Addressing Multiple Object Tracking with Segmentation Masks

Multiple Object Tracking (MOT) aims to locate all the objects from a video, assigning them the same identities across all frames. Traditionally, this problem was addressed following the Tracking by Detection (TbD) paradigm, using detections represented by bounding boxes. However, bounding boxes can...

Descripción completa

Detalles Bibliográficos
Autor: Bendaña Gómez, Manuel
Tipo de recurso: tesis de maestría
Fecha de publicación:2024
País:España
Institución:Universidad de Santiago de Compostela (USC)
Repositorio:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Idioma:inglés
OAI Identifier:oai:minerva.usc.gal:10347/37791
Acceso en línea:https://hdl.handle.net/10347/37791
Access Level:acceso abierto
Palabra clave:Multiple object tracking
Segmentation
Deep learning
1203 Ciencia de los ordenadores
id ES_ff80a5c092e6bb1f9e5833f8347eea1b
oai_identifier_str oai:minerva.usc.gal:10347/37791
network_acronym_str ES
network_name_str España
repository_id_str
spelling Addressing Multiple Object Tracking with Segmentation MasksBendaña Gómez, ManuelMultiple object trackingSegmentationDeep learning1203 Ciencia de los ordenadoresMultiple Object Tracking (MOT) aims to locate all the objects from a video, assigning them the same identities across all frames. Traditionally, this problem was addressed following the Tracking by Detection (TbD) paradigm, using detections represented by bounding boxes. However, bounding boxes can contain information from several objects, something that does not happen with segmentation masks. This work takes the ByteTrack MOT system as a starting point. Our proposal, ByteTrackMask, integrates a class-agnostic segmentation method and a segmentation-based tracker in ByteTrack in order to rescue tracks that would have been lost. Results over validation sets of MOT challenge datasets provide improvements in MOT metrics of interest like MOTA, IDF1 and false negatives.Universidade de Santiago de Compostela. Escola Técnica Superior de EnxeñaríaMucientes Molina, ManuelBrea Sánchez, Víctor Manuel20242024-01-0120242024-01-01master thesishttp://purl.org/coar/resource_type/c_bdccinfo:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/10347/37791reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostelainstname:Universidad de Santiago de Compostela (USC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-ShareAlike 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-sa/4.0/info:eu-repo/semantics/openAccessoai:minerva.usc.gal:10347/377912026-06-15T12:47:27Z
dc.title.none.fl_str_mv Addressing Multiple Object Tracking with Segmentation Masks
title Addressing Multiple Object Tracking with Segmentation Masks
spellingShingle Addressing Multiple Object Tracking with Segmentation Masks
Bendaña Gómez, Manuel
Multiple object tracking
Segmentation
Deep learning
1203 Ciencia de los ordenadores
title_short Addressing Multiple Object Tracking with Segmentation Masks
title_full Addressing Multiple Object Tracking with Segmentation Masks
title_fullStr Addressing Multiple Object Tracking with Segmentation Masks
title_full_unstemmed Addressing Multiple Object Tracking with Segmentation Masks
title_sort Addressing Multiple Object Tracking with Segmentation Masks
dc.creator.none.fl_str_mv Bendaña Gómez, Manuel
author Bendaña Gómez, Manuel
author_facet Bendaña Gómez, Manuel
author_role author
dc.contributor.none.fl_str_mv Universidade de Santiago de Compostela. Escola Técnica Superior de Enxeñaría
Mucientes Molina, Manuel
Brea Sánchez, Víctor Manuel
dc.subject.none.fl_str_mv Multiple object tracking
Segmentation
Deep learning
1203 Ciencia de los ordenadores
topic Multiple object tracking
Segmentation
Deep learning
1203 Ciencia de los ordenadores
description Multiple Object Tracking (MOT) aims to locate all the objects from a video, assigning them the same identities across all frames. Traditionally, this problem was addressed following the Tracking by Detection (TbD) paradigm, using detections represented by bounding boxes. However, bounding boxes can contain information from several objects, something that does not happen with segmentation masks. This work takes the ByteTrack MOT system as a starting point. Our proposal, ByteTrackMask, integrates a class-agnostic segmentation method and a segmentation-based tracker in ByteTrack in order to rescue tracks that would have been lost. Results over validation sets of MOT challenge datasets provide improvements in MOT metrics of interest like MOTA, IDF1 and false negatives.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-01-01
2024
2024-01-01
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/10347/37791
url https://hdl.handle.net/10347/37791
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
Attribution-NonCommercial-ShareAlike 4.0 International
http://creativecommons.org/licenses/by-nc-sa/4.0/
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
Attribution-NonCommercial-ShareAlike 4.0 International
http://creativecommons.org/licenses/by-nc-sa/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
instname:Universidad de Santiago de Compostela (USC)
instname_str Universidad de Santiago de Compostela (USC)
reponame_str Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
collection Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425780173307904
score 15,812429

Similares en LA Referencia