检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Gao, Guangshuai Gao, Junyu Liu, Qingjie Wang, Qi Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Xueyuan Road Haidian District Beijing100191 China Hangzhou Innovation Institute Beihang University Hangzhou310051 China Northwestern Polytechnical University Xi’an Shanxi710072 China

Accurately estimating the number of objects in a single image is a challenging yet meaningful task and has been applied in many applications such as urban planning and public safety. In the various object counting tasks, crowd counting is particularly prominent due to its specific significance to social security and development. Fortunately, the development of the techniques for crowd counting can be generalized to other related fields such as vehicle counting and environment survey, if without taking their characteristics into account. Therefore, many researchers are devoting to crowd counting, and many excellent works of literature and works have spurted out. In these works, they are must be helpful for the development of crowd counting. However, the question we should consider is why they are effective for this task. Limited by the cost of time and energy, we cannot analyze all the algorithms. In this paper, we have surveyed over 220 works to comprehensively and systematically study the crowd counting models, mainly CNN-based density map estimation methods. Finally, according to the evaluation metrics, we select the top three performers on their crowd counting datasets and analyze their merits and drawbacks. Through our analysis, we expect to make reasonable inference and prediction for the future development of crowd counting, and meanwhile, it can also provide feasible solutions for the problem of object counting in other fields. We provide the density maps and prediction results of some mainstream algorithm in the validation set of NWPU dataset for comparison and testing. Meanwhile, density map generation and evaluation tools are also provided. All the codes and evaluation results are made publicly available at https://***/gaoguangshuai/survey-for-crowd-counting. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Co-Saliency detection with Co-Attention fully convolutional network

arXiv

引用

arXiv 2020年

作者： Gao, Guangshuai Zhao, Wenting Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Xueyuan Road Haidian District Beijing100191 China Hangzhou Innovation Institute Beihang University Hangzhou310051 China AI Lab of China Merchants Bank Shenzhen China

Co-saliency detection aims to detect common salient objects from a group of relevant images. Some attempts have been made with the Fully Convolutional Network (FCN) framework and achieve satisfactory detection results. However, due to stacking convolution layers and pooling operation, the boundary details tend to be lost. In addition, existing models often utilize the extracted features without discrimination, leading to redundancy in representation since actually not all features are helpful to the final prediction and some even bring distraction. In this paper, we propose a co-attention module embedded FCN framework, called as Co-Attention FCN (CA-FCN). Specifically, the co-attention module is plugged into the high-level convolution layers of FCN, which can assign larger attention weights on the common salient objects and smaller ones on the background and uncommon distractors to boost final detection performance. Extensive experiments on three popular co-saliency benchmark datasets demonstrate the superiority of the proposed CA-FCN, which outperforms state-of-the-arts in most cases. Besides, the effectiveness of our new co-attention module is also validated with ablation studies. Copyright © 2020, 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

Effects of long term isolation on the emotion change of ‘‘Lunar Palace 365” crewmembers

引用

Science Bulletin 2019年第13期64卷 881-884页

作者： Zikai Hao Yinzhen Zhu Siyuan Feng Chen Meng Dawei Hu Hui Liu Hong Liu Beijing Advanced Innovation Centre for Biomedical Engineering Beihang UniversityBeijing 102402China Institute of Environmental Biology and Life Support Technology School of Biological Science and Medical EngineeringBeihang UniversityBeijing 100083China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100083China International Joint Research Center of Aerospace Biotechnology & Medical Engineering. Beihang University Beijing 100083China

The psychological health risk is one of the most serious and difficult risks to mitigate during manned deep space exploration[1].In a space capsule or station,the environment is isolated,and communication with the outside is limited to telephone or delayed *** monotonous working schedule also aggravates loneliness and homesickness,which could trigger negative moods,such as depression and ***,an astronaut’s unstable emotional state could be a threat to the safety and performance of a space mission.

关键词： Effects schedule trigger most is be

来源：评论

学校读者我要写书评

暂无评论

A development and application of maintainability evaluation system using immersive VR 7

A development and application of maintainability evaluation ...

引用

7th International Multi-Conference on Engineering and technology Innovation 2018, IMETI 2018

作者： Wang, Meihui Li, Yongxiang Lyu, Chuan Liu, Xi School of Reliability and Systems Engineering Beihang University China State Key Laboratory of Virtual Reality Technology System Beihang University China Technology and Engineering Center for Space Utilization Chinese Academy of Science Beijing China Xi'An Modern Control Technology Research Institute Xi'an710065 China

Immersing into virtual reality (VR) is a perception of being physically present in a non-physical world. Using immersive VR in maintenance brings great conveniences. For example, using virtual human operating in hazardous environment before the real person, which can prevent being hurt. In this paper, a system of immersive virtual maintenance (IVM) is presented. It is divided into three parts. The first part is Input, which contains the maintenance task and maintenance design. The second part is Method, with which making the virtual human and the users act in a unified way. The key to build IVM system is the interface between the motion capture system and virtual simulation software. The third part is Output, which presents the maintainability evaluation results. This paper focuses on how to build IVM system, the difficulties and solutions also be detailed. At last, a simple application is given. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Maintainability

来源：评论

学校读者我要写书评

暂无评论

Advanced Robot Programming: a Review

引用

Current robotics Reports 2020年第4期1卷 251-258页

作者： Zhou, Zhongxiang Xiong, Rong Wang, Yue Zhang, Jiafan State Key Laboratory of Industrial Control Technology and Institute of Cyber-Systems and Control of Zhejiang Province Zhejiang University Hangzhou China Research Center China Robotics and Discrete Automation ABB Shanghai China

The review presents an overview of advanced robot programming approaches which aims to ease robot programming and speed up the deployment of industrial robots, and then some considerations are shared with respect to requirements in new trends of manufacturing. The new trend of customization along with Industry 4.0 is appearing which is a challenge for robotized systems. The bottleneck is mainly the efficiency of deployment of industrial robots because traditional programming methods are not intuitive and always time-consuming. Advanced robot programming techniques are expected to ease robot programming and make it accessible for non-experts. A review on advanced robot programming is here presented, firstly introducing the background of this research, followed by reviewing literatures in four categories: programming by demonstration for low-level motion, programming by demonstration for high-level task, speech recognition-based and augmented reality-based programming approaches, and finishing on discussing future works.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new thermal vibration mechanical shot peening residual stress strengthening equipment and its verification

引用

Measurement 2025年

作者： Nian-Pu Xue Qiong Wu Han-Jun Gao Zi-Han Gao Zhao-Jun Liu Yi-Du Zhang Jian Guo Yu Zhu Yin-Long Zhou State Key Laboratory of Virtual Reality Technology and Systems Beijing Engineering Technological Research Center of High-efficient & Green CNC Machining Process and Equipment School of Mechanical Engineering and Automation Beihang University Beijing City 100191 PR China Jingdezhen Research Institute of Beihang University Jingdezhen City 333000 PR China Beijing Aerospace Technology Research Institute Beijing City 100074 PR China AVIC Manufacturing Technology Institute Beijing City 100024 PR China Chongqing Fanghe Environmental Protection Technology Co. Ltd Chongqing City 401120 PR China

Compared to factors such as surface roughness, residual stress, particularly the compressive residual stress (CRS) amplitude and depth of CRS (D-CRS), is key factors influencing fatigue life. However, traditional mechanical shot peening (MSP) has limitations in enhancing the CRS effect. In this study, a novnel thermal vibration MSP (TVMSP) integrated equipment is developed to address this challenge. The equipment combines temperature, vibration, MSP, and electric control systems, enabling the regulation of residual stress through multi-energy coupling. The vibration frequency and dynamic stress response of the equipment are analyzed using both simulations and experiments. The results demonstrated that with the optimized excitation parameters, the validation TVMSP treatment increases the D-CRS by 27.27 % and the maximum CRS (MCRS) amplitude by 16.02 %, compared to traditional MSP. The TVMSP treated surface exhibits dimples and increases surface roughness caused by thermal softening rather than vibration deformation. The developed TVMSP equipment offers a new approach for residual stress regulation and provides a technical and equipment reference for enhancing the fatigue life of key aerospace components.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-robot coordinated exploration of indoor environments using semantic information

引用

Science China(Information Sciences) 2018年第7期61卷 247-257页

作者： Guangsheng LI Wusheng CHOU Fang YIN School of Mechanical Engineering and Automation Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing Key Laboratory of Advanced Nuclear Materials and Physics Beihang University

Dear editor,Multi-robot exploration of indoor environments is a fundamental problem in mobile robotics[1].In the context of multi-robot exploration,the main challenge is in achieving coordination among the robots such that they can be better distributed over the environment for simultaneously exploring different regions and avoiding interference with other robots[2,3].To date,many approaches

关键词： In Multi-robot coordinated exploration of indoor environments using semantic information DBSCAN Figure HMM

来源：评论

学校读者我要写书评

暂无评论

Real-Time 3D Hand Gesture Based Mobile Interaction Interface

Real-Time 3D Hand Gesture Based Mobile Interaction Interface

引用

IEEE International Symposium on Mixed and Augmented reality Workshops (ISMARW)

作者： Yunlong Che Yue Qi Yuxiang Song State Key Laboratory of Virtual Reality Technology and Systems Beijing Peng Cheng Laboratory Shenzhen Qingdao Research Institute of Beihang University Qingdao

ISBN: (纸本)9781728147666

Hand gesture recognition is a challenging problem for natural human-computer interaction(HCI). We address this problem by introducing a real-time human-mobile interaction interface with a depth sensor. Our interface consists of two components, 3D hand pose estimation and hand skeleton state based gesture description. Firstly, we propose a 3D hand pose estimation method that combines learning based pose initialization and physical based model fitting, which can estimate the per-frame's hand pose that appears in the depth camera's field of view. Afterwards, we map the estimated pose to gesture, e.g. open or close, through a hand skeleton state based method. With the tracked hand gesture, we can stably and smoothly implement common operations such as 'Touch', 'Grasp' and 'Hold' with mid-air interface. Our main contribution is combine 3D hand pose estimation and hand gesture tracking, and implementing an interaction application system with the details.

关键词： 3D hand pose estimation Hand gesture recognition Human-mobile interaction Augmented reality Interaction interface Gesture recognition Gestures augmented reality Hand pose estimation based

来源：评论

学校读者我要写书评

暂无评论

A survey on incorporating domain knowledge into deep learning for medical image analysis

arXiv

引用

arXiv 2020年

作者： Xie, Xiaozheng Niu, Jianwei Liu, Xuefeng Chen, Zhengsu Tang, Shaojie Yu, Shui The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Hangzhou Innovation Institute of Beihang University China Jindal School of Management The University of Texas Dallas United States School of Computer Science University of Technology Sydney Australia

Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area. To address this problem, researchers have started looking for external information beyond current available medical datasets. Traditional approaches generally leverage the information from natural images via transfer learning. More recent works utilize the domain knowledge from medical doctors, to create networks that resemble how medical doctors are trained, mimic their diagnostic patterns, or focus on the features or areas they pay particular attention to. In this survey, we summarize the current progress on integrating medical domain knowledge into deep learning models for various tasks, such as disease diagnosis, lesion, organ and abnormality detection, lesion and organ segmentation. For each task, we systematically categorize different kinds of medical domain knowledge that have been utilized and their corresponding integrating methods. We also provide current challenges and directions for future research. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A fast and accurate purification method of image feature point pairs using structural consistency constraints 8

A fast and accurate purification method of image feature poi...

引用

8th International Conference on Computing and Pattern Recognition, ICCPR 2019

作者： Zhai, Bo Liu, Ling Xian, Shu Zheng, Jin Zhao, Bo Hu, Hui-Biao Beijing Institute of Astronautical Systems Engineering China Academy of Launch Vehicle Technology No.1 Nandahongmen Road Fengtai District Beijing100076 China Space Systems Division Beiqing Road Haidian District Beijing100094 China State Key Laboratory of Virtual Reality Technology and Systems No. 37 Xueyuan Road Haidian District Beijing100191 China

ISBN: (纸本)9781450376570

Feature-based matching of images is a key method in pattern recognition, but due to noise, out-of-focus, similar texture, et. al., mismatched feature point pairs are usually generated, and easily result in the incorrect final results. Based on the linear transformation of image scenes, this paper proposes a fast and accurate purification method of matched feature point pairs using the structural consistency of the constructed matching Delaunay triangulations. The structural consistency is expressed and uantified from two aspects: distribution correspondence of the corresponding adjacent vertexes, and the similarity of the corresponding triangular units. By taking the two aspects as restraints, the mismatches are screened out and removed dynamically, which can improve the matching foundation and give better support for the further processing for images and targets. Representative images with different imaging platforms and environments are chosen for experimentation. Results show that compared with the existing classical methods, the proposed method has high accuracy, good robustness and fast computational speed for removing the mismatched feature point pairs. © 2019 Association for Computing Machinery.

关键词： Linear transformations

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：