Sistema de visão computacional aplicado em análises de jogos de tênis
Loading...
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Universidade Federal de Juiz de Fora (UFJF)
DOI
Abstract
The field of artificial intelligence has played a very important role in current
technological development, making machines have a perception of the world similar to
humans and are able to perform many difficult tasks with good precision. In this sense,
a significant part of artificial intelligence deals with systems that perform actions that
require a computer vision system, which acts as a sensor providing high-level information
about a given environment. A research area within the field of computational vision
studies how to reconstruct and understand a 3D scene from the properties present in 2D
images. The results of this line of research become very valuable due to the fact that
some moves can be very difficult to be analyzed just by physically watching a game. Thus,
computer vision tools are being increasingly used in sports applications, where technical
decisions in a given move can be decisive for the match. A sport that has been highly
explored in terms of research development is tennis due to its growing dissemination and
financial relevance, being responsible for annual turnover of R$1.8 billion in Brazil alone.
Thus, this master’s dissertation work aims to develop a system based on computer vision
for analyzing tennis games. The implemented system captures videos during the tennis
game through cameras installed on the court and processes the images obtained, applying
machine learning methods and morphological operations, in order to locate the position
of the ball, the lines of the court and the location of the players after processing. In
addition, the algorithm determines the moment the ball bounces during the game and
analyzes whether it occurred in or out of the field. From the results obtained, the system
demonstrated robustness and reliability. These data are made available to players and
judges both on the court during the game and through an Android application, also
developed in this work. The application aims to allow all data resulting from processing to
be accessed from mobile devices, providing the results quickly and accessible to the user.
Description
Citation
Endorsement
Review
Supplemented By
Referenced By
Creative Commons license
Except where otherwise noted, this item's license is described as Acesso Aberto

