检索结果-内蒙古大学图书馆

IEEE International Workshop on Imaging systems and Techniques (IST)

作者： Pengzhi Zhang Dangxiao Wang Yuru Zhang State Key Lab of Virtual Reality Technology and Systems Beihang University Beijing China

It is unknown that whether friction coefficients of materials can be predicted by their images. In this paper, we explore the correlation between the image gray-level and the friction coefficient of materials. We introduce a systematic approach to find the correlation model. First, four key features were extracted from Gray-Level Co-occurrence Matrix (GLCM) using Hue Saturation Intensity (HSI) color space. Second, BP neural network was utilized to establish the correlation model between the image gray-level and the friction coefficient. The proposed approach was validated using a dataset with 100 samples. The results show that the average regression error of the model is 16.7% for the 100 samples, and 2.8% for the subset of 30 fabric samples among the totals. Within those fabric samples, the prediction error for new samples is 20.1%. The experimental results indicate a possibility of inferring the friction coefficient from the image of the material. This study might provide a way of automatically constructing a haptic database through the large amount of images on the internet.

关键词： Instrumentation and measurement Two dimensional displays

来源：评论

学校读者我要写书评

暂无评论

A Speech Interaction Method in Immersive virtual Maintenance

A Speech Interaction Method in Immersive Virtual Maintenance

引用

2017 International Conference on Applied Mathematics, Modeling and Simulation (AMMS2017)

作者： Yuxue Jin Chuan Lv Jie Geng Di Peng State Key Laboratory of Virtual Reality Technology and System School of Reliability and Systems Engineering Beijing University of Aeronautics and Astronautics

Human-computer interaction, which involves interactive information processing, directly affects the vividness and immersion of virtual operation. Therefore, this paper aims to achieve the naturalization and intelligence of human-computer interaction. We present two language understanding models constructed by knowledge database and case database. Firstly, architecture of voice interactive system is generally introduced. And then, expression of operation object's feature information and fuzzy recognition of operator's intention are at a discussion. At end, experiments have been carried out to verify the significance. Based on the steps above, we develop a methodology of immersive virtual maintenance interaction based on speech interaction technology which can be more accurate and effective.

关键词： human-computer interaction speech recognition immersion virtual maintenance

来源：评论

学校读者我要写书评

暂无评论

Visual and textual sentiment analysis using deep fusion convolutional neural networks

arXiv

引用

arXiv 2017年

作者： Chen, Xingyue Wang, Yunhong Liu, Qingjie State Key Lab. of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Sentiment analysis is attracting more and more attentions and has become a very hot research topic due to its potential applications in personalized recommendation, opinion mining, etc. Most of the existing methods are based on either textual or visual data and can not achieve satisfactory results, as it is very hard to extract sufficient information from only one single modality data. Inspired by the observation that there exists strong semantic correlation between visual and textual data in social medias, we propose an end-to-end deep fusion convolutional neural network to jointly learn textual and visual sentiment representations from training examples. The two modality information are fused together in a pooling layer and fed into fully-connected layers to predict the sentiment polarity. We evaluate the proposed approach on two widely used data sets. Results show that our method achieves promising result compared with the state-of-the-art methods which clearly demonstrate its competency. Copyright © 2017, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A part-based and feature fusion method for clothing classification 17th

A part-based and feature fusion method for clothing classifi...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Huo, Pan Wang, Yunhong Liu, Qingjie State Key Laboratory of Virtual Reality Technology and System Beihang University Beijing100191 China

ISBN: (纸本)9783319488899

Clothing recognition and parsing have attracted substantial attention in computer vision community, which contribute to applications like scene recognition, event recognition, e-commerce, etc. In our work, a part-based and feature fusion method is proposed to classify clothing in natural scenes. Firstly, clothing is described with a partbased model, in which a Deformable Part based Model (DPM) and a key point regression method are used to locate the head-shoulder and human torso. Then, a novel Distinctive Efficient Robust Feature (DERF) and four other low-level features are extracted to represent human clothing. Finally, a feature fusion strategy is utilized to promote the classification performance. Experiments are conducted on a new and well labeled image dataset. The experimental results show the efficiency of our proposed method. © Springer International Publishing AG 2016.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Fast Local Stereo Matching with Effective Matching Cost and Robust Cost Aggregation

Fast Local Stereo Matching with Effective Matching Cost and ...

引用

Annual Conference of the IEEE Industrial Electronics Society

作者： Zhengrong Zhu Xiaoyong Lei State Key Lab. of Virtual Reality Technology and Systems Beihang University Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China

Stereo matching is extensively investigated in computer vision. This article is dedicated to local stereo matching based on adaptive support region for higher accuracy and speed. Firstly, we propose a novel cross-based and diamond-shaped sparse census transform with improved robustness and fastness compared with traditional methods. Secondly, an efficient computation of cost volume is proposed to accommodate diverse images. Once again, we improve the establishment of adaptive support region and ameliorate exponential step cost aggregation at the same time. At last, we achieve final disparity map by winner take all and disparity refinement. Experiments on Middlebury benchmark demonstrate our algorithm's better performance compared with other local methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction to: Automatic differentiation of Glaucoma visual field from non-glaucoma visual field using deep convolutional neural network

引用

BMC medical imaging 2019年第1期19卷 40页

作者： Fei Li Zhe Wang Guoxiang Qu Diping Song Ye Yuan Yang Xu Kai Gao Guangwei Luo Zegu Xiao Dennis S C Lam Hua Zhong Yu Qiao Xiulan Zhang Zhongshan Ophthalmic Center State Key Laboratory of Ophthalmology Sun Yat-sen University Guangzhou China. SenseTime Group Limited Hong Kong China. Guangdong key lab of Computer Vision & Virtual Reality Multimedia Research Center Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China. C-MER Dennis Lam Eye Hospital Shenzhen China. Department of Ophthalmology The First Affiliated Hospital of Kunming Medical University Kunming China. Department of Ophthalmology The First Affiliated Hospital of Kunming Medical University Kunming China. zhoculist@***. Guangdong key lab of Computer Vision & Virtual Reality Multimedia Research Center Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China. yu.qiao@***. Zhongshan Ophthalmic Center State Key Laboratory of Ophthalmology Sun Yat-sen University Guangzhou China. zhangxl2@***.

aa.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor optical remote sensing image registration based on Line-Point Invariant

Multi-sensor optical remote sensing image registration based...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xianmin Wang Qizhi Xu State Key Laboratory of Virtual Reality Technology and System Beihang University Beijing China

ISBN: (纸本)9781509033331

Due to the different imaging modalities and acquisition time, keypoint-based registration methods often suffer from false matches of keypoints while utilizing to register the optical remote sensing images from multi-sensors. In this paper, we proposed a novel method based on Line-Point Invariant for the multi-sensor image registration. First, the line segments of the images are extracted, and then the salient line segments are detected depending upon the adaptive confidence. Subsequently, conjugate salient lines between the two images are identified as the registration primitives by the probability relaxation labelling approach. Second, we obtain the SIFT keypoints of the images and establish the matches of the keypoints based on the Line-Point Invariant via dual matching. Consequently, false keypoint matches are greatly reduced and the correct match rate is significantly enhanced. The experiments conducted on various multi-sensor images demonstrate the effectiveness of the proposed method.

关键词： Image segmentation Optical sensors Remote sensing Image edge detection Optical imaging Image registration Mathematical model

来源：评论

学校读者我要写书评

暂无评论

A STRONG BILAYER APPEARANCE MODEL FOR HUMAN POSE ESTIMATION FROM A HIGH FREEDOM STILL IMAGE

A STRONG BILAYER APPEARANCE MODEL FOR HUMAN POSE ESTIMATION ...

引用

IEEE International Conference on Image Processing

作者： Chengyu Guo Songsong Ruan Xiaohui Liang State Key Lab. of Virtual Reality Technology and Systems Beihang University

ISBN: (纸本)9781467399623

Appearance model is widely used for image description and demonstrates an impressive performance in object detection. However, most appearance models can not be applied to more freedom object in still image, especially when dealt with variant objects whose shapes are modified by warping, rotation, etc. In this article, a simple but effective method to build a regional rotation-invariant feature descriptor is proposed to catch discriminative information of the variant human pose, which has a superior advantage when targets are in arbitrary orientations and slightly warping. Moreover, a mixture spatial model with visible parameters is then presented to differentiate the body structure and estimate the visible accurate position of each joint. The experiment results indicate that the proposed descriptor give near state-of-the-art performance on both handwritten digit recognition database and two public human motion databases containing athletes or pedestrians under certain different variations.

关键词： Human detection Pose estimation Bilayer appearance model Spatial prior distribution pose estimation Body Freedom STILL Posing image description Human Still images Object detection images Warping Pedestrians Descriptors

来源：评论

学校读者我要写书评

暂无评论

SCALING AND OCCLUSION ROBUST ATHLETE TRACKING IN SPORTS VIDEOS

SCALING AND OCCLUSION ROBUST ATHLETE TRACKING IN SPORTS VIDE...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Jianghu Lu Di Huang Yunhong Wang Longteng Kong State Key Lab. of Virtual Reality Technology and Systems Beihang University Beijing 100191 China

ISBN: (纸本)9781479999897

This paper proposes a novel approach to athlete tracking in sports videos. It follows the framework of Compressive Tracking (CT), but extends it by two manners, i.e. scale refinement as well as occlusion recovery. For the former, an objectness method, namely Edge Box (EB) is adopted to generate proposals, replacing the fixed sampling box in CT, which better fits the scales of the candidate objects. For the latter, a candidate obstruction based solution is presented, which makes use of additional trackers to detect possible obstructions especially the ones possessing highly similar appearances as the target one, and relocate the target as occlusion ends. Therefore, the proposed method inherits the advantage of CT in robust object modelling and fast processing speed, and embodies the tolerance to occlusion and scaling. We evaluate the proposed method on a collection of videos of beach volleyball games, and the experimental results and the comparison with recent advanced trackers highlight its effectiveness.

关键词： Object tracking Occlusion Scaling Sports Video Analysis

来源：评论

学校读者我要写书评

暂无评论

Real-time Simulation of Airborne FLIR Sensor

Real-time Simulation of Airborne FLIR Sensor

引用

2016 IEEE Chinese Guidance, Navigation and Control Conference (IEEE CGNCC2016)

作者： Guanfeng Yu Guofeng Zhang State Key Laboratory of Virtual Reality Technology and System/Aircraft Control Integration Technology Laboratory/School of Automation Science and Electrical Engineering Beihang University

ISBN: (纸本)9781467383196

The work presented in this paper focuses on real-time simulation of the airborne forward looking infrared(FLIR) sensor typically configured by modern *** on infrared radiation theoretic model,the infrared transmittance model of "target-background-atmosphereimaging system" is ***,using modern computer graphics hardware,the detection signal is output in real time through the interacting of the virtual environment,which is the working process of sensors in actual infrared *** results shows that the platform can dynamically and efficiently generate realistic infrared images of helicopter varying with different simulation *** dynamic simulation of large scale infrared scene can enhance the situational awareness for pilot.

关键词： image Sensor Real-time Simulation of Airborne FLIR Sensor

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：