A Metaverse for the Good

 

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  


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  


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)

 

                                                                                                                                                                                                                             
 
                                                                   
 
                                                                                                                                                             
 
      

 

 

A Metaverse for the Good: Exploring the Potential and Pitfalls

The idea of a metaverse, a sprawling digital realm where virtual and physical realities intertwine, is no longer confined to the realm of science fiction. It's a tantalizing concept, promising a space where people can engage in a myriad of activities, from leisure to education, business to politics, all while transcending geographical limitations.

At its core, the metaverse represents a fusion of cutting-edge technologies like virtual, augmented, and mixed reality, with the potential to revolutionize the way we interact and exist. However, like any transformative innovation, it carries both promise and peril.

The EMRN (Extended Reality and Metaverse Network) stands at the forefront of exploring this brave new world. Comprising researchers, industry experts, and policymakers, EMRN delves into the multifaceted dimensions of the metaverse concept. Their 2024 conference serves as a melting pot of ideas, inviting voices from academia, industry, and policy to contribute to the discourse.

On April 9-10, 2024, researchers from the Grupo de Tratamiento de Imágenes (GTI) of the Universidad Politécnica de Madrid (UPM) took part in the event “A Metaverse for the Good” organized by The EMRN in Barcelona, Spain.

Pablo Pérez, Marta Orduna (NOKIA), Jesús Gutiérrez (GTI-UPM), and María Nava-Ruiz (Fundación Juan XXIII) illuminated the path towards an inclusive metaverse with their work on "Towards the Incluverse: an inclusive metaverse (for people with intellectual disability)." Their vision underscores the potential of the metaverse to bridge gaps and empower marginalized communities.

 

MetaVerso Barcelona 1


Matteo Dal Magro, Jesús Gutiérrez (GTI-UPM), and Pablo Pérez (NOKIA) delve into the therapeutic potential of the metaverse in "eXtended Reality and Biosignals in the Therapy of Individuals with Intellectual and Physical Disabilities." Their exploration hints at a future where immersive experiences could aid in rehabilitation and wellness.

MetaVerso Barcelona 2


Jesús Gutiérrez, Narciso García (GTI-UPM), and Pablo Pérez (NOKIA), presented the test plan of the Immersive Media Group (IMG) of the Video Quality Experts Group (VQEG) entitled "Towards a recommendation for interactive test methods for subjective assessment of extended reality communications." This worldwide cooperation led by UPM and Nokia seeks a common methodology for the assessment of bidirectional immersive communication systems.

MetaVerso Barcelona 3


Yet, as we embark on this journey towards a metaverse for the good, we must tread cautiously. The immersive nature of this digital realm amplifies both the positive and negative impacts, magnifying the stakes involved.
By fostering collaboration and dialogue among stakeholders, EMRN endeavors to steer the trajectory of the metaverse towards a positive outcome. Through open discussion, research, and policy engagement, they strive to maximize the likelihood of realizing a metaverse that benefits society at large.

At the event, Jesús Gutiérrez (GTI-UPM) and Pablo Pérez (NOKIA), presented their poster titled "Towards a recommendation for interactive test methods for subjective assessment of extended reality communications," adding valuable insights to the dialogue on ethical and practical considerations in metaverse development.

MetaVerso Barcelona 4


Together, let's chart a course towards a metaverse that enriches lives, fosters inclusivity, and propels humanity forward into a new era of possibility.