Publication detail

Vehicle Fine-grained Recognition Based on Convolutional Neural Networks for Real-world Applications

ŠPAŇHEL, J. SOCHOR, J. MAKAROV, A.

Original Title

Vehicle Fine-grained Recognition Based on Convolutional Neural Networks for Real-world Applications

Type

conference paper

Language

English

Original Abstract

We explore the implementation of vehicle fine-grained type and color recognition 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. Experimental evaluation shows that the accuracy of MobileNet net slightly decreases compared to ResNet-50 from 89.55% to 86.13% while inference is 2.4× faster on Jetson.

Keywords

convolutional neural networks, similar vehicle type search, vehicle fine-grained recognition, vehicle reidentification  

Authors

ŠPAŇHEL, J.; SOCHOR, J.; MAKAROV, A.

Released

29. 10. 2018

Publisher

IEEE Signal Processing Society

Location

Belgrade

ISBN

978-1-5386-6974-7

Book

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

Pages from

1

Pages to

5

Pages count

5

BibTex

@inproceedings{BUT155107,
  author="ŠPAŇHEL, J. and SOCHOR, J. and MAKAROV, A.",
  title="Vehicle Fine-grained Recognition Based on Convolutional Neural Networks for Real-world Applications",
  booktitle="2018 14th Symposium on Neural Networks and Applications (NEUREL)",
  year="2018",
  pages="1--5",
  publisher="IEEE Signal Processing Society",
  address="Belgrade",
  doi="10.1109/NEUREL.2018.8587012",
  isbn="978-1-5386-6974-7"
}