Listar por autor "López-Rubio, Ezequiel"
Mostrando ítems 21-40 de 96
-
Deep learning-based anomalous object detection system for panoramic cameras managed by a Jetson TX2 board
Benito-Picazo, Jesús; Domínguez-Merino, Enrique
; Palomo-Ferrer, Esteban José; Ramos-Jiménez, Gonzalo Pascual; López-Rubio, Ezequiel (IEEE, 2021)
Social conflicts appearing in the media are increas ing public awareness about security issues, resulting in a higher demand of more exhaustive environment monitoring methods. Automatic video surveillance systems are a ... -
Deep learning-based anomalous object detection system powered by microcontroller for PTZ cameras
Benito-Picazo, Jesús; Domínguez-Merino, Enrique; Palomo-Ferrer, Esteban José; López-Rubio, Ezequiel; Ortiz-de-Lazcano-Lobato, Juan Miguel (IEEE, 2018)
Automatic video surveillance systems are usually designed to detect anomalous objects being present in a scene or behaving dangerously. In order to perform adequately, they must incorporate models able to achieve accurate ... -
Deep learning-based super-resolution of 3D magnetic resonance images by regularly spaced shifting
Thurnhofer-Hemsi, Karl; López-Rubio, Ezequiel; Domínguez, Enrique; Luque-Baena, Rafael Marcos; Roé-Vellvé, Núria (Elsevier, 2020-07-20)
The image acquisition process in the field of magnetic resonance imaging (MRI) does not always provide high resolution results that may be useful for a clinical analysis. Super-resolution (SR) techniques manage to increase ... -
Deep learning-based video surveillance system managed by low cost hardware and panoramic cameras
Benito-Picazo, Jesús; Domínguez-Merino, Enrique; Palomo-Ferrer, Esteban José; López-Rubio, Ezequiel (IOS Press, 2020)
The design of automated video surveillance systems often involves the detection of agents which exhibit anomalous or dangerous behavior in the scene under analysis. Models aimed to enhance the video pattern recognition ... -
Desarrollo de jugadores automáticos mediante aprendizaje profundo por refuerzo para videojuegos
(2020-01-16)En este proyecto se presenta un modelo de aprendizaje profundo ca- paz de aprender a realizar varias tareas usando el juego de 1993 DOOM como entorno. El agente es entrenado con los píxeles en crudo de la pantalla de ... -
Desarrollo de un clasificador visual de especies de aves mediante redes neuronales convolucionales
(2020-01-16)Se ha desarrollado un clasificador visual de especies de aves mediante redes neuronales convolucionales, en lenguaje Python haciendo uso de la libreríaa Keras. Se dispone de un conjunto de datos de 5771 imágenes repartidas ... -
Desarrollo de una aplicación web para la gestión de expedientes de un bufete de abogados
(2018-02-22)La idea de este proyecto es la creación de una aplicación web que permita al público contactar vía internet con su abogado y seguir online la evolución de su caso hasta su solución final. Para ello, el cliente creará en ... -
Detección automática de glóbulos rojos mediante la transformada de Hough
(2018-03-16)El presente Trabajo de Fin de Grado consiste en la creación de un programa en MATLAB que consiga la detección y recuento de glóbulos rojos en imágenes de microscopía óptica de sangre. Este estudio tiene como fin obtener, ... -
Detección de objetos en entornos dinámicos para videovigilancia
(UMA Editorial, 2016)La videovigilancia por medios automáticos es un campo de investigación muy activo debido a la necesidad de seguridad y control. En este sentido, existen situaciones que dificultan el correcto funcionamiento de los algoritmos ... -
Detection of dangerously approaching vehicles over onboard cameras by speed estimation from apparent size
García Aguilar, Iván; García-González, Jorge; Medina, Daniel; Luque-Baena, Rafael Marcos; Domínguez-Merino, Enrique; López-Rubio, Ezequiel[et al.] (Elsevier, 2023-11-17)
Autonomous driving requires information such as the velocity of other vehicles to prevent potential hazards. This work proposes a real-time deep learning-based framework to estimate vehicle speeds from image captures through ... -
Dynamic learning rates for continual unsupervised learning.
Fernández-Rodríguez, Jose David; Palomo-Ferrer, Esteban José; Ortiz-de-Lazcano-Lobato, Juan Miguel; Ramos-Jiménez, Gonzalo Pascual; López-Rubio, Ezequiel (IOS Press, 2023)
The dilemma between stability and plasticity is crucial in machine learning, especially when non-stationary input distributions are considered. This issue can be addressed by continual learning in order to alleviate ... -
Ellipse fitting by spatial averaging of random ensembles
Thurnhofer-Hemsi, Karl; López-Rubio, Ezequiel; Blázquez-Parra, Elidia Beatriz; Ladrón-de-Guevara-Muñoz, María del Carmen; De-Cózar-Macías, Óscar (Elsevier, 2020-05)
Earlier ellipse fitting methods often consider the algebraic and geometric forms of the ellipse. The work presented here makes use of an ensemble to provide better results. The method proposes a new ellipse parametrization ... -
Encoding generative adversarial networks for defense against image classification attacks
Rodríguez Rodríguez, José Antonio; Pérez Bravo, José María; García-González, Jorge; Molina-Cabello, Miguel Ángel; Thurnhofer-Hemsi, Karl; López-Rubio, Ezequiel[et al.] (2022)
Image classification has undergone a revolution in recent years due to the high performance of new deep learning models. However, severe security issues may impact the performance of these systems. In particular, adversarial ... -
Enhanced Cellular Detection Using Convolutional Neural Networks and Sliding Window Super-Resolution Inference.
García Aguilar, Iván; Rostyslav, Zavoiko; Fernández-Rodríguez, Jose David; Luque-Baena, Rafael Marcos; López-Rubio, Ezequiel (Springer, 2024)
Histopathology currently serves as the standard for breast cancer diagnosis, but its manual execution demands time and expertise from pathologists. Artificial intelligence, particularly in digital pathology, has made ... -
Enhanced generation of automatically labelled image segmentation datasets by advanced style interpreter deep architectures.
Pacheco dos Santos Lima Junior, Marcos Sergio; López-Rubio, Ezequiel; Ortiz-de-Lazcano-Lobato, Juan Miguel; Fernández-Rodríguez, Jose David (Elsevier, 2025)
Large image datasets with annotated pixel-level semantics are necessary to train and evaluate supervised deep-learning models. These datasets are very expensive in terms of the human effort required to build them. Still, ... -
Enhanced Perspective Generation by Consensus of NeX neural models
Pacheco dos Santos Lima Junior, Marcos Sergio; Fernández-Rodríguez, Jose David; Ortiz-de-Lazcano-Lobato, Juan Miguel; López-Rubio, Ezequiel; Domínguez-Merino, Enrique (2022-07)
Neural rendering is a relatively new field of research that aims to produce high quality perspectives of a 3D scene from a reduced set of sample images. This is done with the help of deep artificial neural networks that ... -
Enhanced transfer learning model by image shifting on a square lattice for skin lesion malignancy assessment
Molina-Cabello, Miguel Ángel; Thurnhofer Hemsi, Karl; Maza Quiroga, Rosa María; Domínguez, Enrique; López-Rubio, Ezequiel; Molina-Cabello, Miguel Ángel[et al.] (2021)
Skin cancer is one of the most prevalent diseases among people. Physicians have a challenge every time they have to determine whether a diseased skin is benign or malign. There exist clinical diagnosis methods (such as ... -
Ensemble ellipse fitting by spatial median consensus
Thurnhofer Hemsi, Karl; López-Rubio, Ezequiel; Blázquez-Parra, Elidia Beatriz; Ladrón-de-Guevara-Muñoz, María del Carmen; De-Cózar-Macías, Óscar (2021)
Ellipses are among the most frequently used geometric models in visual pattern recognition and digital image analysis. This work aims to combine the outputs of an ensemble of ellipse fitting methods, so that the deleterious ... -
Estudio de la calidad en las detecciones de la red YOLOv5 con transformación de imágenes
(2022-12)Este trabajo de fin de grado tiene como objetivo el estudio del rendimiento del modelo de detección de objetos en imágenes y videos, YOLOv5, al utilizar imágenes con transformaciones. Para ello se empleará la métrica mAP ... -
Estudio de las propiedades reológicas de sangre con diabetes
(2018-03-22)La diabetes mellitus puede definirse como un trastorno en la actividad normal de las células del organismo cuya característica fundamental es el aumento anormal de la cantidad de glucosa en la sangre. Las personas diabéticas ...