检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Fu, Kui Shi, Peipei Song, Yafei Ge, Shiming Lu, Xiangju Li, Jia State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University Iqiyi Inc National Engineering Laboratory for Video Technology School of EE&CS Peking University Institute of Information Engineering Chinese Academy of Sciences

Large convolutional neural network models have recently demonstrated impressive performance on video attention prediction. Conventionally, these models are with intensive computation and large memory. To address these issues, we design an extremely light-weight network with ultrafast speed, named UVA-Net. The network is constructed based on depthwise convolutions and takes low-resolution images as input. However, this straight-forward acceleration method will decrease performance dramatically. To this end, we propose a coupled knowledge distillation strategy to augment and train the network effectively. With this strategy, the model can further automatically discover and emphasize implicit useful cues contained in the data. Both spatial and temporal knowledge learned by the high-resolution complex teacher networks also can be distilled and transferred into the proposed low-resolution light-weight spatiotemporal network. Experimental results show that the performance of our model is comparable to 11 state-of-the-art models in video attention prediction, while it costs only 0.68 MB memory footprint, runs about 10,106 FPS on GPU and 404 FPS on CPU, which is 206 times faster than previous models. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Seeking the Analytical Approximation of the Stance Dynamics of the 3D Spring-Loaded Inverted Pendulum Model By Using Perturbation Approach

Seeking the Analytical Approximation of the Stance Dynamics ...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Haitao Yu Shengjun Wang Kaizheng Shan Jun Li Lixian Zhang Haibo Gao State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China

The Spring-Loaded Inverted Pendulum (SLIP) has been widely exploited in both biomechanical and robotics research due to its simple form in mathematics and high accuracy in fitting experimental biology data. However the intrinsic nonlinearity of the SLIP dynamics makes accurate analytical representation unavailable. Traditional methods take advantage of numerical integration to handle this issue while several existing analytical approximations focusing on 2D-SLIP model. The 3D-SLIP suitable to physical reality is rarely investigated. This paper presents a novel perturbation-based approach to obtain the closed-form analytical approximations of the 3D-SLIP model in stance phase. In contrast to existing work ignoring the gravitational forces, the proposed approach just relies on assumptions of small leg compression and small leg swept angle. The performance of the derived approximations has been evaluated via comprehensive numerical analysis. The quality of accurate apex prediction promises the approximation as an advantageous and reliable tool for locomotion control of legged robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Control of Quadrotor Equipped with a Two DOF Robotic Arm 3

Control of Quadrotor Equipped with a Two DOF Robotic Arm

引用

3rd IEEE International Conference on Advanced robotics and Mechatronics, ICARM 2018

作者： Jiao, Ran Dong, Mingjie Ding, Rui Chou, Wusheng School of Mechanical Engineering and Automation Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9781538670668

The quadrotor equipped with a robotic arm has been applied to many fields recently. This paper deals with the problem of quadrotor stabilization and trajectory tracking equipped with a 2-DOF robotic arm. By considering the robotic arm as an independent part to affect the center of gravity (COG) of the vehicle, the kinematic and dynamic models are derived. The controller for the whole system is designed with two stages. First, a backstepping sliding mode controller is applied to position tracking (outer loop) and generating desired attitudes for inner loop. Then a backstepping controller with integral action is built for attitude stabilization (inner loop). In addition, a COG compensation system is developed for the controller to cope with the COG variation caused by movement of the robotic arm. Finally, several simulations demonstrate the effectiveness of the proposed control approaches. © 2018 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Simulation and Experimental Research on Transverse Random Vibration of Typical Valve for Launch Vehicle

引用

IOP Conference Series: Earth and Environmental Science 2021年第2期781卷

作者： Jing Song Zhen Guo Chao Xia Jiamin Zhao Hanjun Gao Beijing Institute of Astronautical Systems Engineering Beijing China State Key Laboratory of Virtual Reality Technology and Systems School of Mechanical Engineering and Automation Beihang University Beijing China Anhui HengLi Additive Manufacturing Technology Co. LTD. Wuhu China Anhui Chungu 3D Printing Institute of Intelligent Equipment and Industrial Technology Wuhu China

In order to effectively suppress the transverse random vibration of a class of irregular shape and structure valve for launch vehicle in the ground test, adopting the method of combining finite element simulation and experiment, the influence of different structure tools on the transverse vibration of the valve is investigated. Moreover, the impact of arrangement position of valve and semi-circular tool assembly on transverse vibration of valve is studied. Based on the analysis of the influence of tooling of different structures on the transverse random vibration of the valve, it is proposed that semi-circular fixture can effectively reduce the transverse vibration for this kind of valve. Furthermore, when placed in the center of vibration table or near the vibration source, can decrease transverse vibration of the valve remarkably.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-world Robot Reaching Skill Learning Based on Deep Reinforcement Learning

Real-world Robot Reaching Skill Learning Based on Deep Reinf...

引用

第32届中国控制与决策会议

作者： Naijun Liu Tao Lu Yinghao Cai Rui Wang Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology of the Chinese Academy of Sciences

Traditional programming method can achieve certain manipulation tasks with the assumption that robot environment is known and ***,with robots gradually applied in more domains,robots often encounter working scenes which are complicated,unpredictable,and *** overcome the limitation of traditional programming method,in this paper,we apply deep reinforcement learning(DRL) method to train robot agent to obtain skill *** policy trained with DRL on real-world robot is time-consuming and costly,we propose a novel and simple learning paradigm with the aim of training physical robot ***,our method train a virtual agent in an simulated environment to reach random target position from random initial ***,virtual agent trajectory sequence obtained with the trained policy,is transformed to real-world robot command with coordinate transformation to control robot performing reaching *** show that the proposed method can obtain self-adaptive reaching policy with low training cost,which is of great benefits for developing intelligent and robust robot manipulation skill system.

关键词： Robot reaching skill learning deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Large-Scale Scene Display System Based on WebGL

A Large-Scale Scene Display System Based on WebGL

引用

International Conference on virtual reality and Visualization (ICVRV)

作者： Wencong Jiang Yao Li Yue Qi State Key Laboratory of Virtual Reality Technology and Systems Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Qingdao Research Institute

ISBN: (纸本)9781538684986;9781538684979

In recent decades, computer vision has been a hot area of computer research while 3D reconstruction is one of the hot topics. With the improvement of 3D reconstruction theory and the rapid development of computer hardware technology, the reconstructed 3D models are enlarging in scale and increasing in complexity. Combining the aerial image of UAV with the 3D reconstruction of sequence images, it is of great value to carry out relevant research on the problem of 3D reconstruction of outdoor scenes. The fast rendering of these large-scale scene models is a challenge. At the same time, with the advancement of the HMTL5 specification, browsers have become more and more powerful, and WebGL has gradually gained support from more and more devices. The 3D rendering of the BS architecture will be the future direction of the rendering engine. The browser does not need to install the client program, which is convenient for users to access and process in any environment. Therefore, the large-scale scene display system based on web architecture is more convenient. In this paper, we designed a real-time display system for large-scale scenes, and studied WebGL based rendering frame techniques.

关键词： Rendering (computer graphics) Three-dimensional displays Load modeling Solid modeling Display systems Data models Adaptation models

来源：评论

学校读者我要写书评

暂无评论

KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing

KE-GAN: Knowledge Embedded Generative Adversarial Networks f...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition

作者： Mengshi Qi Yunhong Wang Jie Qin Annan Li State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Inception Institute of Artificial Intelligence UAE

In recent years, scene parsing has captured increasing attention in computer vision. Previous works have demonstrated promising performance in this task. However, they mainly utilize holistic features, whilst neglecting the rich semantic knowledge and inter-object relationships in the scene. In addition, these methods usually require a large number of pixel-level annotations, which is too expensive in practice. In this paper, we propose a novel Knowledge Embedded Generative Adversarial Networks, dubbed as KE-GAN, to tackle the challenging problem in a semi-supervised fashion. KE-GAN captures semantic consistencies of different categories by devising a Knowledge Graph from the large-scale text corpus. In addition to readily-available unlabeled data, we generate synthetic images to unveil rich structural information underlying the images. Moreover, a pyramid architecture is incorporated into the discriminator to acquire multi-scale contextual information for better parsing results. Extensive experimental results on four standard benchmarks demonstrate that KE-GAN is capable of improving semantic consistencies and learning better representations for scene parsing, resulting in the state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visual Topological Mapping and Navigation for Mobile Robot in Large-Scale Environment

Visual Topological Mapping and Navigation for Mobile Robot i...

引用

IEEE International Conference on robotics and Biomimetics

作者： Song Xu Huaidong Zhou Wusheng Chou School of Mechanical Engineering and Automation Beihang University Beijing China School of Mechanical Engineering and Automation State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

Autonomous navigation is a basic prerequisite for mobile robot to realize environmental exploration. Current navigation methods are mainly based on metric maps, which require precise geometric coordinates and lack the capability to efficiently store semantic information of the environment. In this paper, we present a visual topological mapping and navigation method for mobile robot in large-scale environment, which is similar to the human navigation system. Topological map represents the environment as a topology diagram with nodes and edges in which the topological nodes record local semantic information of the environment, such as visual features, robot pose and scene properties. In the topological navigation stage, an image-based Monte Carlo localization is proposed to estimate the semantic pose of robot which can help robot judge whether it has reached the target location more flexibility. Experiments are conducted in real world environments and results indicate that the proposed system exhibits great performance in robustness of navigation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Survey of recent progress in semantic image segmentation with CNNs

引用

Science China(Information Sciences) 2018年第5期61卷 107-124页

作者： Qichuan GENG Zhong ZHOU Xiaochun CAO State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University State Key Laboratory of Information Security Institute of Information EngineeringChinese Academy of Sciences

In recent years, convolutional neural networks(CNNs) are leading the way in many computer vision tasks, such as image classification, object detection, and face recognition. In order to produce more refined semantic image segmentation, we survey the powerful CNNs and novel elaborate layers, structures and strategies, especially including those that have achieved the state-of-the-art results on the Pascal VOC 2012 semantic segmentation challenge. Moreover, we discuss their different working stages and various mechanisms to utilize the structural and contextual information in the image and feature spaces. Finally, combining some popular underlying referential methods in homologous problems, we propose several possible directions and approaches to incorporate existing effective methods as components to enhance CNNs for the segmentation of specific semantic objects.

关键词： semantic image segmentation CNN Pascal VOC 2012 challenge multi-granularity features construction of contextual relationships

来源：评论

学校读者我要写书评

暂无评论

Facial Makeup Transfer Combining Illumination Transfer

arXiv

引用

arXiv 2019年

作者： Xin, J.I.N. Rui, H.A.N. Ning, Ning Li, Xiaodong Zhang, Xiaokun Department of Cyber Security Beijing Electronic Science and Technology Institute Beijing100070 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Department of Automation Tsinghua University Beijing100083 China

To meet the women appearance needs, we present a novel virtual experience approach of facial makeup transfer, developed into windows platform application software. The makeup effects could present on the userâĂZs ´ input image in real time, with an only single reference image. The input image and reference image are divided into three layers by facial feature points landmarked: facial structure layer, facial color layer, and facial detail layer. Except for the above layers are processed by different algorithms to generate output image, we also add illumination transfer, so that the illumination effect of the reference image is automatically transferred to the input image. Our approach has the following three advantages: (1) Black or dark and white facial makeup could be effectively transferred by introducing illumination transfer;(2) Efficiently transfer facial makeup within seconds compared to those methods based on deep learning frameworks;(3) Reference images with the air-bangs could transfer makeup perfectly. Copyright © 2019, The Authors. All rights reserved.

关键词： Application programs

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：