BRIDGET Project
                    
  • Research

    Theory and methods of Digital Image Processing, Visual Static Information encoding (images), Dynamic visual information coding (video, TV and HDTV), Image sintesis,etc.

    Teaching

    Digital Image Processing, Digital Television, Image Encoding, Multimedia System, Computer Vision, Graphics, Telecommunications Systems, Digital transmision

    Join us!!

    Chinese students, Offers of employment , etc.
     
     

News and Events

 

BRIDGET Project 

BRIDGET will open new dimensions for multimedia content creation and consumption by enhancing broadcast programmes with bridgets: links from the programme you are watching to external interactive media elements such as web pages, images, audio clips, different types of video (2D, multi-view, with depth information, free viewpoint) and synthetic 3D models.

Bridgets can be:

- created automatically or manually by broadcasters, either from their own content (e.g., archives, Internet and other services) or from wider Internet sources;

- created by end users, either from their local archives or from Internet content;

- transmitted in the broadcast stream or independently;

- filtered by a recommendation engine based on user profile, relevance, quality, etc.;

- enjoyed on the common main screen or a private second screen, in a user-centric and immersive manner, e.g., within 3D models allowing users to place themselves inside an Augmented Reality (AR) scene at the exact location from which the linked content was captured. 

To deliver the above, BRIDGET will develop:

- a hybrid broadcast/Internet architecture;

- a professional Authoring Tool (AT) to generate bridgets and dynamic AR scenes with spatialised audio;

- an easy-to-use AT for end users;

- a player to select bridgets, and consume and navigate the resulting dynamic AR scenes.

The AT and player will use a range of sophisticated and innovative technologies extending state-of-the-art media analysis and visual search, and 3D scene reconstruction, which will enable customised and context-adapted hybrid broadcast/Internet services offering enhanced interactive, multi-screen, social and immersive content for new forms of AR experiences. BRIDGET tools will be based on and contribute to international standards, thus ensuring the creation of a true horizontal market and ecosystem for connected TV and contributed media applications. 

BRIDGET is a 36 month project which runs from 1st November 2013 until 31st October 2016.

EC-funded STREP, Grant Agreement 610691

March 13, 2024

The Realverse

   Pablo Pérez delivered the talk: "The Realverse – challenges in XR communications".

February 11, 2024

Day of Women and Girls in Science 2024

   GTI showcases the talent, dedication and achievements of its female researchers.

February 29, 2024

Airbus/GTI Working Session

   Representatives from Airbus and NASA explore GTI's Initiatives, discuss future projects, and experience advanced technologies in a fruitful meeting.

December 13, 2023

Data Engineering

   Data Engineering at ETSIT (UPM): An Unlimited Technological Adventure!

  

  

      

      Former News

 

About Us

  •  

    The Grupo de Tratamiento de Imágenes (GTI) [Image Processing Group] is a research group working on theory, methods, and applications of Digital Image and Video Processing, mainly for compression and analysis. Besides specific developments on video related topics, GTI also considers research on complete systems like visual communications, real time computer vision, and multimedia telecom applications. Thus, GTI has developed facilities and toolkits for the design and implementation of video delivery systems and machine-learning based computer vision applications. Currently, GTI activity focuses on immersive video communications and extended (VR, MR, AR) and shared reality applications, including deep-learning for visual computing. GTI infrastructure includes three labs: a complete 3DTV laboratory (3DTV Lab) endowed with a 3D acquisition system, a 3D post-production system, and several 3D displays, a real-time free-viewpoint video laboratory (FVV Live) endowed with linear and planar camera configurations, lightweight schemes for video acquisition, transmission, and rendering, and minimal motion to photon latency, and an immersive laboratory (ImLab) for 360VR, volumetric video and extended/shared reality.

     
  •  

    The Grupo de Tratamiento de Imágenes (GTI) [Image Processing Group] is a research group working on theory, methods, and applications of Digital Image and Video Processing, mainly for compression and analysis. Besides specific developments on video related topics, GTI also considers research on complete systems like visual communications, real time computer vision, and multimedia telecom applications. Thus, GTI has developed facilities and toolkits for the design and implementation of video delivery systems and machine-learning based computer vision applications. Currently, GTI activity focuses on immersive video communications and extended (VR, MR, AR) and shared reality applications, including deep-learning for visual computing. GTI infrastructure includes three labs: a complete 3DTV laboratory (3DTV Lab) endowed with a 3D acquisition system, a 3D post-production system, and several 3D displays, a real-time free-viewpoint video laboratory (FVV Live) endowed with linear and planar camera configurations, lightweight schemes for video acquisition, transmission, and rendering, and minimal motion to photon latency, and an immersive laboratory (ImLab) for 360VR, volumetric video and extended/shared reality.

     

Contact

  •   

    Grupo de Tratamiento de Imágenes

    Edificio C, Desp: C-306

    Dpto. Señales, Sistemas y Radiocomunicaciones

    E.T.S. Ingenieros de Telecomunicación

    Universidad Politécnica de Madrid

    28040 – Madrid (Spain)

    Teléfono: (+34) 91 06 72 383