Filters








2,737 Hits in 6.0 sec

Modelling Simulation and Performance Analysis for Footwear Manufacturing System

2021 Computer Engineering and Intelligent Systems  
Fully automatic tracking of articulated motion in real-time with a monocular RGB camera is a challenging problem which is essential for many virtual reality (VR) and human-computer interaction applications  ...  Our algorithm can be directly employed in practical applications as it is fully automatic, real-time, and temporally stable.  ...  Thus, developing a fully automatic realtime multi-object marker-less human motion tracking algorithm that works with monocular cameras is essential for many applications.  ... 
doi:10.7176/ceis/12-1-01 fatcat:4dtqx5tlonbgzfktipfysakyca

Hyper 360—Towards a Unified Tool Set Supporting Next Generation VR Film and TV Productions

Barnabas Takacs, Zsuzsanna Vincze, Hannes Fassold, Antonis Karakottas, Nikolaos Zioulis, Dimitrios Zarpalas, Petros Daras
2019 Journal of Software Engineering and Applications  
We describe four fundamental challenges that complex real-life Virtual Reality (VR) productions are facing today (such as multi-camera management, quality control, automatic annotation with cinematography  ...  Four Key Challenges of 360˚ VR Film & TV Productions Camera Placement, Motion and Multi-Camera Management 360˚ cameras are designed to deliver VR experiences aimed at placing the Viewers right at the  ...  Journal of Software Engineering and Applications Having estimated the scene's depth, we can synthesize new views and allow for limited translation w.r.t. the motion of the XR device (such as VR headsets  ... 
doi:10.4236/jsea.2019.125009 fatcat:t44vzsg5oreyvmdrenhreiu26i

Computer vision for human modelling and analysis

Adrian Hilton
2003 Machine Vision and Applications  
The author conducted research which led to the first commercial booth system for capturing animated models of people for applications in games, multimedia and virtual reality.  ...  This report summarises the author's views and experience on the application of computer vision technology for the modelling and analysis of people.  ...  The author would like to thank the BBC, dancer Deborah Bull (deborahbull.com) and members of the author's research team Jon Starck and Joel Mitchelson for substantial contributions to the studio capture  ... 
doi:10.1007/s00138-003-0123-4 fatcat:vhlydkwv5ff5taqo5ptxu34k5y

VR content creation and exploration with deep learning: A survey

Miao Wang, Xu-Quan Lyu, Yi-Jun Li, Fang-Lue Zhang
2020 Computational Visual Media  
This article surveys recent research that uses such deep learning methods for VR content creation and exploration.  ...  Intelligence of VR methods and applications has been significantly boosted by the recent developments in deep learning techniques.  ...  [79] proposed a multi-view CNN for sparse human performance capture.  ... 
doi:10.1007/s41095-020-0162-z fatcat:lgogzx26bvhn5f7uyefjkz7zny

On the Use of Multi-Depth-Camera Based Motion Tracking Systems in Production Planning Environments

Florian Geiselhart, Michael Otto, Enrico Rukzio
2016 Procedia CIRP  
Similar to traditional motion capture systems, it is necessary to deal with occlusions, camera registration and calibration and fusion of multi-depth-camera data to obtain a sufficiently large and robust  ...  While marker-based motion capture systems have been used for tracking of worker movements and interaction with those digital models until now, with the advent of markerless tracking technologies like the  ...  With a multi-depth-camera system, costs can be cut to a fraction of a traditional motion capture system for a comparable capture volume.  ... 
doi:10.1016/j.procir.2015.12.088 fatcat:tmnk5j444jh2fgfygryef6ux7u

MonoPerfCap: Human Performance Capture from Monocular Video [article]

Weipeng Xu, Avishek Chatterjee, Michael Zollhöfer, Helge Rhodin, Dushyant Mehta, Hans-Peter Seidel, Christian Theobalt
2018 arXiv   pre-print
Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data.  ...  We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video.  ...  CONCLUSION We have presented the first approach for automatic temporally coherent marker-less human performance capture from a monocular video.  ... 
arXiv:1708.02136v2 fatcat:toewmmbynnbppmxsop43d4xk3e

BodyDigitizer: An Open Source Photogrammetry-based 3D Body Scanner [article]

Travis Gesslein, Daniel Scherer, Jens Grubert
2017 arXiv   pre-print
With the rising popularity of Augmented and Virtual Reality, there is a need for representing humans as virtual avatars in various application domains ranging from remote telepresence, games to medical  ...  applications.  ...  Applications that can strongly benefit from person-specific human 3D representations include remote telepresence [24] , games and social VR [3], fitness applications [4] or medical applications [23  ... 
arXiv:1710.01370v2 fatcat:gmn622by7bfhxoqzpstaeohwny

Multi-Embodiment of Digital Humans in Virtual Reality for Assisting Human-Centered Ergonomics Design

Kevin Fan, Akihiko Murai, Natsuki Miyata, Yuta Sugiura, Mitsunori Tada
2017 Augmented Human Research  
We conducted user studies to evaluate human ergonomics design in five scenarios in virtual reality, comparing multi-embodiment with single embodiment.  ...  We present a multi-embodiment interface aimed at assisting human-centered ergonomics design, where traditionally the design process is hindered by the need of recruiting diverse users or the utilization  ...  The participants wore motion-captured HMD and suit.  ... 
doi:10.1007/s41133-017-0010-6 fatcat:xmx6ourffzeihdno5luewkdhhi

Realizing a low-latency virtual reality environment for motor learning

Thomas Waltemate, Felix Hülsmann, Thies Pfeiffer, Stefan Kopp, Mario Botsch
2015 Proceedings of the 21st ACM Symposium on Virtual Reality Software and Technology - VRST '15  
To fill this gap, we propose a set of requirements towards VR systems for motor learning, with a special focus on motion capturing and rendering.  ...  We then assess and evaluate state-of-the-art techniques and technologies for motion capturing and rendering, in order to provide data on latencies for different setups.  ...  Figure 2 : A minimal architecture for a VR environment for motor learning combines a motion capturing system, motion processing (e.g., for re-targeting or motion analysis), as well as a render engine for  ... 
doi:10.1145/2821592.2821607 dblp:conf/vrst/WaltemateHPKB15 fatcat:rvh26jpwunctrn2pp3uhupvwmq

A Multi-camera Network System for Markerless 3D Human Body Voxel Reconstruction

Tao Yang, Yanning Zhang, Meng Li, Dapei Shao, Xingong Zhang
2009 2009 Fifth International Conference on Image and Graphics  
This paper presents a fully automated system for realtime 3D human visual hull reconstruction and skeleton voxels extraction.  ...  , various body configurations and multiple persons.  ...  Introduction Developing a real-time and fully automatic human motion capture system is a subject of great scientific and commercial interest [1] [2] [3] [4] [5] [6] [7] [8] , and it finds application  ... 
doi:10.1109/icig.2009.89 dblp:conf/icig/YangZLSZ09 fatcat:fhshkwb5vvgcho2hvjgx72y2fe

EgoCap

Helge Rhodin, Christian Richardt, Dan Casas, Eldar Insafutdinov, Mohammad Shafiei, Hans-Peter Seidel, Bernt Schiele, Christian Theobalt
2016 ACM Transactions on Graphics  
It is particularly useful in virtual reality to freely roam and interact, while seeing the fully motion-captured virtual body.  ...  Therefore, we propose a new method for real-time, marker-less, and egocentric motion capture: estimating the full-body skeleton pose from a lightweight stereo pair of fisheye cameras attached to a helmet  ...  Acknowledgements We thank all reviewers for their valuable feedback, Dushyant Mehta, James Tompkin, and The Foundry for license support.  ... 
doi:10.1145/2980179.2980235 fatcat:kx3rcoljurb3xgewan4acsb2qa

A Mutual Motion Capture System for Face-to-face Collaboration [article]

Atsuyuki Nakamura, Kiyoshi Kiyokawa, Photchara Ratsamee, Tomohiro Mashita, Yuki Uranishi, Haruo Takemura
2017 International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments  
Therefore, in this research, proposed is a motion capture technique for a multi-user VR / AR environment using head mounted displays (HMDs), that does not limit the working range of the user nor require  ...  Moreover, motion capture targeting multiple people is becoming necessary in multi-user virtual reality (VR) and augmented reality (AR) environments.  ...  For example, OpenPose [CSWS16] can estimate 2D pose of multi-person from a single image.  ... 
doi:10.2312/egve.20171332 dblp:conf/egve/NakamuraKRMUT17 fatcat:ncrdunkxv5cbxj6odgakvjedia

Why and how to use virtual reality to study human social interaction: The challenges of exploring a new research landscape

Xueni Pan, Antonia F. de C. Hamilton
2018 British Journal of Psychology  
Why and how to use virtual reality to study human social interaction: The challenges of exploring a new research landscape. British Journal of Psychology, ISSN 0007-1269 [Article]  ...  It is commonly termed mocap (short for motion capture).  ...  This could be a disadvantage for some applications as the glasses do not fully 'block' reality (i.e., one cannot fully embody someone else's body in the CAVE).  ... 
doi:10.1111/bjop.12290 pmid:29504117 pmcid:PMC6055846 fatcat:jvujp6arnjfw5cfxyl7hb7yrau

EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras [article]

Helge Rhodin, Christian Richardt, Dan Casas, Eldar Insafutdinov, Mohammad Shafiei, Hans-Peter Seidel, Bernt Schiele, Christian Theobalt
2016 arXiv   pre-print
The captured user can freely move around, which enables reconstruction of larger-scale activities and is particularly useful in virtual reality to freely roam and interact, while seeing the fully motion-captured  ...  We therefore propose a new method for real-time, marker-less and egocentric motion capture which estimates the full-body skeleton pose from a lightweight stereo pair of fisheye cameras that are attached  ...  Acknowledgements We thank all reviewers for their valuable feedback, Dushyant Mehta, James Tompkin, and The Foundry for license support.  ... 
arXiv:1609.07306v1 fatcat:xatetlqtpbbsbclzgv3ik2fxee

The virtual human as a multimodal interface

Daniel Thalmann
2000 Proceedings of the working conference on Advanced visual interfaces - AVI '00  
This paper discusses the main issues for creating Interactive Virtual Environments with Virtual Humans emphasizing the following aspects: creation of Virtual Humans, gestures, interaction with objects,  ...  The motion of the real person is captured using a Flock of Birds.  ...  However, with motion capture, this is the most common approach used in video-games. For task oriented motions, specific motion motors should be used.  ... 
doi:10.1145/345513.345232 dblp:conf/avi/Thalmann00 fatcat:5amargcaozav5dxng4337bhkbm
« Previous Showing results 1 — 15 out of 2,737 results