Semantic Segmentation in 2D Videogames

Master Universitario in Deep Learning for Audio and Video Signal Processing

Detalles Bibliográficos
Autor: Montalvo Rodrigo, Javier
Tipo de recurso: tesis de maestría
Fecha de publicación:2021
País:España
Institución:Universidad Autónoma de Madrid
Repositorio:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglés
OAI Identifier:oai:repositorio.uam.es:10486/697503
Acceso en línea:http://hdl.handle.net/10486/697503
Access Level:acceso abierto
Palabra clave:Semantic Segmentation
Synthetic Data
Reinforcement Learning
Telecomunicaciones
id ES_49c17651d1a6617f7d76ae8bde60b9df
oai_identifier_str oai:repositorio.uam.es:10486/697503
network_acronym_str ES
network_name_str España
repository_id_str
spelling Semantic Segmentation in 2D VideogamesMontalvo Rodrigo, JavierSemantic SegmentationSynthetic DataReinforcement LearningTelecomunicacionesMaster Universitario in Deep Learning for Audio and Video Signal ProcessingThis Master Thesis focuses on applying semantic segmentation, a computer vision technique, with the objective of improving the performance of deep-learning reinforcement models, and in particular, the performance over the original Super Mario Bros videogame. While humans can play a stage from a videogame like Super Mario Bros, and quickly identify from the elements in the screen what object is the character they are playing with, what are enemies and what elements are obstacles, this is not the case for neural networks, as they require a certain training to understand what is displayed in the screen. Using semantic segmentation, we can heavily simplify the frames from the videogame, and reduce visual information of elements in the screen to class and location, which is the most relevant information required to complete the game. In this work, a synthetic dataset generator that simulates frames from the Super Mario Bros videogame has been developed. This dataset has been used to train semantic segmentation deep-learning models which have been incorporated to a deep reinforcement learning algorithm with the objective of improving the performance of it. We have found that applying semantic segmentation as a frame processing method can actually help reinforcement learning models to train more efficiently and with better generalization. These results also suggest that there could be other computer vision techniques, like object detection or tracking, that could be found useful to help with the training of reinforcement learning algorithms, and they could be an interesting topic for future research.García Martín, ÁlvaroMartínez Sánchez, José MaríaDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica Superior20212021-06-01master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10486/697503reponame:Biblos-e Archivo. Repositorio Institucional de la UAMinstname:Universidad Autónoma de MadridInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:repositorio.uam.es:10486/6975032026-06-23T12:46:27Z
dc.title.none.fl_str_mv Semantic Segmentation in 2D Videogames
title Semantic Segmentation in 2D Videogames
spellingShingle Semantic Segmentation in 2D Videogames
Montalvo Rodrigo, Javier
Semantic Segmentation
Synthetic Data
Reinforcement Learning
Telecomunicaciones
title_short Semantic Segmentation in 2D Videogames
title_full Semantic Segmentation in 2D Videogames
title_fullStr Semantic Segmentation in 2D Videogames
title_full_unstemmed Semantic Segmentation in 2D Videogames
title_sort Semantic Segmentation in 2D Videogames
dc.creator.none.fl_str_mv Montalvo Rodrigo, Javier
author Montalvo Rodrigo, Javier
author_facet Montalvo Rodrigo, Javier
author_role author
dc.contributor.none.fl_str_mv García Martín, Álvaro
Martínez Sánchez, José María
Departamento de Tecnología Electrónica y de las Comunicaciones
Escuela Politécnica Superior
dc.subject.none.fl_str_mv Semantic Segmentation
Synthetic Data
Reinforcement Learning
Telecomunicaciones
topic Semantic Segmentation
Synthetic Data
Reinforcement Learning
Telecomunicaciones
description Master Universitario in Deep Learning for Audio and Video Signal Processing
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-06-01
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv http://hdl.handle.net/10486/697503
url http://hdl.handle.net/10486/697503
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Biblos-e Archivo. Repositorio Institucional de la UAM
instname:Universidad Autónoma de Madrid
instname_str Universidad Autónoma de Madrid
reponame_str Biblos-e Archivo. Repositorio Institucional de la UAM
collection Biblos-e Archivo. Repositorio Institucional de la UAM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407443838042112
score 15.301629

Similares en LA Referencia