2021 IEEE 7th International Conference on Virtual Reality (ICVR)最新文献_第2页

Research on Real-Time Rendering of Reflection Caustics in Water Scenes 水景反射焦散的实时渲染研究

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483863

Huiling Guo, Sai Wang, Yong Tang, Ying Li, Jing Zhao

{"title":"Research on Real-Time Rendering of Reflection Caustics in Water Scenes","authors":"Huiling Guo, Sai Wang, Yong Tang, Ying Li, Jing Zhao","doi":"10.1109/ICVR51878.2021.9483863","DOIUrl":"https://doi.org/10.1109/ICVR51878.2021.9483863","url":null,"abstract":"To compensate for the lack of water surface reflection caustics in the real-time rendering of water scenes, a method for simulating the water surface reflection caustics is proposed. Firstly, the model of water surface height field is constructed by introducing the Inverse Fast Fourier Transform, and the reflection calculation area of the water surface light is reduced by using the space division method. Secondly, considering the angle of the reflected light to the surface of the object, the positional relationship between the sunlight and the hull, as well as other factors, the value of the reflected light received at the sampling point is calculated. For the lack of projection occlusion, the technology of rendering to texture is introduced to improve the traditional method of the projection texture, and draw the occluded texture details. Finally, a large number of experimental results are compared with real photographs and related literature. The results demonstrate that the proposed method can effectively simulate the reflection caustic effect of the water surface, increase the details and the realism, and meet the real-time efficiency.","PeriodicalId":266506,"journal":{"name":"2021 IEEE 7th International Conference on Virtual Reality (ICVR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131981514","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

VR Technology and Application in Martial Arts VR技术及其在武术中的应用

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483700

Zeng Yuqing, Mingliang Cao, H. Zhang, Zhong Yong

引用次数: 2

Motion Estimation with L0 Norm Regularization 基于L0范数正则化的运动估计

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483834

Jun Chen, Zemin Cai, Xiaohua Xie, Jianhuang Lai

{"title":"Motion Estimation with L0 Norm Regularization","authors":"Jun Chen, Zemin Cai, Xiaohua Xie, Jianhuang Lai","doi":"10.1109/ICVR51878.2021.9483834","DOIUrl":"https://doi.org/10.1109/ICVR51878.2021.9483834","url":null,"abstract":"In this paper, we proposed a novel variational optical flow model with L0 norm regularization, which uses a sparse flow gradient counting scheme, and can globally control how many non-zero flow gradients are preserved to recover important motion structures in a sparsity-control manner. It is particularly effective for enhancing major flow edges while eliminating a manageable degree of low-amplitude motion structures to control smoothing and reduce oversegmentation artifacts. Different from other edge-preserving smoothing regularizers, it does not depend on local motion features, but locates important flow edges globally. It will not cause edge blurriness due to avoiding local filtering or average operation, and can preserve salient motion structures, even small-scale motion structures with high contrast can be preserved remarkably well. Benefited from the advantages of L0 norm regularization, the proposed optical flow method shows outstanding performance in sharpening major flow edges, flattening insignificant motion details to control smoothing and reduce oversegmentation artifacts while preserving fine-scale motion structures with high contrast. It also achieves good performance on the Middlebury dataset.","PeriodicalId":266506,"journal":{"name":"2021 IEEE 7th International Conference on Virtual Reality (ICVR)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122329849","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

Research on Swimming Training Based on Numerical Simulation and VR Technology 基于数值模拟和VR技术的游泳训练研究

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483864

Zhiya Chen, Tianzeng Li, Jin Yang

引用次数: 0

Evaluating an Augmented Reality-Based Partially Assisted Approach to Remote Assistance in Heterogeneous Robotic Applications 评估基于增强现实的部分辅助方法在异构机器人应用中的远程辅助

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483849

D. Calandra, Alberto Cannavò, F. Lamberti

{"title":"Evaluating an Augmented Reality-Based Partially Assisted Approach to Remote Assistance in Heterogeneous Robotic Applications","authors":"D. Calandra, Alberto Cannavò, F. Lamberti","doi":"10.1109/ICVR51878.2021.9483849","DOIUrl":"https://doi.org/10.1109/ICVR51878.2021.9483849","url":null,"abstract":"Among the countless applications of Augmented Reality (AR) in the industry, remote assistance represents one of the most prominent and widely studied use cases. Recently, the way in which assistance can be delivered started to evolve, unleashing the full potential of such technology. New methodologies have been proposed able to foster operators’ autonomy and reduce under-utilization of skilled human resources. This paper studies the effectiveness of a recently proposed approach to AR-based remote assistance, referred to as partially assisted, which differs from the traditional step-by-step guidance in the way the AR hints are conveyed by the expert to the operator. The suitability of this approach has been proved already for a number of simple industrial tasks, but a comprehensive study has yet to be performed for validating its effectiveness in complex use cases. This paper addresses this lack by considering as a case study the mastering of a robotic manipulator, a procedure involving a number of heterogeneous operations. The performance of the partially assisted approach is compared with step-by-step guidance based on both objective and subjective metrics. Results showed that the former approach could be particularly effective in reducing the time investment for the expert, allowing the operator to autonomously complete the assigned task in a time comparable to traditional assistance with a negligible need for further support.","PeriodicalId":266506,"journal":{"name":"2021 IEEE 7th International Conference on Virtual Reality (ICVR)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116806233","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

Real-Time Instance Segmentation Tracking Algorithm in Mixed Reality 混合现实中的实时实例分割跟踪算法

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483810

Dengsha Yu, Zifei Yan, Baolin Ming

{"title":"Real-Time Instance Segmentation Tracking Algorithm in Mixed Reality","authors":"Dengsha Yu, Zifei Yan, Baolin Ming","doi":"10.1109/ICVR51878.2021.9483810","DOIUrl":"https://doi.org/10.1109/ICVR51878.2021.9483810","url":null,"abstract":"In a mixed reality environment, in order to complete the interaction of manipulating virtual items with physical wooden sticks, a real-time and accurate object tracking algorithm is needed. Therefore, we design a fast, pixel-wised object tracking model to quickly and accurately segment wooden sticks in each frame. The model consists of two parts: The first part is an object detection model, which is responsible for identifying and detecting the bounding box of the object in the first frame; The second part is the instance segmentation model, which uses the bounding box of the object obtained in the previous frame and the current frame’s image features (extracted by the convolutional neural networks) to calculate the object boundary points in the current frame. In addition, we use dynamic convolutions in the CNNs to increase the representation capacity of the feature extraction parts without increasing the depth or width of the network. Experiments show that under the task of tracking stick objects in a mixed reality environment, our method achieves competitive performance in real-time running speed and segmentation quality.","PeriodicalId":266506,"journal":{"name":"2021 IEEE 7th International Conference on Virtual Reality (ICVR)","volume":"60 31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131070240","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

An Improved YOLOv3 Object Detection Network for Mobile Augmented Reality 一种改进的YOLOv3移动增强现实目标检测网络

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483829

Quanyu Wang, Zhi Wang, Bei Li, Dejian Wei

{"title":"An Improved YOLOv3 Object Detection Network for Mobile Augmented Reality","authors":"Quanyu Wang, Zhi Wang, Bei Li, Dejian Wei","doi":"10.1109/ICVR51878.2021.9483829","DOIUrl":"https://doi.org/10.1109/ICVR51878.2021.9483829","url":null,"abstract":"With the spread of mobile devices such as mobile phones, MAR(Mobile augmented reality), which is a technology that realizes augmented reality on mobile devices, is becoming one of the most popular directions in augmented reality research. In MAR, the capturing and positioning of target objects, that is, tracking and registration technology is a crucial problem. In mobile devices, tracking registration technologies that use cam-eras as tracking sensors are divided into hardware sensor-based and computer vision-based tracking registration technologies. Compared with the former, the latter has the characteristics of low hardware equipment requirements and high accuracy. However, traditional computer vision-based tracking registration technologies are susceptible to factors such as background environment, distance, and angle. To overcome the weakness, our research combines the development of deep learning in the field of object detection and lightens YOLOV3 network, which includes simplifying the network structure, improving multi-scale feature fusion detection, optimizing the dimensions of candidate frames through clustering, and optimizing the loss function, so that the object detection network can be used on mobile devices with guaranteed accuracy, and reduces the influence of background environment and other factors on the visual tracking registration technology. Our research realizes a mobile augmented reality system based on the IOS system, which achieves state-of-the-art performance.","PeriodicalId":266506,"journal":{"name":"2021 IEEE 7th International Conference on Virtual Reality (ICVR)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122832350","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

Virtual Reality Training Environment for Electric Systems 电气系统虚拟现实训练环境

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483825

Zhenjun Jiang, Yang Yang, Qingshu Yuan, Pengfei Leng, Yanyan Liu, Zhigeng Pan

引用次数: 2

An Improved GRU Network for Human Motion Prediction 一种改进的GRU网络用于人体运动预测

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483851

Weijie Yu, R. Liu, D. Zhou, Qiang Zhang, Xiaopeng Wei

引用次数: 1

Autonomous Landing Point Retrieval Algorithm for UAVs Based on 3D Environment Perception 基于三维环境感知的无人机自主着陆点检索算法

2021 IEEE 7th International Conference on Virtual Reality (ICVR) Pub Date : 2021-05-20 DOI: 10.1109/ICVR51878.2021.9483840

Zhanpeng Gan, Huarong Xu, Yuanrong He, W. Cao, Guanhua Chen

{"title":"Autonomous Landing Point Retrieval Algorithm for UAVs Based on 3D Environment Perception","authors":"Zhanpeng Gan, Huarong Xu, Yuanrong He, W. Cao, Guanhua Chen","doi":"10.1109/ICVR51878.2021.9483840","DOIUrl":"https://doi.org/10.1109/ICVR51878.2021.9483840","url":null,"abstract":"With the development of science and technology, UAV has been applied to all aspects of life. Computer vision technology has been used as a common external sensing technology because of its low cost, high reliability and good accuracy. The autonomous landing of UAV is an important technology of autonomous flight. The common visual guidance landing of UAV is based on the ground target detection of cooperative target and the output of UAV landing point position. This method requires the UAV to accurately identify the established ground cooperative target, so when the target is lost or the UAV needs to make a forced landing, the UAV will not be able to land normally, in serious cases, it will lead to UAV damage. Therefore, in order to solve the problem of UAV autonomous landing in unknown environment, this paper proposes an autonomous landing point retrieval algorithm based on UAV 3D environment perception. First, this paper will conduct a preliminary road search at a certain height to obtain information on both sides of the road. Secondly, the external 3D point cloud environment is reconstructed in real time through the binocular camera, the pre-landing plane is found by plane fitting, and the 3D information is mapped to the 2D plane to extract the plane mask, and finally the random forest is used to determine the landing point. Through experimental analysis, the algorithm in this paper can better guide the UAV to land in an unknown environment.","PeriodicalId":266506,"journal":{"name":"2021 IEEE 7th International Conference on Virtual Reality (ICVR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122950318","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