Detection-aware multi-object tracking evaluation

Master Universitario en Deep Learning for Audio and Video Signal Processing

Detalhes bibliográficos
Autor: Muñoz Aguado, Jorge
Tipo de documento: dissertação
Data de publicação:2021
País:España
Recursos:Universidad Autónoma de Madrid
Repositório:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglês
OAI Identifier:oai:repositorio.uam.es:10486/700260
Acesso em linha:http://hdl.handle.net/10486/700260
Access Level:Acceso aberto
Palavra-chave:Multi-object tracking
Object detection
Object tracking
Telecomunicaciones
id ES_ba4e32a904a07012114cabffb23e008d
oai_identifier_str oai:repositorio.uam.es:10486/700260
network_acronym_str ES
network_name_str España
repository_id_str
spelling Detection-aware multi-object tracking evaluationMuñoz Aguado, JorgeMulti-object trackingObject detectionObject trackingTelecomunicacionesMaster Universitario en Deep Learning for Audio and Video Signal ProcessingMulti-Object Tracking (MOT) is a hot topic in the computer vision field. It is a complex task that requires a detector, to identify objects, and a tracker, to follow them. It is useful for self-driving, surveillance and robot vision, between others, where research teams and companies are trying to improve their models. In order to determine which model performs better, they are scored using tracking metrics. In this thesis we experiment with MOT metrics aware of detection by using correlation matrices. By analyzing the results, we realize that tracking metrics incur in certain issues that prevent them for correctly reflecting tracking performance. The performance of the detector is relevant when scoring tracking models. The problem observed is that tracking metrics weigh differently elements that evaluate detection performance. Thus, improving one detector’s aspect with a high weight in the MOT metric will significantly improve the tracker’s score, but not necessarily indicating the amount of effort done by the tracker. That is, trackers are not evaluated in a balanced way. In order to solve this issue with the tracker scoring, we present a new multi-object tracking metric, based on the effort done by the tracker given a certain set of detections. This effort is calculated based on the improvement of bounding boxes over the ones given by the detector and the precision to keep the trace of the objects in a sequence. The metric has been tested for two widely employed datasets and shows us its reliability scoring tracking metrics. Also, it do not incur in the problem presented above.San Miguel Avedillo, Juan CarlosDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica Superior20212021-09-01master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10486/700260reponame: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:10486/7002602026-06-23T12:46:27Z
dc.title.none.fl_str_mv Detection-aware multi-object tracking evaluation
title Detection-aware multi-object tracking evaluation
spellingShingle Detection-aware multi-object tracking evaluation
Muñoz Aguado, Jorge
Multi-object tracking
Object detection
Object tracking
Telecomunicaciones
title_short Detection-aware multi-object tracking evaluation
title_full Detection-aware multi-object tracking evaluation
title_fullStr Detection-aware multi-object tracking evaluation
title_full_unstemmed Detection-aware multi-object tracking evaluation
title_sort Detection-aware multi-object tracking evaluation
dc.creator.none.fl_str_mv Muñoz Aguado, Jorge
author Muñoz Aguado, Jorge
author_facet Muñoz Aguado, Jorge
author_role author
dc.contributor.none.fl_str_mv San Miguel Avedillo, Juan Carlos
Departamento de Tecnología Electrónica y de las Comunicaciones
Escuela Politécnica Superior
dc.subject.none.fl_str_mv Multi-object tracking
Object detection
Object tracking
Telecomunicaciones
topic Multi-object tracking
Object detection
Object tracking
Telecomunicaciones
description Master Universitario en Deep Learning for Audio and Video Signal Processing
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-09-01
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/10486/700260
url http://hdl.handle.net/10486/700260
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_ 1869417886723866624
score 15.300719

Registros relacionados