Visual Analysis in Traffic & Re-identification

Publikation: Bog/antologi/afhandling/rapportPh.d.-afhandlingForskning

329 Downloads (Pure)

Resumé

Automated analysis of traffic situations - be it cars, signs, or pedestrians -
is becoming increasingly relevant and feasible with the advent of powerful
sensors, computers, and algorithms. This PhD thesis tackles three themes
within this realm: Traffic sign detection, pedestrian detection and analysis,
and person re-identification.

In traffic sign detection, the work comprises a thorough survey of the state
of the art, assembly of the worlds largest public dataset with U.S. traffic signs,
and work in machine learning based detection algorithms. It was shown that
detection of U.S. traffic signs has traditionally lacked behind detection of
European signs, which led to the effort of collecting the dataset and pushing
the state of the art in detection performance for these signs by using the
Aggregate Channel Features detector.

Within pedestrian detection, a method combining Viola-Jones and HOG/SVM
has been put forth, which gives the speed advantage of Viola-Jones and the
detection performance of HOG/SVM. Work has also been done in tracking
the gaze of drivers to determine which pedestrians a driver may have missed.
Finally, pedestrian tracking has been performed in an attempt to predict their
future behavior in order to avoid dangerous situations.

Person re-identification has been attempted in a multi-modal fashion. Traditionally,
re-identification has been performed using only RGB input from
regular surveillance cameras, but we added depth and thermal information
to the mix. Several iterations of a multi-modal system were tested, but the
advantage of the additional information turned out to be limited.
OriginalsprogEngelsk
ForlagAalborg Universitetsforlag
ISBN (Elektronisk)978-87-7112-333-3
DOI
StatusUdgivet - 2015
NavnPh.d.-serien for Det Teknisk-Naturvidenskabelige Fakultet, Aalborg Universitet
ISSN2246-1248

Citer dette

Møgelmose, A. (2015). Visual Analysis in Traffic & Re-identification. Aalborg Universitetsforlag. Ph.d.-serien for Det Teknisk-Naturvidenskabelige Fakultet, Aalborg Universitet https://doi.org/10.5278/vbn.phd.engsci.00026
Møgelmose, Andreas. / Visual Analysis in Traffic & Re-identification. Aalborg Universitetsforlag, 2015. (Ph.d.-serien for Det Teknisk-Naturvidenskabelige Fakultet, Aalborg Universitet).
@phdthesis{55f9251ed71c41da82d9c97cb230f379,
title = "Visual Analysis in Traffic & Re-identification",
abstract = "Automated analysis of traffic situations - be it cars, signs, or pedestrians -is becoming increasingly relevant and feasible with the advent of powerfulsensors, computers, and algorithms. This PhD thesis tackles three themeswithin this realm: Traffic sign detection, pedestrian detection and analysis,and person re-identification.In traffic sign detection, the work comprises a thorough survey of the stateof the art, assembly of the worlds largest public dataset with U.S. traffic signs,and work in machine learning based detection algorithms. It was shown thatdetection of U.S. traffic signs has traditionally lacked behind detection ofEuropean signs, which led to the effort of collecting the dataset and pushingthe state of the art in detection performance for these signs by using theAggregate Channel Features detector.Within pedestrian detection, a method combining Viola-Jones and HOG/SVMhas been put forth, which gives the speed advantage of Viola-Jones and thedetection performance of HOG/SVM. Work has also been done in trackingthe gaze of drivers to determine which pedestrians a driver may have missed.Finally, pedestrian tracking has been performed in an attempt to predict theirfuture behavior in order to avoid dangerous situations.Person re-identification has been attempted in a multi-modal fashion. Traditionally,re-identification has been performed using only RGB input fromregular surveillance cameras, but we added depth and thermal informationto the mix. Several iterations of a multi-modal system were tested, but theadvantage of the additional information turned out to be limited.",
author = "Andreas M{\o}gelmose",
note = "Thomas B. Moeslund, Principal Supervisor",
year = "2015",
doi = "10.5278/vbn.phd.engsci.00026",
language = "English",
publisher = "Aalborg Universitetsforlag",

}

Møgelmose, A 2015, Visual Analysis in Traffic & Re-identification. Ph.d.-serien for Det Teknisk-Naturvidenskabelige Fakultet, Aalborg Universitet, Aalborg Universitetsforlag. https://doi.org/10.5278/vbn.phd.engsci.00026

Visual Analysis in Traffic & Re-identification. / Møgelmose, Andreas.

Aalborg Universitetsforlag, 2015.

Publikation: Bog/antologi/afhandling/rapportPh.d.-afhandlingForskning

TY - BOOK

T1 - Visual Analysis in Traffic & Re-identification

AU - Møgelmose, Andreas

N1 - Thomas B. Moeslund, Principal Supervisor

PY - 2015

Y1 - 2015

N2 - Automated analysis of traffic situations - be it cars, signs, or pedestrians -is becoming increasingly relevant and feasible with the advent of powerfulsensors, computers, and algorithms. This PhD thesis tackles three themeswithin this realm: Traffic sign detection, pedestrian detection and analysis,and person re-identification.In traffic sign detection, the work comprises a thorough survey of the stateof the art, assembly of the worlds largest public dataset with U.S. traffic signs,and work in machine learning based detection algorithms. It was shown thatdetection of U.S. traffic signs has traditionally lacked behind detection ofEuropean signs, which led to the effort of collecting the dataset and pushingthe state of the art in detection performance for these signs by using theAggregate Channel Features detector.Within pedestrian detection, a method combining Viola-Jones and HOG/SVMhas been put forth, which gives the speed advantage of Viola-Jones and thedetection performance of HOG/SVM. Work has also been done in trackingthe gaze of drivers to determine which pedestrians a driver may have missed.Finally, pedestrian tracking has been performed in an attempt to predict theirfuture behavior in order to avoid dangerous situations.Person re-identification has been attempted in a multi-modal fashion. Traditionally,re-identification has been performed using only RGB input fromregular surveillance cameras, but we added depth and thermal informationto the mix. Several iterations of a multi-modal system were tested, but theadvantage of the additional information turned out to be limited.

AB - Automated analysis of traffic situations - be it cars, signs, or pedestrians -is becoming increasingly relevant and feasible with the advent of powerfulsensors, computers, and algorithms. This PhD thesis tackles three themeswithin this realm: Traffic sign detection, pedestrian detection and analysis,and person re-identification.In traffic sign detection, the work comprises a thorough survey of the stateof the art, assembly of the worlds largest public dataset with U.S. traffic signs,and work in machine learning based detection algorithms. It was shown thatdetection of U.S. traffic signs has traditionally lacked behind detection ofEuropean signs, which led to the effort of collecting the dataset and pushingthe state of the art in detection performance for these signs by using theAggregate Channel Features detector.Within pedestrian detection, a method combining Viola-Jones and HOG/SVMhas been put forth, which gives the speed advantage of Viola-Jones and thedetection performance of HOG/SVM. Work has also been done in trackingthe gaze of drivers to determine which pedestrians a driver may have missed.Finally, pedestrian tracking has been performed in an attempt to predict theirfuture behavior in order to avoid dangerous situations.Person re-identification has been attempted in a multi-modal fashion. Traditionally,re-identification has been performed using only RGB input fromregular surveillance cameras, but we added depth and thermal informationto the mix. Several iterations of a multi-modal system were tested, but theadvantage of the additional information turned out to be limited.

U2 - 10.5278/vbn.phd.engsci.00026

DO - 10.5278/vbn.phd.engsci.00026

M3 - Ph.D. thesis

BT - Visual Analysis in Traffic & Re-identification

PB - Aalborg Universitetsforlag

ER -

Møgelmose A. Visual Analysis in Traffic & Re-identification. Aalborg Universitetsforlag, 2015. (Ph.d.-serien for Det Teknisk-Naturvidenskabelige Fakultet, Aalborg Universitet). https://doi.org/10.5278/vbn.phd.engsci.00026