• Extraction and recognition of violin gestures on music performance

  Nou Plana, Ignasi (2019)

  Assessment of performance in music have been used frequently in learning and teaching areas. Automate this process involves the study and analysis of different key-points and its particular features. This kind of assessment ...
• Computer vision approach to air pollution prediction using multimodal data

  Antón, Carles (2019)

  Climate change is one of the hardest problems humanity will have to face in the next century. Data analysis and computer vision are two powerful tools that can help us perform tasks that would usually take more time on ...
• Automatic assessment of violin performance using machine learning

  Ortega Rams, Ariadna (2019)

  Automatic Assessment of music performance is nowadays a relevant field of study, given the growing interest in the usage of computer-based music learning systems. In this project, we present a Machine Learning Approach to ...
• OpenLedMapper, un software de LED mapping basat en l’entorn openFrameworks

  Pelaez Carrera, Albert (2019-10-23)

  El LED mapping és una tècnica visual i d’il·luminació que consisteix en generar continguts en un software determinat i reproduir-los en sistemes de LED controlables píxel a píxel, ja siguin en forma de tira, o focus. ...
• Approaching image processing and computer vision problems via Light Field Imaging

  Garcia Moll, Clara (2019-10-23)

  Light field imaging is an emerging technology which allows capturing an image with richer information than just a two-dimensional image. Traditional cameras capture only light intensity. In contrast, light field cameras, ...
• Sistema automático de verificación de cumplimiento de planogramas usando inteligencia artificial aplicada a imágenes

  Albacar Fernández, Pol (2019-10-23)

  El proyecto consiste en desarrollar un sistema ofrecido en forma Web App apoyado por una arquitectura de sistemas robusta con la principal funcionalidad de ayudar a las compañías a conseguir un control completo del ...
• Chord identification in real-time using a neural network

  Giró Serratosa, Daniel (2019)

  The necessity of musicians to transcribe by ear a music piece is a common known problem, given that the music score is not always available. Transcribing by ear is a difficult task, and for this reason, the automatic music ...
• Advanced GNSS-R signals processing with GPU

  Cervelló i Nogués, Oriol (2019)

  Global Navigation Satellite Systems (GNSS) are mainly used for positioning. Nonetheless part of those signals emitted towards the Earth are reflected and can be used for GNSS-Reflectometry (GNSS-R), a novel Earth Observation ...
• Multimodal study of Alzheimer's Disease using machine learning methods

  Rabella Gras, Noel (2019)

  It is estimated that there are around 47 million people affected by Alzheimer's disease (AD) in the world. For this reason, there are more and more studies and data collection about groups of patients, using techniques ...
• On the study of noise inreal street photographs

  Ramis Palau, Carlos (2019)

  This work wants to be a new step on the study of noise in real images. The main contribution of this work is the presentation and creation of a new real noisy photographs dataset. The special characteristics of this ...
• Stereo to binaural upmix based on ambience extraction

  Sánchez Guzmán, Yeray (2019)

  In this project we aim to create a 3D audio stereo upmix system with the purpose of producing a more immersive listening experience. To do so, we use an approach which segmentates the direct and ambience components of an ...
• Disseny i desplegament d’un sistema CiviCRM aplicat a la gestió de voluntariat dins del projecte Code Club Catalunya

  Pérez Serra, Raquel (2019)

  En aquest treball s’ha dissenyat i desplegat un sistema gestor de clients basat en web que permet administrar una base de dades de voluntariat dins del programa Code Club Catalunya. L’objectiu és facilitar el registre ...
• Detector de baches con deep learning

  Manzanares González, Albert (2019)

  El estado de mantenimiento de las carreteras actuales es deficiente en la mayoría de los casos y puede causar un peligro para sus usuarios, además de daños a sus vehículos. La manera de reportar estas incidencias es de ...
• 3D convolutional neural networks for Alzheimer's disease diagnosis

  Lucas Castellano, Aitor (2019)

  Alzheimer's disease (AD) is an incurable neurodegenerative disease. Magnetic Resonance Imaging (MRI) is used to assess the damage caused by the disease and to capture complex changes on the brain. In this work, we study ...
• Separación de fuentes sonoras en vídeos musicales asistida por el análisis del movimiento

  Ugarte Molinet, Igor (2019)

  Este proyecto propone un método para la separación de fuentes sonoras de una mezcla, empleando el movimiento de los intérpretes de dicha señal. El proceso se compone de tres bloques. El primer bloque realiza un análisis ...
• Source localization in ambisonics sound fields

  Ros Atmetlla, Fèlix (2019)

  Direction of Arrival (DoA) estimation is a procedure used to describe the spatial direction from which a sound source comes. In this work, we estimate DoA from firstorder Ambisonic recordings, using intensity vector ...
• Enhancement of working memory capacity using Theta binaural beats

  Castro San Cristóbal, Pau (2019)

  Understanding the mechanisms and brain processes that neural networks perform in order to achieve cognition has always been one of the main questions in psychology and neuroscience. Neural oscillations are thought to be ...
• Reconocimiento automático de la posición del violín y el arco para la evaluación automática de la interpretación musical

  Santaella Sánchez, Javier (2019-10-04)

  En el campo de la enseñanza de instrumentos musicales es de gran importancia proveer una retroacción continuada durante las horas de práctica (sin profesor) del correcto uso de ellos. En el caso particular del violín, los ...
• Automatic cardiac segmentation by fusing deep learning models

  Rodríguez Prado, Diego Vincent (2019)

  Nowadays machine learning models can be used to automate the process of cardiac segmentation, a tedious task usually done by cardiologists and radiologists to diagnose heart diseases and get insights of a certain patient’s ...
• 3D reconstruction from silhouettes and photoconsistency based on depth map fusion

  Cots Pujol, Helena (2019)

  In this thesis, we present a multi-view 3D reconstruction system from silhouettes and photoconsistency information based on depth map fusion. The method receives as input a set of images from different points of view ...

View more