Rapid automatic vehicle manufacturer recognition using Random
forest

D 2017

Rapid automatic vehicle manufacturer recognition using Random forest

SEDLÁK, Jan and Lubomír POPELÍNSKÝ

Basic information

Original name

Rapid automatic vehicle manufacturer recognition using Random forest

Authors

SEDLÁK, Jan (203 Czech Republic, guarantor, belonging to the institution) and Lubomír POPELÍNSKÝ (203 Czech Republic, belonging to the institution)

Edition

Bristol, Proceedings of the 21st International Database Engineering Applications Symposium, IDEAS, p. 161-168, 8 pp. 2017

Publisher

ACM

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

RIV identification code

RIV/00216224:14330/17:00099501

Organization unit

Faculty of Informatics

ISBN

978-1-4503-5220-8

DOI

http://dx.doi.org/10.1145/3105831.3105869

Keywords in English

machine learning; vehicle manufacturer classification; SVM; Random forest

Abstract

V originále

This paper studies the applicability of machine learning methods in identifying the individual vehicle ttributes based on camera images from the real environment. We focus on a vehicle manufacturer recognition. Classfication based on the front vehicle mask makes possible to identify also vehicles without manufacturer’s logo. THe algorithm has been evaluated on 2988 samples collected directly from cameras in real environment. Random forest algorithm has achieved the best results in classiffication. Accuracy for classifying the most frequent two manufacturers, ˇSkoda and Volkswagen has been 97.21% and 98.10% respectively. It is also fast enough to use it in real-time, even on low-cost devices like mobile phones or single-board computers like Raspberry Pi. Functional implementation of this method has been successfully deployed in a real-world environment.

Links

MUNI/A/0897/2016, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VI.

Investor: Masaryk University, Category A

Citovat

SEDLÁK, Jan and Lubomír POPELÍNSKÝ. Rapid automatic vehicle manufacturer recognition using Random forest. Online. In Bipin C. Desai and Jun Hong and Richard McClatchey. Proceedings of the 21st International Database Engineering Applications Symposium, IDEAS. Bristol: ACM, 2017, p. 161-168. ISBN 978-1-4503-5220-8. Available from: https://dx.doi.org/10.1145/3105831.3105869.

@inproceedings{1404191,
   author = {Sedlák, Jan and Popelínský, Lubomír},
   address = {Bristol},
   booktitle = {Proceedings of the 21st International Database Engineering Applications Symposium, IDEAS},
   doi = {http://dx.doi.org/10.1145/3105831.3105869},
   editor = {Bipin C. Desai and Jun Hong and Richard McClatchey},
   keywords = {machine learning; vehicle manufacturer classification; SVM; Random forest},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Bristol},
   isbn = {978-1-4503-5220-8},
   pages = {161-168},
   publisher = {ACM},
   title = {Rapid automatic vehicle manufacturer recognition using Random forest},
   year = {2017}
}

TY  - JOUR
ID  - 1404191
AU  - Sedlák, Jan - Popelínský, Lubomír
PY  - 2017
TI  - Rapid automatic vehicle manufacturer recognition using Random forest
PB  - ACM
CY  - Bristol
SN  - 9781450352208
KW  - machine learning
KW  - vehicle manufacturer classification
KW  - SVM
KW  - Random forest
N2  - This paper studies the applicability of machine learning methods in identifying the individual vehicle ttributes based on camera images from the real environment. We focus on a vehicle manufacturer recognition. Classfication based on the front vehicle mask makes possible to identify also vehicles without manufacturer’s logo. THe algorithm has been evaluated on 2988 samples collected directly from cameras in real environment. Random forest algorithm has achieved the best results in classiffication. Accuracy for classifying the most frequent two manufacturers, ˇSkoda and Volkswagen has been 97.21% and 98.10% respectively. It is also fast enough to use it in real-time, even on low-cost devices like mobile phones or single-board computers like Raspberry Pi. Functional implementation of this method has been successfully deployed in a real-world environment.
ER  -

SEDLÁK, Jan and Lubomír POPELÍNSKÝ. Rapid automatic vehicle manufacturer recognition using Random forest. Online. In Bipin C. Desai and Jun Hong and Richard McClatchey. \textit{Proceedings of the 21st International Database Engineering Applications Symposium, IDEAS}. Bristol: ACM, 2017, p.~161-168. ISBN~978-1-4503-5220-8. Available from: https://dx.doi.org/10.1145/3105831.3105869.

Detailed Information on Publication Record