Detail výsledku

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

ŠPAŇHEL, J.; SOCHOR, J.; MAKAROV, A. Detection of Traffic Violations of Road Users Based on Convolutional Neural Networks. In 2018 14th Symposium on Neural Networks and Applications (NEUREL). Belgrade: IEEE Signal Processing Society, 2018. p. 1-6. ISBN: 978-1-5386-6974-7.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Špaňhel Jakub, Ing., Ph.D., UPGM (FIT)
Sochor Jakub, Ing., Ph.D.
MAKAROV, A.
Abstrakt

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.  

Klíčová slova

camera calibration, convolutional neural networks, pedestrian detection, traffic violation, vehicle detection

Rok
2018
Strany
1–6
Sborník
2018 14th Symposium on Neural Networks and Applications (NEUREL)
Konference
2018 14th Symposium on Neural Networks and Applications (NEUREL)
ISBN
978-1-5386-6974-7
Vydavatel
IEEE Signal Processing Society
Místo
Belgrade
DOI
10.1109/NEUREL.2018.8586996
UT WoS
000457745100017
EID Scopus
2-s2.0-85060927923
BibTeX 
@inproceedings{BUT155106,
  author="ŠPAŇHEL, J. and SOCHOR, J. and MAKAROV, A.",
  title="Detection of Traffic Violations of Road Users Based on Convolutional Neural Networks",
  booktitle="2018 14th Symposium on Neural Networks and Applications (NEUREL)",
  year="2018",
  pages="1--6",
  publisher="IEEE Signal Processing Society",
  address="Belgrade",
  doi="10.1109/NEUREL.2018.8586996",
  isbn="978-1-5386-6974-7"
}
Projekty
iARTIST - industry-Academia Research on Three-dimensional Image Sensing for Transportation, EU, Seventh Research Framework Programme, zahájení: 2017-10-01, ukončení: 2018-01-31, ukončen
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru