2018 International Conference on Virtual Reality and Visualization (ICVRV)最新文献_第4页

Gradient Domain Based Processing Method for Image Synthesis 基于梯度域的图像合成处理方法

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/ICVRV.2018.00029

Zhike Yi, Liang Liu, Jing Zhang, Shuai Li, A. Hao

{"title":"Gradient Domain Based Processing Method for Image Synthesis","authors":"Zhike Yi, Liang Liu, Jing Zhang, Shuai Li, A. Hao","doi":"10.1109/ICVRV.2018.00029","DOIUrl":"https://doi.org/10.1109/ICVRV.2018.00029","url":null,"abstract":"Digital image synthesis technology is an important technology in the field of computer graphics. It is widely used in various scenes such as digital image editing, film and television production, graphic design and so on. Gradient domain is an important concept in digital images. It can reflect the degree of variation of pixel values in each location of a digital image in its adjacent areas, and has a good perception effect on the edges of objects in digital images. Gradient-domain image synthesis method is an effective technique in the field of digital image synthesis. Its goal is to select a specific region from the source image and fuse it into the background image so that the images which before and after the fusion have no fusion traces. Vivid and natural. In this paper, the characteristics of digital image synthesis method based on gradient domain are analyzed. The Poisson clonal algorithm is used for image fusion. The characteristics of the core equations involved in Poisson clonal algorithm are studied. The equations are solved by combining the characteristics of coefficient matrix. The process is optimized and the solution of the linear equation is replaced by a Gaussian elimination method with a conjugate gradient method, which enables the digital image fusion process to be completed within a user-acceptable speed range.","PeriodicalId":159517,"journal":{"name":"2018 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"659 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113982140","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

Virtual Reassembly of Fractured Bones for Orthopedic Surgery 骨科手术中骨折的虚拟重组

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/ICVRV.2018.00012

Lei Wang, Junjun Pan, Qiangqiang Yao

{"title":"Virtual Reassembly of Fractured Bones for Orthopedic Surgery","authors":"Lei Wang, Junjun Pan, Qiangqiang Yao","doi":"10.1109/ICVRV.2018.00012","DOIUrl":"https://doi.org/10.1109/ICVRV.2018.00012","url":null,"abstract":"In orthopedic surgery, the traditional restoration of comminuted fracture basically relies on surgeon's manual work, which is usually intricate and error-prone. If fractured bones are poorly reassembled, the patient may suffer from more exposure to radiation and longer recovery time. More severely, some operation mistakes can cause sequela, such as joint dysfunction and infection. Therefore, orthopedic surgeons urgently need an intelligent assistance solution to improve the accuracy and reliability of fractured bones reassembly in procedure. This paper presents an automatic pipeline for virtual reassembly of fractured bones which are broken into pieces. It uses an intact bone as a template. We first reconstruct the 3D fractured bone from CT data using MIMICS. Then we analyze the shape structure of bone model through extracting key feature points and comparing descriptors. Finally, we search the correspondence between the fragments and template. The aligning is performed to ensure the fragments can join together. Compared with some semi-automatic reassembly methods for archaeological artifacts and forensic evidences, ours is fully automatic without human interactions and specialized to medical purposes. It can help orthopedic surgeons to make correct decisions in fractured bones reassembly.","PeriodicalId":159517,"journal":{"name":"2018 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127839109","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

Applicability Analysis on Three Interaction Paradigms in Immersive VR Environment 三种交互模式在沉浸式VR环境中的适用性分析

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/ICVRV.2018.00024

Zhuoran Li, Shiqi Zhang, M. Anwar, Junchang Wang

引用次数: 2

Physically-Based Algorithm for Natural Rime Growth Simulation 基于物理的自然雾凇生长模拟算法

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/icvrv.2018.00021

Ye Li, Meng Yang, Gang Yang

引用次数: 0

Aircraft Detection Based on Multiple Scale Faster-RCNN 基于多尺度快速rcnn的飞机检测

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/ICVRV.2018.00026

Wei Miao, Z. Luo

引用次数: 3

A Large-Scale Scene Display System Based on WebGL 基于WebGL的大规模场景显示系统

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/ICVRV.2018.00011

W. Jiang, Yao Li, Yue Qi

{"title":"A Large-Scale Scene Display System Based on WebGL","authors":"W. Jiang, Yao Li, Yue Qi","doi":"10.1109/ICVRV.2018.00011","DOIUrl":"https://doi.org/10.1109/ICVRV.2018.00011","url":null,"abstract":"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.","PeriodicalId":159517,"journal":{"name":"2018 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128409468","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 Secure and Efficient Face-Recognition Scheme Based on Deep Neural Network and Homomorphic Encryption 一种安全高效的基于深度神经网络和同态加密的人脸识别方案

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/ICVRV.2018.00017

Xiaodong Li, Qing Han, Xin Jin

{"title":"A Secure and Efficient Face-Recognition Scheme Based on Deep Neural Network and Homomorphic Encryption","authors":"Xiaodong Li, Qing Han, Xin Jin","doi":"10.1109/ICVRV.2018.00017","DOIUrl":"https://doi.org/10.1109/ICVRV.2018.00017","url":null,"abstract":"In recent years, with the maturity of face recognition technology, face recognition has been widely used in real life, raising concerns about the accuracy of face recognition results, the efficiency of face recognition and the safety of data. So we proposed a secure and efficient face-recognition scheme based on deep neural network and homomorphic encryption. The entire scheme is divided into two parts: the client and the server. The client obtains the face images. The server performs recognition. Face features are extracted using deep neural networks and then encrypted with the Paillier algorithm. The data of face features is transferred from the client to the server with encrypted mode and does not need to be decrypted in the entire recognition process. In the recognition process, we adopt a highly efficient secretive Hamming distance calculation method and introduce a parallel computing scheme to encrypt feature data and calculate the ciphertext Hamming distance, which greatly improves the recognition efficiency of the entire program. No messages are leaked between the client and the server on the entire scheme, which achieves the purpose of protecting privacy and security. Compared with the previous secure face recognition scheme, the experimental results show that we improve the accuracy of and the efficiency of recognition while ensuring security.","PeriodicalId":159517,"journal":{"name":"2018 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127926250","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: 3

A Robust Method for Hands Gesture Recognition from Egocentric Depth Sensor 一种基于自中心深度传感器的手势识别鲁棒方法

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/icvrv.2018.00015

Ye Bai, Yue Qi

引用次数: 1

NLQA Based Knowledge Search for Virtual Geographic Environment 基于NLQA的虚拟地理环境知识搜索

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/icvrv.2018.00019

B. Jiang, Liheng Tan, Xiaohui Chen, Wei Zhang

引用次数: 0

Skeleton Capsule Net: An Efficient Network for Action Recognition 骨架胶囊网:一种高效的动作识别网络

2018 International Conference on Virtual Reality and Visualization (ICVRV) Pub Date : 2018-10-01 DOI: 10.1109/ICVRV.2018.00022

Yue Yu, Niehao Tian, Xiangru Chen, Ying Li

引用次数: 1