Speaking in the Key of Science

 

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)

 

                                                                                                                                                                                                                             
 
                                                                   
 
                                                                                                                                                             
 
      

 

 

Exploring the world through the lens of an event camera

Yesterday, April 9th, 2025, the Grupo de Tratamiento de Imágenes (GTI) successfully hosted the fifth seminar in the "Speaking in the Key of Science" series—an event that continues to establish itself as a key reference point for exploring the latest advances in Artificial Intelligence, Computer Vision, Extended Reality (XR), and other emerging fields.


The seminar, titled "Exploring the world through the lens of an event camera," was delivered by Guillermo Gallego, Professor at TU Berlin and the Einstein Center Digital Future.

 

Guillermo1 2

 

During the session, Guillermo introduced us to the fascinating world of event cameras, vision sensors inspired by human perception that offer a revolutionary alternative to traditional cameras. Through a clear and detailed theoretical explanation, we learned how these sensors work, what kind of information they capture, and why they are especially valuable in scenarios where speed, dynamic range, and energy efficiency are critical. He also presented some of their cutting-edge applications in computer vision and robotics—from tracking and recognition systems to real-time motion estimation and autonomous navigation.

 

Guillermo1 1 Guillermo1 4


The practical demonstration was undoubtedly one of the seminar’s highlights. We had the chance to see an event camera in action and witness how it responds with remarkable efficiency to dynamic changes in a scene. Through several live demos, its potential to capture fast motion with impressive precision was illustrated, along with its ability to operate effectively under challenging lighting conditions, where conventional cameras often struggle.


This seminar not only deepened our understanding of event-based vision but also sparked thought-provoking discussions about the future of visual sensing technologies. As innovation continues to push the boundaries of what’s possible in computer vision and robotics, events like these are essential for fostering knowledge exchange and inspiring new research directions. We look forward to continuing this journey of exploration in the upcoming sessions of Speaking in the Key of Science.