Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Chapter

Download BibTeX

Title

Vision system for automatic recognition of Polish historic vehicles

Authors

[ 1 ] Instytut Automatyki i Robotyki, Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ P ] employee | [ S ] student

Scientific discipline (Law 2.0)

[2.2] Automation, electronics, electrical engineering and space technologies

Year of publication

2022

Chapter type

chapter in monograph / paper

Publication language

english

Keywords
EN
  • Polish historic vehicles
  • vision system
  • artificial neural networks
  • web application
  • image recognition
  • image processing
Abstract

EN In this article, a system for automatic recognition of Polish historic vehicles is proposed. A unique database of vehicle images was prepared, including real and scale vehicles. A software was developed to automatically classify vehicle models and assess their condition using artificial neural networks. Training, validation and test were performed for various datasets and neural network models. In the best case the VGG16 network reached 95% of vehicle model classification accuracy. In addition, a web application visualizing vehicle recognition is offered.

Pages (from - to)

167 - 172

Book

SPA 2022 Signal Processing : Algorithms, Architectures, Arrangements, and Applications : Conference Proceedings, Poznan, 21st-22nd September 2022

Presented on

SPA 2022 Signal Processing - Algorithms, Architectures, Arrangements, and Applications, 21-22.09.2022, Poznań, Polska

Ministry points / chapter

20

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.