and positive emotions. © 2010-2012 IEEE.

关键词： Force Measurement Force Control Fluctuations Decoding Pressing Dynamics Affective Computing Transducers Real Time systems Flow Experience Intrinsic Fluctuations Fine Fingertip Force Control Task Performance Cross Validation Dynamics Task Performance Control Task Flow Dynamics Fine Control Flow Fluctuations Fine Motor Control Tasks Performance Metrics Volume Flow Flow Variables Personal Skills Force Control Finer Time Scales Synchronization Performance Paired T Test Prediction Error Cohens D Flow Meter Task Difficulty Target Range Random Permutations Power Spectral Density Analysis Flow Experience Experience Sampling Method Flow Probe Main Session Force Output Subjective Metrics Decoding Performance Target Force Decoding Accuracy

来源：评论

学校读者我要写书评

暂无评论

Light field depth estimation:A comprehensive survey from principles to future

引用

High-Confidence Computing 2024年第1期4卷 92-107页

作者： Tun Wang Hao Sheng Rongshan Chen Da Yang Zhenglong Cui Sizhe Wang Ruixuan Cong Mingyuan Zhao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Zhongfa Aviation Institute Beihang UniversityHangzhou 311115China Faculty of Applied Sciences Macao Polytechnic UniversityMacao 999078China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Light Field(LF)depth estimation is an important research direction in the area of computer vision and computational photography,which aims to infer the depth information of different objects in threedimensional scenes by capturing LF *** this new era of significance,this article introduces a survey of the key concepts,methods,novel applications,and future trends in this *** summarize the LF depth estimation methods,which are usually based on the interaction of radiance from rays in all directions of the LF data,such as epipolar-plane,multi-view geometry,focal stack,and deep *** analyze the many challenges facing each of these approaches,including complex algorithms,large amounts of computation,and speed *** addition,this survey summarizes most of the currently available methods,conducts some comparative experiments,discusses the results,and investigates the novel directions in LF depth estimation.

关键词： Light field Depth estimation Deep learning Sub-aperture image Epipolar-plane image

来源：评论

学校读者我要写书评

暂无评论

"dongba Script Character Construction Space": VR science-based interactive experience of pictographs in intangible cultural heritage 23

"dongba Script Character Construction Space": VR science-bas...

引用

2023 SIGGRAPH Asia 2023 XR, SA 2023

作者： Lu, Yulu Dai, Wensi Yan, Shuo School of New Media Art and Design Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

ISBN: (纸本)9798400703164

The "Dongba Script Character Construction Space"is an interactive science VR experience based on the Dongba script of the Naxi people in Yunnan Province, China, which provides an immersive virtual reality experience based on the traditional Yiyin script theory. [Selmanović et al., 2020] Specifically, this work combines the character construction characteristics of "pictogram", "simple ideographs"and "compound ideographs"to explore the meaning and visual symbolic characteristics of Naxi pictograms through three interesting forms of interaction, and provides more possibilities for the inheritance and development of Dongba in the future by using various forms of interaction. © 2023 Owner/Author.

关键词： virtual reality

来源：评论

学校读者我要写书评

暂无评论

Motion Control of Underwater Robot with Four Bionic Fin

Motion Control of Underwater Robot with Four Bionic Fin

引用

2023 IEEE International Conference on Unmanned systems, ICUS 2023

作者： Kang, Song Shi, Botong Chou, Wusheng School of Mechanical Engineering and Automation Beihang University Beijing China The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9798350316308

The shallow sea biological fishing robot is mainly used for the detection and fishing of marine products, with a wide and urgent application prospect. Due to the defects of spiral propulsion, a propulsion scheme of bionic fin propelling underwater robot for biological fishing in the shallow sea is introduced in this paper. Bionic fin propelling can also be used as a supplementary propulsion mode in the case of propeller damage. In this paper, a control algorithm based on central pattern generator (CPG) is presented on the basis of dynamic analysis. The simulation analysis is carried out for the vibration parameters of the fin, the force generated by the fin and the speed of the robot. Further, the swimming gait of the robot is planned. Finally, through experimental verification, the underwater robot can realize the movement function of each degree of freedom, and the propulsive force and movement speed are proven to be consistent with the theoretical and simulation analysis results. © 2023 IEEE.

关键词： Motion control

来源：评论

学校读者我要写书评

暂无评论

Foot-constrained spatial-temporal transformer for keyframe-based complex motion synthesis

Foot-constrained spatial-temporal transformer for keyframe-b...

引用

作者： Li, Hao Dai, Ju Zeng, Rui Bai, Junxuan Chen, Zhangmeng Pan, Junjun State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Mathematics and Theories Peng Cheng Laboratory Shenzhen China Institute of Artificial Intelligence in Sports Capital University of Physical Education and Sports Beijing China

keyframe-based motion synthesis holds significant effects in games and movies. Existing methods for complex motion synthesis often require secondary post-processing to eliminate foot sliding to yield satisfied motions. In this paper, we analyze the cause of the sliding issue attributed to the mismatch between root trajectory and motion postures. To address the problem, we propose a novel end-to-end Spatial-Temporal transformer network conditioned on foot contact information for high-quality keyframe-based motion synthesis. Specifically, our model mainly compromises a spatial-temporal transformer encoder and two decoders to learn motion sequence features and predict motion postures and foot contact states. A novel constrained embedding, which consists of keyframes and foot contact constraints, is incorporated into the model to facilitate network learning from diversified control knowledge. To generate matched root trajectory with motion postures, we design a differentiable root trajectory reconstruction algorithm to construct root trajectory based on the decoder outputs. Qualitative and quantitative experiments on the public LaFAN1, Dance, and Martial Arts datasets demonstrate the superiority of our method in generating high-quality complex motions compared with state-of-the-arts. © 2023 John Wiley & Sons, Ltd.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Research on Object Oriented Plan Management System modeling 18

Research on Object Oriented Plan Management System modeling

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Chang, Junjun Yang, Chao Xiao, Jin Southwest China Research Institute of Electronic Equipment Chengdu China Beihang University The State Key Lab of Virtual Reality Technology and Systems Beijing China

ISBN: (纸本)9798350312201

Under the background that the manufacturing industry is facing the digital transformation, the demand for business modeling is increasingly urgent. Only through business modeling can business processes, business rules and the authority and boundary of roles be sorted out, so as to solve the problem of "information island"among the information systems of various departments of the enterprise. There are many modeling languages/tools that can be applied to business modeling at home and abroad, including flowchart, Event-driven Process Chain(EPC), ICAM Definition Languages(IDEF), Business Process Model and Notation(BPMN) and Unified Modeling Language(UML), etc. Each of these languages/tools has its own advantages and disadvantages. Business modeling under the background of digital transformation is not limited to the traditional "description"of business processes and business rules, but more to find a modeling method, starting from the needs of the organization, step by step to "develop"a business system in line with the expectations of the organization;However, at present, the academic and industrial research on this aspect is very little. Inspired by the history of software development methodology shifting from a process-oriented to an object-oriented method, this paper considers business modeling based on UML and object-oriented method. There are many object-oriented modeling methods. Through research, we find that HarmonySE method can be applied to business modeling to meet the needs of business modeling under the background of digital transformation. Then, it details how to model a plan management system based on UML and HarmonySE methodologies on Astah Professional, a UML modeling tool. Finally, the advantages of business modeling based on UML and HarmonySE are described. © 2023 IEEE.

关键词： Unified Modeling Language

来源：评论

学校读者我要写书评

暂无评论

Refining Boundary Sample Space for Differentiable Rendering 16

Refining Boundary Sample Space for Differentiable Rendering

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Gao, Ruicheng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Jingdezhen Research Institute Beihang University Jingdezhen333000 China Qingdao Research Institute Beihang University Qingdao266104 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

The objective of physics-based differentiable rendering (PBDR) is to propagate gradients between scene parameters and the intensities of image pixels in a manner that is physically correct. The gradients obtained can be applied in optimization algorithms for the reconstruction of 3D geometry or materials, or they can be further propagated into neural network to learn neural representations of the scene. However, applying automatic differentiation techniques directly to the primary rendering process will result in biased gradients, as the rendering integral contains moving high-dimensional discontinuities. Based on how these discontinuities are managed-either implicitly or explicitly-existing PBDR methods can be categorized into two groups: reparameterization methods and boundary sampling methods. Boundary sampling methods need to construct paths that have one segment tangent to the geometry being differentiated in order to estimate a boundary integral to address the discontinuities explicitly. Such paths are usually constructed by sampling the tangent segment first and then extending it to complete the paths for subsequent processing. Fortunately, the number of dimensions in the space composed of such tangent segments is only three. In scenes comprised solely of triangle meshes, the first dimension is used to parameterize all the edges on the mesh, which determines a point on the tangent segment. The remaining two dimensions are used to parameterize the direction of the tangent segment. However, state-of-the-art boundary sampling methods parameterize the first dimension uniformly, which is inefficient because only a small portion of the edges contributes to the boundary integral, resulting in wasted parameter space. In this paper, we parameterize the first dimension by considering both edge length and contributions, thereby allocating more parameter space to important edges. Experiments demonstrate that our methods achieve lower variance gradients in the forward dif

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

A Multilayer Component Pane 3D Layout Frame Design for Responsive Websites

A Multilayer Component Pane 3D Layout Frame Design for Respo...

引用

2023 IEEE International Symposium on Mixed and Augmented reality Adjunct, ISMAR-Adjunct 2023

作者： Xu, Guohui Wang, Shan Hu, Yong Shen, Xukun Beihang University School of New Media Art and Design China Beihang University State Key Laboratory of Virtual Reality Technology and Systems China Yunnan Innovation Institute of Beihang University China

ISBN: (纸本)9798350328912

With a virtual reality (VR) head-mounted display (HMD), users can easily achieve immersive browsing. However, popular VR browsers use a virtual floating screen for web presentations, which severely limits the user experience. In this paper, we propose a responsive website based on Web VR and a 3D UI layout framework equipped with VR device features. The framework consists of two parts: Main Content and 3D Navigation. To test the usability of the framework, we designed an experimental prototype and conducted user tests with 24 participants. The experiments show that the framework can effectively improve the quality of the user experience when browsing the web in a virtual reality environment. The research shows the possible design direction of the user interface for presenting web pages in the future virtual environment. © 2023 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

An Immersive Layout Framework for Web Design in virtual reality

An Immersive Layout Framework for Web Design in Virtual Real...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing systems, CHI EA 2023

作者： Lu, Yu Hu, Yong Shen, Xukun Chen, Zhaojia School of New Media Art and Design Beihang University China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China Yunnan Innovation Institute Beihang University China

ISBN: (纸本)9781450394222

In recent years, many consumer-grade VR devices have emerged, and VR devices have the potential to become the next generation of terminals for visiting websites. Compared to traditional PC and mobile devices, VR moves away from the desktop concept and can show information in a 3D environment. This two-dimensional to three-dimensional transformation means that website layouts, media content, and interactions can make the user experience more immersive. Currently, VR users can visit websites through built-in or third-party browsers, but most website content and UI visuals are consistent with the desktop version instead of the VR version. The website has no separate visual and interactive designs for VR devices. Therefore, this paper analyzes the design elements from three aspects: spatial layout design of website hierarchical structures, presentation of multimedia contents, and interaction modes, and proposes a VR website design framework based on the fan-shaped layout using the spatial depth cue. Based on this design framework, we built a prototype of the VR version of the website in the context of the online museum website of intangible cultural heritage in Yunnan Province. We provided a reference for spatial layout and visual style design for developing the VR website. © 2023 Owner/Author.

关键词： Web Design

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：