Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
versions View all 2 versions
addClaim

Estudio y comparación de las versiones de YOLO para la aplicación al tenis en tiempo real

Authors: De Jeu Boronat, Claudia;

Estudio y comparación de las versiones de YOLO para la aplicación al tenis en tiempo real

Abstract

En el ámbito del deporte la grabación y análisis de los partidos se ha convertido en una herramienta esencial para la preparación y mejora del rendimiento de los deportistas. El campo de la visión artificial ha sido aplicado en una gran variedad de deportes, incluido el tenis, con el propósito de ayudar y ayudar en dichos análisis. Este Trabajo Fin de Grado está centrado en el estudio e implementación del Deep Learning y visión artificial en el ámbito de la detección de objetos. En concreto en la detección de los componentes esenciales del tenis, como son la pelota, la raqueta, y el jugador, mediante la aplicación de la red neuronal YOLO. YOLO ha generado un gran interés por los amantes del Deep Learning en la detección de objetos en tiempo real. A lo largo del trabajo se aprenderá sobre el campo de las redes neuronales convolucionales profundas y se realizará una comparación entre las diferentes versiones de YOLO mediante el análisis de los resultados de los diferentes experimentos. Se concluirá con la mejor opción para la detección de objetos en tiempo real, así como la detección de objetos muy pequeños y con altas velocidades de movimiento. Además, este trabajo conlleva la elaboración y etiquetación de la base de datos que se utilizará con el fin de entrenar el modelo sobre partidos reales y profesionales de tenis.

In the world of sport, monitoring and analysing of matches has become an indispensable instrument for the coaching and performance improvement of athletes. The field of Computer Vision has been applied in a wide variety of sports, including tennis, in order to assist and support such analyses. This Research Project is focused on the study and implementation of Deep Learning and Computer Vision in the domain of object detection. Specifically in the detection of the key components of tennis, such as the ball, the racquet, and the player, through the application of the neural network YOLO. YOLO has raised a high interest among Deep Learning experts on real time object detection. Throughout the paper we will learn about the field of deep convolutional neural networks and a comparison will be made between different YOLO versions by analysing the results of different experiments. It will conclude with the optimal solution for real time object detection the detection, as well as the detection of very small objects with high movement speed. Furthermore, this work implies the elaboration and labelling of the dataset that will be used in order to train the model on real and professional tennis matches.

Universidad de Sevilla. Grado en Ingeniería de las Tecnologías de Telecomunicación

Country
Spain
Related Organizations
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green