Publication detail

Multi-Class Weather Classification from Single Images with Convolutional Neural Networks on Embedded Hardware

BRAVENEC, T.

Original Title

Multi-Class Weather Classification from Single Images with Convolutional Neural Networks on Embedded Hardware

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

The paper is focused on creating a lightweight machine learning solution for classification of weather conditions from input images, that can process the input data in real time on embedded devices. The approach to the classification uses deep convolutional neural networks architecture with focus on lightweight design and fast inference, while providing high accuracy results. The focus on creating lightweight convolutional neural network architecture capable of classification of weather conditions also enables usage of the network in real time applications at the edge.

Keywords

deep learning, neural networks, computer vision, weather classification, machine learning, parallel computing, inference on edge, reduced precision computing

Authors

BRAVENEC, T.

Released

27. 4. 2021

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií

Location

Brno

ISBN

978-80-214-5942-7

Book

Proceedings I of the 27th Conference STUDENT EEICT 2021

Edition number

1

Pages from

1

Pages to

5

Pages count

5

BibTex

@inproceedings{BUT171849,
  author="Tomáš {Bravenec}",
  title="Multi-Class Weather Classification from Single Images with Convolutional Neural Networks on Embedded Hardware",
  booktitle="Proceedings I of the 27th Conference STUDENT EEICT 2021",
  year="2021",
  number="1",
  pages="1--5",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  address="Brno",
  isbn="978-80-214-5942-7"
}