Accurate classification for Automatic Vehicle Type Recognition based on ensemble classifiers

Simple item page
dc.contributor.authorShvai, Nadiya
dc.contributor.authorHasnat, Abul
dc.contributor.authorMeicler, Antoine
dc.contributor.authorNakib, Amir
dc.date.accessioned2020-09-07T11:32:06Z
dc.date.available2020-09-07T11:32:06Z
dc.date.issued2019
dc.description.abstractIn this work, a real world problem of the vehicle type classification for Automatic Toll Collection (ATC) is considered. This problem is very challenging because any loss of accuracy even of the order of 1% quickly turns into a significant economic loss. To deal with such problem, many companies currently use Optical Sensors (OS) and human observers to correct the classification errors. Herein, a novel vehicle classification method is proposed. It consists in regularizing the problem using one camera to obtain vehicle class probabilities using a set of Convolutional Neural Networks (CNN), then, uses the Gradient Boosting based classifier to fuse the continuous class probabilities with the discrete class labels obtained from OS. The method is evaluated on a real world dataset collected from the toll collection points of the VINCI Autoroutes French network. Results show that it performs significantly better than the existing ATC system and, hence will vastly reduce the workload of human operators.en_US
dc.identifier.citationAccurate classification for Automatic Vehicle Type Recognition based on ensemble classifiers [electronic resource] / Nadiya Shvai, Abul Hasnat, Antoine Meicler, Amir Nakib // IEEE Transactions on Intelligent Transportation Systems. - 2019. - P. 1-10.en_US
dc.identifier.urihttps://doi.org/10.1109/TITS.2019.2906821
dc.identifier.urihttps://ekmair.ukma.edu.ua/handle/123456789/17913
dc.language.isoenuk_UA
dc.relation.sourceIEEE Transactions on Intelligent Transportation Systems.en_US
dc.statusfirst publisheduk_UA
dc.subjectVehicle Classificationen_US
dc.subjectConvolutional Neural Networken_US
dc.subjectGradient Boostingen_US
dc.subjectarticleen_US
dc.titleAccurate classification for Automatic Vehicle Type Recognition based on ensemble classifiersen_US
dc.typeArticleuk_UA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Accurate_classification_for_Automatic_Vehicle_Type_Recognition.pdf
Size:
11.99 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
7.54 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Кафедра математики