Main areas detection on tennis courts

ABSTRACT : This paper is going to show all the ETL process, which includes obtaining of the images, label process of images of tennis matches with the objective of detecting the main areas of the court. The process continues with the generation of a baseline using a heuristic process and the generation of a deep learning model, with modification on the characteristics of the images, that allows the detection of main areas on the tennis courts, as well as the pick of the best option for the task selected, based on their performance.

• Autores: Arroyave Lopez, Juliana; Echavarria Echeverri, Rodrigo Alejandro
• Tipo de recurso: Tesis
• Fecha de publicación: 2021
• Institución: Universidad de Antioquia
• Repositorio: Repositorio UdeA
• Idioma: eng
• OAI Identifier: oai:bibliotecadigital.udea.edu.co:10495/24642
• Acceso en línea: http://hdl.handle.net/10495/24642
• Palabra clave: Inteligencia artificial; Visión por computador; Computer vision; Artificial intelligence; Procesamiento de imagen; Image processing; Aprendizaje automático (inteligencia artificial); Semantic segmentatio; Object detection; Multiclass classification; Hough transform; U-Net; Deep-learning; Python; Segmentación semántica; Detección de objetos
• Rights: openAccess
• License: http://creativecommons.org/licenses/by-nc-sa/2.5/co/