A Survey of Vehicle Re-Identification Based on Deep Learning

Vehicle re-identification is one of the core technologies of intelligent transportation systems, and it is crucial for the construction of smart cities. With the rapid development of deep learning, vehicle re-identification technologies have made significant progress in recent years. Therefore, maki...

Full description

Bibliographic Details
Main Authors: Hongbo Wang, Jiaying Hou, Na Chen
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8915694/
id doaj-2e61ca06d287468f96e0180566ce4be1
record_format Article
spelling doaj-2e61ca06d287468f96e0180566ce4be12021-03-30T00:47:51ZengIEEEIEEE Access2169-35362019-01-01717244317246910.1109/ACCESS.2019.29561728915694A Survey of Vehicle Re-Identification Based on Deep LearningHongbo Wang0https://orcid.org/0000-0002-0976-9102Jiaying Hou1https://orcid.org/0000-0002-7624-586XNa Chen2https://orcid.org/0000-0002-0942-7196State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, ChinaVehicle re-identification is one of the core technologies of intelligent transportation systems, and it is crucial for the construction of smart cities. With the rapid development of deep learning, vehicle re-identification technologies have made significant progress in recent years. Therefore, making a comprehensive survey about the vehicle re-identification methods based on deep learning is quite indispensable. There are mainly five types of deep learning-based methods designed for vehicle re-identification, i.e. methods based on local features, methods based on representation learning, methods based on metric learning, methods based on unsupervised learning, and methods based on attention mechanism. The major contributions of our survey come from three aspects. First, we give a comprehensive review of the current five types of deep learning-based methods for vehicle re-identification, and we further compare them from characteristics, advantages, and disadvantages. Second, we sort out vehicle public datasets and compare them from multiple dimensions. Third, we further discuss the challenges and possible research directions of vehicle re-identification in the future based on our survey.https://ieeexplore.ieee.org/document/8915694/Deep learningintelligent transportation systemvehicle re-identificationvehicle public datasets
collection DOAJ
language English
format Article
sources DOAJ
author Hongbo Wang
Jiaying Hou
Na Chen
spellingShingle Hongbo Wang
Jiaying Hou
Na Chen
A Survey of Vehicle Re-Identification Based on Deep Learning
IEEE Access
Deep learning
intelligent transportation system
vehicle re-identification
vehicle public datasets
author_facet Hongbo Wang
Jiaying Hou
Na Chen
author_sort Hongbo Wang
title A Survey of Vehicle Re-Identification Based on Deep Learning
title_short A Survey of Vehicle Re-Identification Based on Deep Learning
title_full A Survey of Vehicle Re-Identification Based on Deep Learning
title_fullStr A Survey of Vehicle Re-Identification Based on Deep Learning
title_full_unstemmed A Survey of Vehicle Re-Identification Based on Deep Learning
title_sort survey of vehicle re-identification based on deep learning
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2019-01-01
description Vehicle re-identification is one of the core technologies of intelligent transportation systems, and it is crucial for the construction of smart cities. With the rapid development of deep learning, vehicle re-identification technologies have made significant progress in recent years. Therefore, making a comprehensive survey about the vehicle re-identification methods based on deep learning is quite indispensable. There are mainly five types of deep learning-based methods designed for vehicle re-identification, i.e. methods based on local features, methods based on representation learning, methods based on metric learning, methods based on unsupervised learning, and methods based on attention mechanism. The major contributions of our survey come from three aspects. First, we give a comprehensive review of the current five types of deep learning-based methods for vehicle re-identification, and we further compare them from characteristics, advantages, and disadvantages. Second, we sort out vehicle public datasets and compare them from multiple dimensions. Third, we further discuss the challenges and possible research directions of vehicle re-identification in the future based on our survey.
topic Deep learning
intelligent transportation system
vehicle re-identification
vehicle public datasets
url https://ieeexplore.ieee.org/document/8915694/
work_keys_str_mv AT hongbowang asurveyofvehiclereidentificationbasedondeeplearning
AT jiayinghou asurveyofvehiclereidentificationbasedondeeplearning
AT nachen asurveyofvehiclereidentificationbasedondeeplearning
AT hongbowang surveyofvehiclereidentificationbasedondeeplearning
AT jiayinghou surveyofvehiclereidentificationbasedondeeplearning
AT nachen surveyofvehiclereidentificationbasedondeeplearning
_version_ 1724187783364345856