Rapid automatic vehicle manufacturer recognition using Random forest

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F17%3A00099501" target="_blank" >RIV/00216224:14330/17:00099501 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1145/3105831.3105869" target="_blank" >http://dx.doi.org/10.1145/3105831.3105869</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3105831.3105869" target="_blank" >10.1145/3105831.3105869</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Rapid automatic vehicle manufacturer recognition using Random forest

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Rapid automatic vehicle manufacturer recognition using Random forest

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 21st International Database Engineering Applications Symposium, IDEAS

ISBN

9781450352208

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

161-168

Název nakladatele

ACM

Místo vydání

Bristol

Místo konání akce

Bristol

Datum konání akce

1. 1. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—