发布求助
文献互助 智能选刊 最新文献

Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1最新文献

筛选
英文 中文
Real-time video stylization using spatial-temporal gabor filtering 利用时空gabor滤波的实时视频风格化
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3013986
Rui Wang, Ping Li, Bin Sheng, Hanqiu Sun, E. Wu
{"title":"Real-time video stylization using spatial-temporal gabor filtering","authors":"Rui Wang, Ping Li, Bin Sheng, Hanqiu Sun, E. Wu","doi":"10.1145/3013971.3013986","DOIUrl":"https://doi.org/10.1145/3013971.3013986","url":null,"abstract":"This paper describes a new video stylization approach that achieves non-photorealistic rendering effects by using highly efficient spatial-temporal Gabor filtering. An edge extraction algorithm is developed to detect long coherent edges, to which the human visual system is sensitive. A nonlinear diffusion is then applied to remove unimportant details. Our approach extends the optical flow computation for constructing the Gabor flow to represent pixel similarity, and to preserve the temporal coherence when applied to video sequences. In particular, our video stylization is designed in a spatiotemporal manner to achieve temporal coherence in resulting animations. Real-time performance is achieved through the highly parallel implementation on modern graphics hardware (GPU). Therefore, our video stylization can be naturally applied to real-time video communication and interactive video-based rendering. The experimental results have demonstrated the high-quality production of our real-time video stylization.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128573677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
A novel method for short-time human activity recognition based on improved template matching technique 基于改进模板匹配技术的短时间人体活动识别新方法
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3014004
Benyue Su, Qingfeng Tang, Jing Jiang, Min Sheng, A. Yahya, Guangjun Wang
{"title":"A novel method for short-time human activity recognition based on improved template matching technique","authors":"Benyue Su, Qingfeng Tang, Jing Jiang, Min Sheng, A. Yahya, Guangjun Wang","doi":"10.1145/3013971.3014004","DOIUrl":"https://doi.org/10.1145/3013971.3014004","url":null,"abstract":"Traditional human activity recognition algorithms based on wearable sensors have a drawback in recognizing short-time samples. Due to, the instability of the traditional time and frequency features in short-time sample condition, the recognition results can be seriously affected. This paper proposes a new algorithm for human activity recognition based on improved template matching (ITM) for the short-time samples. Our proposed approach is based on four stages: First stage, we transform all longtime samples into short-time activity template with sliding window and structure over-completes training template set. Consequently, each kind of pattern of the activity will contain adequate atomic patterns. Second stage, we apply the short-time activity template instead of the unstable traditional features to describe the actions, where each activity template represents one short-time kinestate of the activity. Third stage, matching the short-time test sample with the over-complete training template set directly and calculate the residual between the test sample and each training template. Last stage, we determine the label of the test sample according to the smallest residual. In this paper all of the public WARD1.0 and our database are used to show the robustness of the proposed method under the conditions of using short-time samples (i.e., about 0.3s). In particular, the recognition rates which are based on the above two databases can reach to 96.1% and 96.8% respectively.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126838901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
A bio-inspired image local feature representation based on vision network model 基于视觉网络模型的仿生图像局部特征表示
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3014001
B. Lang, Y. Fan, Jing Huang
{"title":"A bio-inspired image local feature representation based on vision network model","authors":"B. Lang, Y. Fan, Jing Huang","doi":"10.1145/3013971.3014001","DOIUrl":"https://doi.org/10.1145/3013971.3014001","url":null,"abstract":"In this paper, a hierarchical network model based on human vision physiological mechanism was put forward. Firstly, simple cell and complex cell in primary visual cortex is modeled, then studied the response pattern of V4 area and inferior temporal cortex on ventral side channel and representing the local features of input image utilized the computational model. The experiment results show that local image features extracted by computational model have sufficient discrimination; furthermore, the local image features extracted using biological visual model demonstrated much more excellent generalization ability in natural scene with complicated background.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130889280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Real-time head pose estimation for driver assistance system using low-cost on-board computer 基于低成本车载计算机的驾驶员辅助系统实时头部姿态估计
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3014015
Chao Yin, Xubo Yang
{"title":"Real-time head pose estimation for driver assistance system using low-cost on-board computer","authors":"Chao Yin, Xubo Yang","doi":"10.1145/3013971.3014015","DOIUrl":"https://doi.org/10.1145/3013971.3014015","url":null,"abstract":"We propose a fast head pose estimation method using monocular video. It is highly optimized for on-board computers and for driving situations, which is applicable to existing low-cost on-board computer for cars and suitable for high real-time driver assistance systems. In our algorithm pipeline, the face detection step eliminates slow floating point computations using pixel intensity binary test, and reduce search scope effectively. In the face alignment step, we utilize the high performance of local binary feature and extend the single pose regression model to handle large rotations. The pose estimation step uses a mean rigid face model to calculate head pose fast by solving 2D-3D correspondence. To reduce computation further, we bypass or simplify pipeline steps using previous frame result, and redo the full pipeline adaptively. Experiments show our method is more efficient than existing approaches, which makes high real-time applications for on-board computers possible.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133883786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
A small scene assistant maintenance system based on optical see-through augmented reality 基于光学透视增强现实的小型场景辅助维护系统
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3014021
Yanfeng Tong, Yongtian Wang, Jing Chen, Chen Chen
{"title":"A small scene assistant maintenance system based on optical see-through augmented reality","authors":"Yanfeng Tong, Yongtian Wang, Jing Chen, Chen Chen","doi":"10.1145/3013971.3014021","DOIUrl":"https://doi.org/10.1145/3013971.3014021","url":null,"abstract":"We propose an assistant maintenance system for PC based on optical see-through AR. based on analysis the characteristics of small scene maintenance; barrier-free interaction and multi-level visualization were proposed. The system divided into motion perceptual, human-computer interaction, maintenance scene analysis, maintenance scene retrieval and visualization display. The augment reality system can be used to guide the users to operate the equipment step by step even without the professional skills. In order to test this system, we design some experiments and collect the experimental data to evaluate the efficiency of this system.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124854044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
A framework of face synthesis based on multilinear analysis 基于多线性分析的人脸综合框架
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3014026
Song Yuhao, Hui Zhang
{"title":"A framework of face synthesis based on multilinear analysis","authors":"Song Yuhao, Hui Zhang","doi":"10.1145/3013971.3014026","DOIUrl":"https://doi.org/10.1145/3013971.3014026","url":null,"abstract":"This paper addresses the problem of privacy protection in face synthesis. We propose a new face synthesis approach based on tensor decomposition. By using the mathematical properties of tensor analysis, we decompose a face image into multiple factors so that the synthesis process could concentrate only on privacy related information. Then, we generate a new face image by altering the privacy related factors and keeping the other ones untouched. Compared to previous algorithms, our approach has the advantage in producing a synthetic face image without the risk of privacy leaking. We conduct the experiments in different datasets and factors to show the flexibility of the proposed approach. After gaining the synthesis images, we apply the automatic recognition algorithms for both expressions and faces to them. The experiment results demonstrate the effectiveness of our approach.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"13 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125789823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Quad-tree spatial index for dynamic allocation of sea ice modeling in ice navigation simulator 海冰导航模拟器中海冰建模动态分配的四叉树空间索引
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3014014
Yuhao Sun, Yong Yin, Yicheng Jin, Shuai Gao
{"title":"Quad-tree spatial index for dynamic allocation of sea ice modeling in ice navigation simulator","authors":"Yuhao Sun, Yong Yin, Yicheng Jin, Shuai Gao","doi":"10.1145/3013971.3014014","DOIUrl":"https://doi.org/10.1145/3013971.3014014","url":null,"abstract":"Amount of sea ice models is necessary in ice region scene visualization in navigation simulator. If there is no scientific or effective space allocation method in the ice modeling process, it may cause huge waste of time and space resources, what would make the whole scene simulation system run with a poor real-time situation, for the reason of sea ice models in large quantities. This paper describes a quad-tree spatial index method to analyse and solve the sea ice modeling and allocation process in ice region scene system of navigation simulator. The results of the simulation show that it could reduce resources consumption of time and space, and optimize the visualization of sea ice scene what would improve the whole navigation simulation system fluency finally. It provides a foundation which could simulate the ice region scene in real-time and the ship-ice interaction process effectively as well.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130707060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
An accurate multi-sensor fusion measurement method for marker-free augmented reality system 面向无标记增强现实系统的多传感器精确融合测量方法
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3017426
Hang Dong, Fei Wang, Peilin Jiang
{"title":"An accurate multi-sensor fusion measurement method for marker-free augmented reality system","authors":"Hang Dong, Fei Wang, Peilin Jiang","doi":"10.1145/3013971.3017426","DOIUrl":"https://doi.org/10.1145/3013971.3017426","url":null,"abstract":"Augmented Reality has attracted more and more academic interests in recent years. Unfortunately there are few studies on designing a AR system for textureless target without markers. In order to break up the constraints of pre-defined markers, we propose a robust augmented reality system for textureless maker-free targets with high precision level. The performance of traditional vision-based reconstruction methods was limited when handling textureless targets. To improve this, we design a multi-sensor fusion system to reconstruct the textureless non-cooperative spherical target based on four simple lasers and a visual camera, which can provide accurate pose information for augmented reality without any depth sensor. The experiment results indicate that the our system can estimate the geometric parameters of textureless spherical target with high accuracy in real time and this method performs well on augmented reality application.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124268431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Modeling and simulation of the trawl in fishing simulator 拖网捕鱼模拟器的建模与仿真
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3013981
Shuai Gao, Yong Yin, Xiaofeng Sun, Helong Shen
{"title":"Modeling and simulation of the trawl in fishing simulator","authors":"Shuai Gao, Yong Yin, Xiaofeng Sun, Helong Shen","doi":"10.1145/3013971.3013981","DOIUrl":"https://doi.org/10.1145/3013971.3013981","url":null,"abstract":"The aim of the present study is to develop a numerical calculation method to accomplish dynamic simulation of the fishing nets in fishing simulator. Fishing nets were modeled as a group of lumped mass points interconnected with springs that have no mass under the uniform flow motion. Nonlinear dynamic equations of fishing nets were solved with the precise integration method. The position and velocity can be obtained by solving the net model. The comparison of the results of this study against associated experiment revealed the numerical method of nets model is reliable, while the real-time of simulation was ensured. This study shows that our method is valid for the simulation of fishing nets.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116117041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Motion simulation of wet cloth on contact surface considering air effects and humidity 考虑空气效应和湿度的湿布接触面运动仿真
Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1 Pub Date : 2016-12-03 DOI: 10.1145/3013971.3013985
Rui Wang, Shuangjiu Xiao
{"title":"Motion simulation of wet cloth on contact surface considering air effects and humidity","authors":"Rui Wang, Shuangjiu Xiao","doi":"10.1145/3013971.3013985","DOIUrl":"https://doi.org/10.1145/3013971.3013985","url":null,"abstract":"We present a physically based method to simulate the dynamic effects of wet cloth on contact surface under different humidity. In our dynamic calculation model, air pressure difference between two sides of the cloth is considered, which is influenced by the air permeability of cloth. We also present a new adsorption model derived from real-world measurements to calculate the friction more accurately. Contrary to previous methods, we take the effects of humidity into account, which may influence the calculation of air permeability and adhesion force. Experimental results show that our approach can accurately simulate different dynamic effects of wet cloth with different humidity.","PeriodicalId":269563,"journal":{"name":"Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry - Volume 1","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124525862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信