Rozpoznání atributů vozidel pomocí metod strojového učení (Zvaná přednáška)

SEDLÁK, Jan. Rozpoznání atributů vozidel pomocí metod strojového učení (Zvaná přednáška) (Automatic recognition of vehicle attributes using machine learning (Invited talk)). In Mária Bieliková, Ivan Srba. Proceedings in Informatics and Information Technologies. Bratislava: WIKT & DaZ. Bratislava: Nakladatel’stvo STU, 2016, p. 49-52. ISBN 978-80-227-4619-9.

Basic information

• Original name: Rozpoznání atributů vozidel pomocí metod strojového učení (Zvaná přednáška)
• Name (in English): Automatic recognition of vehicle attributes using machine learning (Invited talk)
• Authors: SEDLÁK, Jan.
• Edition: Bratislava, Proceedings in Informatics and Information Technologies. Bratislava: WIKT & DaZ, p. 49-52, 4 pp. 2016.
• Publisher: Nakladatel’stvo STU

Other information

• Original language: Czech
• Type of outcome: Proceedings paper
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: Slovakia
• Confidentiality degree: is not subject to a state or trade secret
• Publication form: printed version "print"
• Organization unit: Faculty of Informatics
• ISBN: 978-80-227-4619-9
• Keywords (in Czech): strojové učení; neuronové sítě; klasifikace výrobce; barva vozidla; SVM; Random forest; hluboké neuronové sítě
• Keywords in English: machine learning; neural networks; brand classification; vehicle color; SVM; Random forest; deep neural networks

Abstract

Detection and recognition of vehicle attributes is important part of the ITS systems, particularly when searching for interest or stolen vehicles. The lecture discusses applicability of machine learning methods, including RandomForest, Support vector machine and deep neural networks, in identifying the individual vehicle attributes based on camera images from the real environment. The results from functional implementation of machine learning algorithms for classification of color and vehicle make, deployed in real-world environment for the purpose of Police of the Czech Republic, will be presented.

Abstract (in English)

Detection and recognition of vehicle attributes is important part of the ITS systems, particularly when searching for interest or stolen vehicles. The lecture discusses applicability of machine learning methods, including RandomForest, Support vector machine and deep neural networks, in identifying the individual vehicle attributes based on camera images from the real environment. The results from functional implementation of machine learning algorithms for classification of color and vehicle make, deployed in real-world environment for the purpose of Police of the Czech Republic, will be presented.

Links

• MUNI/A/0945/2015, interní kód MU: Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace V.

Investor: Masaryk University, Category A