Submitted by Diogo Barreiros (diogo.barreiros@ufba.br) on 2017-03-10T14:39:59Z
No. of bitstreams: 1
tese_alexandre_versao_final_bd.pdf: 3780030 bytes, checksum: 765f095f9626a12f3b43a6bf9fdb97f3 (MD5) / Approved for entry into archive by Vanessa Reis (vanessa.jamile@ufba.br) on 2017-03-10T14:52:25Z (GMT) No. of bitstreams: 1
tese_alexandre_versao_final_bd.pdf: 3780030 bytes, checksum: 765f095f9626a12f3b43a6bf9fdb97f3 (MD5) / Made available in DSpace on 2017-03-10T14:52:25Z (GMT). No. of bitstreams: 1
tese_alexandre_versao_final_bd.pdf: 3780030 bytes, checksum: 765f095f9626a12f3b43a6bf9fdb97f3 (MD5) / The 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.
| Identifer | oai:union.ndltd.org:IBICT/oai:192.168.11:11:ri/21639 |
| Date | 13 May 2016 |
| Creators | Franco, Alexandre da Costa e Silva |
| Contributors | Oliveira, Luciano Rebouças de, Schnitman, Leizer, Lemes, Rubisley de Paula, Loula, Angelo Conrado, Papa, João Paulo |
| Publisher | Escola Politécnica / Instituto de Matemática, Programa de Pós-Graduação em Mecatrônica, UFBA, brasil |
| Source Sets | IBICT Brazilian ETDs |
| Language | Portuguese |
| Detected Language | English |
| Type | info:eu-repo/semantics/publishedVersion, info:eu-repo/semantics/doctoralThesis |
| Source | reponame:Repositório Institucional da UFBA, instname:Universidade Federal da Bahia, instacron:UFBA |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0017 seconds