MENU
  • About Us
  •  Research
    •  
      Projects
    •  
      Publications
    • GTI Blog
    •  
      GTI Data
    • Quality of Experience tests
  •  Teaching
    •  
      Undergraduate
    •  
      Graduate
    •  
      PhD courses
    • Specialized Master courses
  • People
  •  Join Us!!
    •  
      Chinese Students
    •  
      Jobs, PhD, TFG/TFM, Grants
  • News and Events
  • Dem-3DTV
  • Contact

 

    

 

  • GTI
  • FVVLive
  • Projects

  • Publications

  • GTI Blog

  • GTI Data

  • Quality of Experience tests

LogoFVV 

FVV Live is a real-time, low-latency, end-to-end free viewpoint video system including capture, transmission, synthesis on an edge server, and visualisation and control on a mobile terminal.

The following video shows an application where the advanced features of FVV Live are used (free viewpoint, user control, real-time, low-latency, ...) while explaining the technical developments:

For more info, contact us:  This email address is being protected from spambots. You need JavaScript enabled to view it. I'm sorry; your browser doesn't support HTML5 video.

 

SYSTEM DESCRIPTION

The following video presents the laboratory initial setup (cameras on rig, not on individual tripods) as well as the low-latency real-time performance: I'm sorry; your browser doesn't support HTML5 video.

 

CAPTURE

- Consumer-grade stereo cameras over standard USB connections, no genlock required.

- Software synchronization procedure over a shared clock source distributed using PTP (IEEE 1588-2002). 

- Real-time depth estimation and segmentation to enable layered synthesis and bandwidth savings. 

FVV6

TRANSMISSION 

- Real-time encoding all (necessary) camera streams, both color and depth, RTP transmission.

- Depth information means structure, but video lossy codecs are designed for natural images and the HVS: lossless coding.

- Extended precision to deliver depth data for the synthesis: adaptation of 4:2:0 video structures to get 12 bits per pixel.

FVV2

SYNTHESIS AND VISUALIZATION

- Real-time synthesis, too much data from all cameras, therefore only the cameras nearest to the virtual viewpoint are used. 

- Very complex task, and also unreliable depth data. Soft transitions mix contributions from closest reference cameras. 

- Dense off-line background model with Retinex+AKAZE+SfM+MVS. 

- Layered synthesis to integrate reliable off-line background model with on-line foreground to combat noisy on-line depth estimation in the background.  

- Cell phone controls the position of the virtual camera.  

                                         FVV3  FVV4

FVV5

 

For more info, contact us:  This email address is being protected from spambots. You need JavaScript enabled to view it. 

 

Tweet

 

1.png4.png0.png2.png0.png7.png8.png

Copyright © 2015 Grupo de Tratamiento de Imágenes.

All Rights Reserved

SiteMap Intranet

2013 - Powered by Beautiful-Templates.com. All Rights Reserved.