检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Tan, Qingyang Gao, Lin Lai, Yu-Kun Yang, Jie Xia, Shihong Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences School of Computer Science & Informatics Cardiff University

Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components. However, these techniques suffer from fundamental limitations especially for meshes with noise or large-scale deformations, and may not always be able to identify important deformation components. In this paper we propose a novel mesh-based autoencoder architecture that is able to cope with meshes with irregular topology. We introduce sparse regularization in this framework, which along with convolutional operations, helps localize deformations. Our framework is capable of extracting localized deformation components from mesh data sets with large-scale deformations and is robust to noise. It also provides a nonlinear approach to reconstruction of meshes using the extracted basis, which is more effective than the current linear combination approach. Extensive experiments show that our method outperforms state-of-the-art methods in both qualitative and quantitative evaluations. Copyright © 2017, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

High-level activity recognition based on analysis of spatio-Temporal contexts

High-level activity recognition based on analysis of spatio-...

引用

2017 IEEE SmartWorld Ubiquitous Intelligence and computing, Advanced and Trusted Computed, Scalable computing and Communications, Cloud and Big Data computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017

作者： Lang, Ruixiang Ye, Jian Huang, Bin Sun, Yangwei Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China

ISBN: (纸本)9781538604342

High-level activity recognition (HAR) has got widely used in healthcare, recommendation, activity sensitive applications etc. Because of the complexity, diversity and individuality of high-level activity, researchers are faced with the challenge of increasing recognition accuracy under realistic conditions. In daily life, high-level activity has a strong association with spatial location since people are used to doing an activity in a specific location. Furthermore, some high-level activities usually co-occur in temporal sequence, which is supposed to be considered in activity inference. In this paper, we propose an approach of high-level activity recognition based on analysis of spatio-Temporal contexts. The approach extracts Region of Activity (ROA) from spatial locations and discovers Daily Activity Pattern (DAP) from temporal sequence of activities to support the design of classifiers of high-level activity. The experiments show that the proposed approach bring about promising performance improvements on activity recognition. The fusion of ROA and DAP gain an advantage over the existing work in accuracy. © 2017 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Footstep and motion planning in semi-unstructured environments using randomized possibility graphs

Footstep and motion planning in semi-unstructured environmen...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Michael X. Grey Aaron D. Ames C. Karen Liu School of Interactive Computing Georgia Institute of Technology Atlanta GA Mechanical and Civil Engineering & Control and Dynamical Systems California Institute of Technology Pasadena CA

Traversing environments with arbitrary obstacles poses significant challenges for bipedal robots. In some cases, whole body motions may be necessary to maneuver around an obstacle, but most existing footstep planners can only select from a discrete set of predetermined footstep actions; they are unable to utilize the continuum of whole body motion that is truly available to the robot platform. Existing motion planners that can utilize whole body motion tend to struggle with the complexity of large-scale problems. We introduce a planning method, called the “Randomized Possibility Graph”, which uses high-level approximations of constraint manifolds to rapidly explore the “possibility” of actions, thereby allowing lower-level motion planners to be utilized more efficiently. We demonstrate simulations of the method working in a variety of semi-unstructured environments. In this context, “semi-unstructured” means the walkable terrain is flat and even, but there are arbitrary 3D obstacles throughout the environment which may need to be stepped over or maneuvered around using whole body motions.

关键词： Manifolds Planning Navigation Legged locomotion Shape Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Traffic parameters prediction using a three-channel convolutional neural network 1

引用

2nd IFIP TC 12 International Conference on Intelligence Science, ICIS 2017

作者： Zang, Di Wang, Dehai Cheng, Jiujun Tang, Keshuang Li, Xin Department of Computer Science and Technology Tongji University Shanghai China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Department of Transportation Information and Control Engineering Tongji University Shanghai China Shanghai Lujie Electronic Technology Co. Ltd. PudongShanghai China

ISBN: (数字)9783319681214

ISBN: (纸本)9783319681207

Traffic three elements consisting of flow, speed and occupancy are very important parameters representing the traffic information. Prediction of them is a fundamental problem of Intelligent Transportation Systems (ITS). Convolutional Neural Network (CNN) has been proved to be an effective deep learning method for extracting hierarchical features from data with local correlations such as image, video. In this paper, in consideration of the spatiotemporal correlations of traffic data, we propose a CNN-based method to forecast flow, speed and occupancy simultaneously by converting raw flow, speed and occupancy (FSO) data to FSO color images. We evaluate the performance of this method and compare it with other prevailing methods for traffic prediction. Experimental results show that our method has superior performance. © IFIP International Federation for Information Processing 2017.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Using convolutional neural network with asymmetrical kernels to predict speed of elevated highway 1

引用

2nd IFIP TC 12 International Conference on Intelligence Science, ICIS 2017

作者： Zang, Di Ling, Jiawei Cheng, Jiujun Tang, Keshuang Li, Xin Department of Computer Science and Technology Tongji University Shanghai China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Department of Transportation Information and Control Engineering Tongji University Shanghai China Shanghai Lujie Electronic Technology Co. Ltd. Pudong Shanghai China

ISBN: (数字)9783319681214

ISBN: (纸本)9783319681207

In this paper, we present a deep learning based approach to performing the whole-day prediction of the traffic speed for the elevated highway. In order to learn the temporal features of traffic speed data in a hierarchical way, an improved convolutional neural network (CNN) with asymmetric kernels is proposed. Speed data are collected from loop detectors of Yan’an elevated highway of Shanghai. To test the performance of the presented method, we compare it with some conventional approaches of traffic speed estimation. Experimental results demonstrate that our method outperforms all of them. © IFIP International Federation for Information Processing 2017.

关键词： Speed

来源：评论

学校读者我要写书评

暂无评论

Verification of algorithm for point extraction from hyperbolic reflections in GPR data

Verification of algorithm for point extraction from hyperbol...

引用

International Workshop on Advanced Ground Penetrating Radar (IWAGPR)

作者： Aleksandar Ristić Željko Bugarinović Miro Govedarica Lara Pajewski Xavier Derobert Department for computing and control engineering University of Novi Sad Novi Sad Serbia Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Rome Italy IFFSTAR LUNAM University Bouguenais France

The main goal of this paper is to determine the characteristics of an algorithm for point extraction from hyperbolic reflections in Ground-Penetrating Radar (GPR) data with different acquisition settings. Analysis is performed on a series of experimental radargrams that were collected in real conditions, on the same location. Two district heating pipes DN250 in atrench, covered by compacted sand, were scanned and the acquisition was done by using a 900MHz antenna. The pipe depth and the axial distance were measured when the trench was open. Measured dimensions were then compared with the values obtained by the algorithm.

关键词： Ground penetrating radar Reflection Algorithm design and analysis Data mining Heating systems Artificial neural networks Civil engineering

来源：评论

学校读者我要写书评

暂无评论

Novel industrial robot sorting technology based on machine vision

Novel industrial robot sorting technology based on machine v...

引用

2017 9th International Conference on Modelling, Identification and control (ICMIC 2017)

作者： Chenyang Li Yibing Ma Shiyu Wang Feng Qiao the Image Processing Center School of AstronauticsBeihang University the Shenyang Institute of Computing Technology Chinese Academy of Sciences the Faculty of Information and Control Engineering Shenyang Jianzhu University

A traditional sorting system generally adopts teaching or off-line *** cannot make an adjustment at once when the work environment *** at the shortcomings of the traditional way of sorting,an industrial robot sorting system was investigated based on robot vision for Parallel robot and Cognex In – Sight 7000 series industrial intelligent *** system integrated the advantages of the visual system and the parallel robot *** make some corresponding improvements of classical Canny edge detection operator,and extract the image edge information as matching *** overcomes the impact of illumination on the visual *** visual system can automatically recognize position and classification information of objects when the sorting objects come into the camera view through the conveyor *** system significantly improves the robot's ability to adapt to the working environment,and the production efficiency,making the system more *** the same time,the experimental results show that the hardware and software design of the system is correct,and it has high sorting success rate.

关键词： Parallel Robot Machine Vision Canny Operator Sorting System Classification and Recognition

来源：评论

学校读者我要写书评

暂无评论

Trust Consensus Protocol for Heterogeneous Underwater Robotic Systems

Trust Consensus Protocol for Heterogeneous Underwater Roboti...

引用

作者： Mazdin, Petra Arbanas, Barbara Haus, Tomislav Bogdan, Stjepan Petrovic, Tamara Miskovic, Nikola University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Robotics and Intelligent Control Systems Croatia University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Underwater Systems and Technologies Croatia

In this paper we analyze the application of a binary trust-consensus protocol in multi-agent systems with switching communication topology. Trust represents belief of one agent that the other one is capable of executing a specific task. The approach is motivated by an underwater robot system in which robots, called aMussels, are dispersed in the environment and measure environmental properties (for example sea-current) over a longer period of time, with sensors which are prone to failures. The goal is to apply the binary trust-consensus protocol to enable the system to autonomously detect failures of aMussels. Since direct communication between aMussels is energy consuming, a new type of moving robot, called aFish, is introduced that serves as a carrier of information. Since aFish have a limited communication range, communication topology is switching. Simulations are run first in Matlab for a homogeneous system, and then in a realistic simulation environment for the described scenario with heterogeneous agents. Results show that the protocol converges to the correct trust values and that the convergence time depends on the connectivity of the communication graph. © 2016

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Nano-granular layers for sensor applications fabricated by means of electron beam induced deposition 6

Nano-granular layers for sensor applications fabricated by m...

引用

6. GMM-Workshops Mikro-Nano-Integration - 6th GMM Workshop on Micro-Nano-Integration

作者： Klauser, W. Bartenwerfer, M. Elfert, P. Krauskopf, E. Fatikow, S. Division Microrobotics and Control Engineering Department of Computing Science University of Oldenburg OldenburgD-26129 Germany

ISBN: (纸本)9783800742783

This work combines the Electron Beam induced Deposition technique with a purposeful scanning pattern generation for the scanning electron microscope by means of a self-developed scan generator. This allows for deposition of nanogranular metal structures with specific geometries, which can be used as strain sensors on the nano- and microscale. Furthermore, the deposition process is combined with a vision-based automation sequence using a self-developed software framework for drift compensation. © 2016 VDE VERLAG GMBH ∙ Berlin ∙ Offenbach

关键词：

来源：评论

学校读者我要写书评

暂无评论

Euclidean proximity function in image processing

Euclidean proximity function in image processing

引用

2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2016

作者： Stasik, Pawel M. Department of Control and Systems Engineering Faculty of Computing Science Poznán University of Technology Poznań Poland

ISBN: (纸本)9788362065271

In image processing measuring and valuing a distance between two points is important. The obtained values can be used for determining whether two points are close to each other or to define weights for a filter concentrated around a central element. While there are measures of proximity, neither of them was defined with a such use in mind, mostly concentrating on problem of an optimization. The idea is to turn the Euclidean distance between two points into a measure of how close (or far) two points are from each other, basing on two given ranges. The function was mostly obtained by a theoretical analysis supported with a mathematical calculation and examples of use. As it was proven in the work, the obtained function can be implemented not only to measure proximity, but also as a flexible kernel for image filters, allowing for blurring or edge-detection.

关键词： Edge detection

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：