BRIDGET Project

 

Research  

 

GTI Data   

 

Open databases created and software developed by the GTI and supplemental material to papers.  

 

Databases  

SportCLIP (2025): Multi-sport dataset for text-guided video summarization.
Ficosa (2024): The FNTVD dataset has been generated using the Ficosa's recording car.
MATDAT (2023):  More than 90K labeled images of martial arts tricking.
SEAW – DATASET (2022): 3 stereoscopic contents in 4K resolution at 30 fps.
UPM-GTI-Face dataset (2022): 11 different subjects captured in 4K, under 2 scenarios, and 2 face mask conditions.
LaSoDa (2022): 60 annotated images from soccer matches in five stadiums with different characteristics and light conditions.
PIROPO Database (2021):People in Indoor ROoms with Perspective and Omnidirectional cameras.
EVENT-CLASS (2021): High-quality 360-degree videos in the context of tele-education.
Parking Lot Occupancy Database (2020)
Nighttime Vehicle Detection database (NVD) (2019)
Hand gesture dataset (2019): Multi-modal Leap Motion dataset for Hand Gesture Recognition.
ViCoCoS-3D (2016): VideoConference Common Scenes in 3D.
LASIESTA database (2016): More than 20 sequences to test moving object detection and tracking algorithms.
Hand gesture database (2015): Hand-gesture database composed by high-resolution color images acquired with the Senz3D sensor.
HRRFaceD database (2014):Face database composed by high resolution images acquired with Microsoft Kinect 2 (second generation).
Lab database (2012): Set of 6 sequences to test moving object detection strategies.
Vehicle image database (2012): More than 7000 images of vehicles and roads.           

 

Software  

NaviFormer (2025): A Deep Reinforcement Learning Transformer-like Model to Holistically Solve the Navigation Problem.
Empowering Computer Vision in Higher Education(2024): A Novel Tool for Enhancing Video Coding Comprehension.
Engaging students in audiovisual coding through interactive MATLAB GUIs (2024)
TOP-Former: A Multi-Agent Transformer Approach for the Team Orienteering Problem (2023)
Solving Routing Problems for Multiple Cooperative Unmanned Aerial Vehicles using Transformer Networks (2023)
Vision Transformers and Traditional Convolutional Neural Networks for Face Recognition Tasks (2023)
Faster GSAC-DNN (2023): A Deep Learning Approach to Nighttime Vehicle Detection Using a Fast Grid of Spatial Aware Classifiers.
SETForSeQ (2020): Subjective Evaluation Tool for Foreground Segmentation Quality. 
SMV Player for Oculus Rift (2016)
Bag-D3P (2016): Face recognition using depth information. 
TSLAB (2015): Tool for Semiautomatic LABeling.    

   

Supplementary material  

Viewpoint-Invariant Soccer Pitch Registration Using Geometric and Learned Features (2025)
Soccer line mark segmentation and classification with stochastic watershed transform (2022)
A fully automatic method for segmentation of soccer playing fields (2022)
Grass band detection in soccer images for improved image registration (2022)
Evaluating the Influence of the HMD, Usability, and Fatigue in 360VR Video Quality Assessments (2020)
Automatic soccer field of play registration (2020)   
Augmented reality tool for the situational awareness improvement of UAV operators (2017)
Detection of static moving objects using multiple nonparametric background-foreground models on a Finite State Machine (2015)
Real-time nonparametric background subtraction with tracking-based foreground update (2015)  
Camera localization using trajectories and maps (2014)

 

                                                                                                                                                                                                                             
 
                                                                   
 
                                                                                                                                                             
 
      

 

 

 

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