Detail publikačního výsledku

Traffic Analysis Using Machine Learning Approach

ZELENÝ, O.; FRÝZA, T.

Originální název

Traffic Analysis Using Machine Learning Approach

Anglický název

Traffic Analysis Using Machine Learning Approach

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

This paper provides insight to the YOLOv5 deep learning architecture and its use for vehicle detection and classification in order to improve traffic management in larger cities and busy roads. The paper presents simple system with one fixed camera and Jetson Nano, a computer for embedded and AI application, to detect and classify vehicles.

Anglický abstrakt

This paper provides insight to the YOLOv5 deep learning architecture and its use for vehicle detection and classification in order to improve traffic management in larger cities and busy roads. The paper presents simple system with one fixed camera and Jetson Nano, a computer for embedded and AI application, to detect and classify vehicles.

Klíčová slova

Deep learning, Computer vision, Traffic analysis, Convolutional Neural Networks, You Only Look Once, COCO dataset

Klíčová slova v angličtině

Deep learning, Computer vision, Traffic analysis, Convolutional Neural Networks, You Only Look Once, COCO dataset

Autoři

ZELENÝ, O.; FRÝZA, T.

Rok RIV

2024

Vydáno

26.04.2022

Nakladatel

Brno University of Technology, Faculty of ERlectronic Engineering and Communication

Místo

Brno

ISBN

978-80-214-6029-4

Kniha

PROCEEDINGS I OF THE 28TH STUDENT EEICT 2022 General papers

Edice

1

Strany od

265

Strany do

268

Strany počet

4

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_1_v2.pdf

Plný text v Digitální knihovně

http://hdl.handle.net/

BibTex

@inproceedings{BUT186978,
  author="Ondřej {Zelený} and Tomáš {Frýza}",
  title="Traffic Analysis Using Machine Learning Approach",
  booktitle="PROCEEDINGS I OF THE 28TH STUDENT EEICT 2022 General papers",
  year="2022",
  series="1",
  pages="265--268",
  publisher="Brno University of Technology, Faculty of ERlectronic Engineering and Communication",
  address="Brno",
  isbn="978-80-214-6029-4",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_1_v2.pdf"
}