检索结果-内蒙古大学图书馆

virtual reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Yang Gao Hongming Bai Ziyi Pei Wenfeng Song Aimin Hao State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Computer School Beijing Information Science and Technology University Beijing China

We develope a VR-based watercolor painting system. The system generates paintings in the form of vector graphics, which remain clear under free scaling and panoramic projection in VR space. Meanwhile, in order to create a better operation experience and more convenient user interaction in the VR environment, we optimize the system to enable a variety of realistic watercolor effects and provide users with a number of optional painting settings such as color, size, effect, etc. After a short period of study, users can easily use the system to complete the VR painting experience.

关键词： Design engineering Three-dimensional displays Brushes Art Conferences virtual environments Color

来源：评论

学校读者我要写书评

暂无评论

Consider for Best Student Paper Award Model-Free Control for Quadrotor Attitude via Tent Map-Based Pigeon-Inspired Optimization

Consider for Best Student Paper Award Model-Free Control for...

引用

International Conference on Unmanned Aircraft systems (ICUAS)

作者： Yang Yuan Haibin Duan Chen Wei State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical Engineering Beihang University Beijing China Department of Mathematics and Theories Virtual Reality Fundamental Research Laboratory Peng Cheng Laboratory Shenzhen China

The attitude control problem of the quadrotor in the presence of disturbance and model uncertainty is studied in this paper. Firstly, a first-order filter is applied to generate the desired derivate of the reference signal. Then, a model-free adaptive attitude controller is designed for the condition that model parameters are not available. The discrete equation of the angular velocity is obtained by using the compact form dynamic linearization method, and the cascade controller is established based on the continuous kinematics and discrete dynamics. In addition, tent map-based pigeon-inspired optimization is designed to optimize the parameters of the filter and controller. Compared with original pigeon-inspired optimization, the premature problem can be effectively contained. Finally, the simulation results demonstrate the feasibility of the model-free attitude controller and the advantages of the Tent map-based pigeon-inspired optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User Perception Based label Layout for Efficient Target Localization in virtual Environment

SSRN

引用

SSRN 2024年

作者： Luan, Shuai Wu, Jian Zhou, Dong Ke, Wei Wang, Lili State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Faculty of Applied Sciences Macao Polytechnic University China

virtual reality (VR) technology provides users with an immersive experience in virtual environments. In target localization scenarios, labels are essential for guiding users to quickly identify and locate targets, thereby enhancing localization efficiency. However, the increasing complexity and volume of information in virtual environments often leads to label information overload and label visual clutter. To address these challenges, we propose a user perception-based label layout method to improve target localization efficiency. This method introduces the concept of object interest score, which dynamically quantifies user interest in scene objects over time and is used for label filtering. Additionally, a mapping function from label attributes to user-perceived time is constructed, allowing the estimation of how quickly a user can perceive a label. By leveraging both the object interest score and user-perceived time, we develop a user perception force-driven label layout optimization method. To evaluate the layout’s effectiveness, we propose a new metric, label perceived time cost, which measures the effort required for users to perceive the labels of objects of interest. User studies show that the proposed method significantly improves target localization efficiency, reduces task load, enhances usability, and minimizes sickness compared to traditional dynamic force-based label layouts. © 2024, The Authors. All rights reserved.

关键词： virtual environments

来源：评论

学校读者我要写书评

暂无评论

Augmented reality-based visual-haptic modeling for thoracoscopic surgery training systems

引用

virtual reality & Intelligent Hardware 2021年第4期3卷 274-286页

作者： Yonghang TAI Junsheng SHI Junjun PAN Aimin HAO Victor CHANG Yunnan Key Lab Optoelectronic Information Technology Yunnan Normal UniversityKunming 650500China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China School of Computing Engineering and Digital TechnologiesTeesside UniversityMiddlesbrough TS13BXUK

Background Compared with traditional thoracotomy,video-assisted thoracoscopic surgery(VATS)has less minor trauma,faster recovery,higher patient compliance,but higher requirements for *** surgery training simulation systems are important and have been widely used in Europe and *** reality(AR)in surgical training simulation systems significantly improve the training effect of virtual surgical training,although AR technology is still in its initial *** reality has gained increased attention in technology-driven modern medicine but has yet to be used in everyday *** This study proposed an immersive AR lobectomy within a thoracoscope surgery training system,using visual and haptic modeling to study the potential benefits of this critical *** content included immersive AR visual rendering,based on the cluster-based extended position-based dynamics algorithm of soft tissue physical ***,we designed an AR haptic rendering systems,whose model architecture consisted of multi-touch interaction points,including kinesthetic and pressure-sensitive ***,based on the above theoretical research,we developed an AR interactive VATS surgical training *** Twenty-four volunteers were recruited from the First People's Hospital of Yunnan Province to evaluate the VATS training ***,content,and construct validation methods were used to assess the tactile sense,visual sense,scene authenticity,and simulator *** The results of our construction validation demonstrate that the simulator is useful in improving novice and surgical skills that can be retained after a certain period of *** video-assisted thoracoscopic system based on AR developed in this study is effective and can be used as a training device to assist in the development of thoracoscopic skills for novices.

关键词： Augmented reality VATS Surgery training XPBD

来源：评论

学校读者我要写书评

暂无评论

Interactive Panoramic Ray Tracing for Mixed 360° RGBD Videos

Interactive Panoramic Ray Tracing for Mixed 360° RGBD Video...

引用

virtual reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Jian Wu Lili Wang Wei Ke State key laboratory of virtual reality technology and systems Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Macao Polytechnic University

This paper introduces an interactive panoramic ray tracing method for rendering real-time photo-realistic illumination and shadow effects when inserting virtual objects into 360° RGBD videos. First, we approximate the geometry of a real scene with a panoramic depth buffer and a screen space depth buffer. Then, a sparse sampling ray generation method is proposed to accelerate the tracing process by reducing the number of rays that need to be emitted in ray tracing. After this, an irradiance estimation pass is introduced to generate a noisy Monte-Carlo image. At last, the final result is smoothed by interpolation, spatial-temporal filtering, and differential rendering. We tested our method in some natural and synthetic scenes and compared the results of our approach with the ground truth and that of the Image-Based Lighting method. The results show that our method can generate visually photo-realistic frames for virtual objects in 360° RGBD videos in real-time, making the rendering results more natural and credible.

关键词： Three-dimensional displays Monte Carlo methods Lighting virtual reality Ray tracing User interfaces Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

EXPLORING DRIVING-AWARE SALIENT OBJECT DETECTION VIA KNOWLEDGE TRANSFER

EXPLORING DRIVING-AWARE SALIENT OBJECT DETECTION VIA KNOWLED...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Su, Jinming Xia, Changqun Li, Jia State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University China Peng Cheng Laboratory Shenzhen China Meituan

ISBN: (纸本)9781665438643

Recently, general salient object detection (SOD) has made great progress with the rapid development of deep neural networks. However, task-aware SOD has hardly been studied due to the lack of task-specific datasets. In this paper, we construct a driving task-oriented dataset where pixel-level masks of salient objects have been annotated. Comparing with general SOD datasets, we find that the cross-domain knowledge difference and task-specific scene gap are two main challenges to focus the salient objects when driving. Inspired by these findings, we proposed a baseline model for the driving task-aware SOD via a knowledge transfer convolutional neural network. In this network, we construct an attention-based knowledge transfer module to make up the knowledge difference. In addition, an efficient boundary-aware feature decoding module is introduced to perform fine feature decoding for objects in the complex task-specific scenes. The whole network integrates the knowledge transfer and feature decoding modules in a progressive manner. Experiments show that the proposed dataset is very challenging, and the proposed method outperforms 12 state-of-the-art methods on the dataset, which facilitates the development of task-aware SOD. © 2021 IEEE

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Semantic Segmentation Based on Fusion of Transformer and Lightweight Deeplabv3+

Remote Sensing Image Semantic Segmentation Based on Fusion o...

引用

International Conference on Guidance, Navigation and Control, ICGNC 2022

作者： Cao, Yuanyang Chen, Jian Xue, Zhentao Zhang, Zichao Hu, Gui College of Engineering China Agricultural University Beijing China Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities MNR Shanghai China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural Resources Shenzhen China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijng China

ISBN: (纸本)9789811966125

Aiming at the problems that the classification of remote sensing image datasets is not balanced so that the accuracy of semantic segmentation is not high and the segmentation effect of scarce samples is poor. Transformer encoder with multihead self-attention mechanism is integrated into Deeplabv3+ network, and the attention mechanism is used to enhance the ability to capture global information, so as to improve the precision requirement of scarce categories in remote sensing semantic segmentation task. The algorithm firstly uniformly crops high-resolution remote sensing images into low-resolution image information for batch training and reducing information loss. Secondly, MobileNetV2, a lightweight backbone feature extraction network, is used to replace Xception network of Deeplabv3+. Finally, Transformer encoder based on multihead self-attention mechanism is connected in series with atrous spatial pyramid pooling (ASPP) of Deeplabv3+ encoder region to increase its segmentation precision by enhancing feature learning of scarce category samples in deep feature information. The experimental result shows that the proposed model called TransDeeplabv3+ gets 67.67% mIoU and 81.86% mPA on GID remote sensing dataset. Compared with Deeplabv3+ model, mIoU and mPA are improved by 9.46% and 8.52% respectively. TransDeeplabv3+ can effectively increase the precision because of the ability of increasing attention to the scarce species samples and solve the problem of the decrease of segmentation accuracy due to unbalanced data categories. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Pigeon Inspired Optimization Based Multi-Uav Obstacle Avoidance Control

SSRN

引用

SSRN 2024年

作者： Wu, Hao Duan, Haibin State Key Laboratory of Virtual Reality Technology and Systems School of Autonomous Science and Electrical Engineering Beihang University Beijing100083 China Peng Cheng Laboratory Shenzhen518000 China

UAV formation collision avoidance control plays an important role in UAV (unmanned aerial vehicle) flight missions, and is a crucial technology in complex environments such as mountainous areas. Aiming at the collision avoidance control problem of UAV formation, a UAV formation control protocol is designed, which includes formation direction control component, flocking speed consistent control component, inter-aircraft formation control component, entity and the virtual leader’s speed consistent control component, obstacle avoidance component and height control component to control UAV formation for obstacle avoidance. Aiming at the difficulty of determining the control gain in formation control protocol, a hierarchical pigeon inspired optimization (HPIO) is proposed to optimize the control gain, including updating the original pigeon inspired optimization to divide the hierarchy, improving the compass operator stage and regenerating the solution in the local optimal case. Finally, the flight process of four UAVs and one virtual leader under complex obstacle environment is simulated, and the control strategies optimized by CPSO, PIO, PPPIO and PCHS-PIO are compared to verify the effectiveness of the proposed method. © 2024, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

MLLMReID: Multimodal Large Language Model-based Person Re-identification

arXiv

引用

arXiv 2024年

作者： Yang, Shan Zhang, Yongfei Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Multimodal large language models (MLLM) have achieved satisfactory results in many tasks. However, their performance in the task of ReID (ReID) has not been explored to date. This paper will investigate how to adapt them for the task of ReID. An intuitive idea is to fine-tune MLLM with ReID image-text datasets, and then use their visual encoder as a backbone for ReID. However, there still exist two apparent issues: (1) Designing instructions for ReID, MLLMs may overfit specific instructions, and designing a variety of instructions will lead to higher costs. (2) When fine-tuning the visual encoder of a MLLM, it is not trained synchronously with the ReID task. As a result, the effectiveness of the visual encoder fine-tuning cannot be directly reflected in the performance of the ReID task. To address these problems, this paper proposes MLLMReID: Multimodal Large Language Model-based ReID. Firstly, we proposed Common Instruction, a simple approach that leverages the essence ability of LLMs to continue writing, avoiding complex and diverse instruction design. Secondly, we propose a multi-task learning-based synchronization module to ensure that the visual encoder of the MLLM is trained synchronously with the ReID task. The experimental results demonstrate the superiority of our method. © 2024, CC BY-NC-ND.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance

arXiv

引用

arXiv 2024年

作者： Li, Yinglong Wu, Hongyu Wang, Xiaogang Qin, Qingzhao Zhao, Yijiao Wang, Yong Hao, Aimin State Key Laboratory of Virtual Reality Technology and Systems Beihang University China Peking University School Hospital of Stomatology China College of Computer and Information Science Southwest University China

We propose FaceCom, a method for 3D facial shape completion, which delivers high-fidelity results for incomplete facial inputs of arbitrary forms. Unlike end-to-end shape completion methods based on point clouds or voxels, our approach relies on a mesh-based generative network that is easy to optimize, enabling it to handle shape completion for irregular facial scans. We first train a shape generator on a mixed 3D facial dataset containing 2405 identities. Based on the incomplete facial input, we fit complete faces using an optimization approach under image inpainting guidance. The completion results are refined through a post-processing step. FaceCom demonstrates the ability to effectively and naturally complete facial scan data with varying missing regions and degrees of missing areas. Our method can be used in medical prosthetic fabrication and the registration of deficient scanning data. Our experimental results demonstrate that FaceCom achieves exceptional performance in fitting and shape completion tasks. The code is available at https://***/dragonylee/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Air navigation

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：