Parking Space Verification: Improving Robustness Using A Convolutional Neural Network

Troels Høg Peter Jensen, Helge Thomsen Schmidt, Niels Dyremose Bodin, Kamal Nasrollahi, Thomas B. Moeslund

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

633 Downloads (Pure)

Resumé

With the number of privately owned cars increasing, the issue of locating an available parking space becomes apparant. This paper deals with the verification of vacant parking spaces, by using a vision based system looking over parking areas. In particular the paper proposes a binary classifier system, based on a Convolutional Neural Network, that is capable of determining if a parking space is occupied or not. A benchmark database consisting of images captured from different parking areas, under different weather and illumination conditions, has been used to train and test the system. The system shows promising performance on the database with an accuracy of 99.71% overall and is robust to the variations in parking areas and weather conditions.
OriginalsprogEngelsk
TitelProceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Vol/bind5
ForlagSCITEPRESS Digital Library
Publikationsdato2018
Sider311-318
ISBN (Trykt)978-989-758-226-4
DOI
StatusUdgivet - 2018
BegivenhedInternational Conference on Computer Vision Theory and Applications - Porto, Portugal
Varighed: 27 feb. 20171 mar. 2017
Konferencens nummer: 12
http://www.visapp.visigrapp.org

Konference

KonferenceInternational Conference on Computer Vision Theory and Applications
Nummer12
LandPortugal
ByPorto
Periode27/02/201701/03/2017
Internetadresse

Fingerprint

Parking
Neural networks
Classifiers
Railroad cars
Lighting

Citer dette

Jensen, T. H. P., Schmidt, H. T., Bodin, N. D., Nasrollahi, K., & Moeslund, T. B. (2018). Parking Space Verification: Improving Robustness Using A Convolutional Neural Network. I Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Bind 5, s. 311-318). SCITEPRESS Digital Library. https://doi.org/10.5220/0006135103110318
Jensen, Troels Høg Peter ; Schmidt, Helge Thomsen ; Bodin, Niels Dyremose ; Nasrollahi, Kamal ; Moeslund, Thomas B. / Parking Space Verification : Improving Robustness Using A Convolutional Neural Network. Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Bind 5 SCITEPRESS Digital Library, 2018. s. 311-318
@inproceedings{5c28bcf2a1af4f06aea219b75a96216d,
title = "Parking Space Verification: Improving Robustness Using A Convolutional Neural Network",
abstract = "With the number of privately owned cars increasing, the issue of locating an available parking space becomes apparant. This paper deals with the verification of vacant parking spaces, by using a vision based system looking over parking areas. In particular the paper proposes a binary classifier system, based on a Convolutional Neural Network, that is capable of determining if a parking space is occupied or not. A benchmark database consisting of images captured from different parking areas, under different weather and illumination conditions, has been used to train and test the system. The system shows promising performance on the database with an accuracy of 99.71{\%} overall and is robust to the variations in parking areas and weather conditions.",
author = "Jensen, {Troels H{\o}g Peter} and Schmidt, {Helge Thomsen} and Bodin, {Niels Dyremose} and Kamal Nasrollahi and Moeslund, {Thomas B.}",
year = "2018",
doi = "10.5220/0006135103110318",
language = "English",
isbn = "978-989-758-226-4",
volume = "5",
pages = "311--318",
booktitle = "Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",
publisher = "SCITEPRESS Digital Library",

}

Jensen, THP, Schmidt, HT, Bodin, ND, Nasrollahi, K & Moeslund, TB 2018, Parking Space Verification: Improving Robustness Using A Convolutional Neural Network. i Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. bind 5, SCITEPRESS Digital Library, s. 311-318, Porto, Portugal, 27/02/2017. https://doi.org/10.5220/0006135103110318

Parking Space Verification : Improving Robustness Using A Convolutional Neural Network. / Jensen, Troels Høg Peter; Schmidt, Helge Thomsen; Bodin, Niels Dyremose; Nasrollahi, Kamal; Moeslund, Thomas B.

Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Bind 5 SCITEPRESS Digital Library, 2018. s. 311-318.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Parking Space Verification

T2 - Improving Robustness Using A Convolutional Neural Network

AU - Jensen, Troels Høg Peter

AU - Schmidt, Helge Thomsen

AU - Bodin, Niels Dyremose

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

PY - 2018

Y1 - 2018

N2 - With the number of privately owned cars increasing, the issue of locating an available parking space becomes apparant. This paper deals with the verification of vacant parking spaces, by using a vision based system looking over parking areas. In particular the paper proposes a binary classifier system, based on a Convolutional Neural Network, that is capable of determining if a parking space is occupied or not. A benchmark database consisting of images captured from different parking areas, under different weather and illumination conditions, has been used to train and test the system. The system shows promising performance on the database with an accuracy of 99.71% overall and is robust to the variations in parking areas and weather conditions.

AB - With the number of privately owned cars increasing, the issue of locating an available parking space becomes apparant. This paper deals with the verification of vacant parking spaces, by using a vision based system looking over parking areas. In particular the paper proposes a binary classifier system, based on a Convolutional Neural Network, that is capable of determining if a parking space is occupied or not. A benchmark database consisting of images captured from different parking areas, under different weather and illumination conditions, has been used to train and test the system. The system shows promising performance on the database with an accuracy of 99.71% overall and is robust to the variations in parking areas and weather conditions.

U2 - 10.5220/0006135103110318

DO - 10.5220/0006135103110318

M3 - Article in proceeding

SN - 978-989-758-226-4

VL - 5

SP - 311

EP - 318

BT - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

PB - SCITEPRESS Digital Library

ER -

Jensen THP, Schmidt HT, Bodin ND, Nasrollahi K, Moeslund TB. Parking Space Verification: Improving Robustness Using A Convolutional Neural Network. I Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Bind 5. SCITEPRESS Digital Library. 2018. s. 311-318 https://doi.org/10.5220/0006135103110318