Detection of Traffic Violations of Road Users Based on Convolutional Neural Networks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130798" target="_blank" >RIV/00216305:26230/18:PU130798 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1109/NEUREL.2018.8586996" target="_blank" >http://dx.doi.org/10.1109/NEUREL.2018.8586996</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/NEUREL.2018.8586996" target="_blank" >10.1109/NEUREL.2018.8586996</a>

Result language

angličtina

Original language name

Detection of Traffic Violations of Road Users Based on Convolutional Neural Networks

Original language description

In this paper, we explore the implementation of vehicle and pedestrian detection based on neural networks in a real-world application. We suggest changes to the previously published method with respect to capabilities of low-powered devices, such as Nvidia Jetson platform. Our experimental evaluation shows that detectors are capable of running 10.7 FPS on Jetson TX2 and can be used in real-world applications.  

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

R - Projekt Ramcoveho programu EK

Publication year

2018

Confidentiality

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

Article name in the collection

2018 14th Symposium on Neural Networks and Applications (NEUREL)

ISBN

978-1-5386-6974-7

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

1-6

Publisher name

IEEE Signal Processing Society

Place of publication

Belgrade

Event location

SAVA Center Milentija Popovića 9 11070, Belgrade

Event date

Nov 20, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000457745100017