Please use this identifier to cite or link to this item: https://repositorio.ufba.br/handle/ri/21639
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorOliveira, Luciano Rebouças de-
dc.contributor.authorFranco, Alexandre da Costa e Silva-
dc.creatorFranco, Alexandre da Costa e Silva-
dc.date.accessioned2017-03-10T14:52:25Z-
dc.date.available2017-03-10T14:52:25Z-
dc.date.issued2017-03-10-
dc.date.submitted2016-05-13-
dc.identifier.urihttp://repositorio.ufba.br/ri/handle/ri/21639-
dc.description.abstractThe automatic person re-identification (re-id) problem resides in matching an unknown person image to a database of previously labeled images of people. Among several issues to cope with this research field, person re-id has to deal with person appearance and environment variations. As such, discriminative features to represent a person identity must be robust regardless those variations. Comparison among two image features is commonly accomplished by distance metrics. Although features and distance metrics can be handcrafted or trainable, the latter type has demonstrated more potential to breakthroughs in achieving state-of-the-art performance over public data sets. A recent paradigm that allows to work with trainable features is deep learning, which aims at learning features directly from raw image data. Although deep learning has recently achieved significant improvements in person re-identification, found on some few recent works, there is still room for learning strategies, which can be exploited to increase the current state-of-the-art performance. In this work a novel deep learning strategy is proposed, called here as coarse-to-fine learning (CFL), as well as a novel type of feature, called convolutional covariance features (CCF), for person re-identification. CFL is based on the human learning process. The core of CFL is a framework conceived to perform a cascade network training, learning person image features from generic-to-specific concepts about a person. Each network is comprised of a convolutional neural network (CNN) and a deep belief network denoising autoenconder (DBN-DAE). The CNN is responsible to learn local features, while the DBN-DAE learns global features, robust to illumination changing, certain image deformations, horizontal mirroring and image blurring. After extracting the convolutional features via CFL, those ones are then wrapped in covariance matrices, composing the CCF. CCF and flat features were combined to improve the performance of person re-identification in comparison with component features. The performance of the proposed framework was assessed comparatively against 18 state-of-the-art methods by using public data sets (VIPeR, i-LIDS, CUHK01 and CUHK03), cumulative matching characteristic curves and top ranking references. After a thorough analysis, our proposed framework demonstrated a superior performance.pt_BR
dc.language.isopt_BRpt_BR
dc.rightsAcesso Abertopt_BR
dc.subjectAutonomous robotspt_BR
dc.subjectPolynomial interpolationpt_BR
dc.subjectStandalone navigationpt_BR
dc.subjectInteligência artificialpt_BR
dc.subjectvisão computacionalpt_BR
dc.subjectAprendizagem de máquinapt_BR
dc.titleOn deeply learning features for automatic person image re-identificationpt_BR
dc.typeTesept_BR
dc.contributor.refereesSchnitman, Leizer-
dc.contributor.refereesLemes, Rubisley de Paula-
dc.contributor.refereesLoula, Angelo Conrado-
dc.contributor.refereesPapa, João Paulo-
dc.publisher.departamentEscola Politécnica / Instituto de Matemáticapt_BR
dc.publisher.programPrograma de Pós-Graduação em Mecatrônicapt_BR
dc.publisher.initialsUFBApt_BR
dc.publisher.countryBrasilpt_BR
Appears in Collections:Tese (PPGM)

Files in This Item:
File Description SizeFormat 
tese_alexandre_versao_final_bd.pdf3,69 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.