Detail publikace

Unconstrained License Plate Detection in Hardware

JURÁNEK, R. MUSIL, P. ZEMČÍK, P.

Originální název

Unconstrained License Plate Detection in Hardware

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In this paper, we propose an FPGA implementation of license plate detection (LPD) in images captured by arbitrarily placed cameras, vehicle-mounted cameras, or even handheld cameras. In such images, the license plates can appear in a wide variety of positions and angles. Thus we cannot rely on a-priori known geometric properties of the license plates as many contemporary applications do. Unlike the existing solutions targeted for DSP, FPGA or similar low power devices, we do not make any assumptions about license plate size and orientation in the image. We use multiple sliding window detectors based on simple image features, each tuned to a specific range of projections. On a dataset captured by a camera mounted on a vehicle, we show that detection rate is 98 % (and 98.7 % when combined with video tracking). We demonstrate that our FPGA implementation can process 1280×1024 pixel image at over 40 FPS with a minimum width of detected license plates approximately 100 pixels. The FPGA block is fully functional and it is intended to be used in a smart camera to parking control in residential zones.

Klíčová slova

ALPR, Soft Cascade, Decision Trees, WaldBoost

Autoři

JURÁNEK, R.; MUSIL, P.; ZEMČÍK, P.

Vydáno

28. 4. 2021

Nakladatel

SciTePress - Science and Technology Publications

Místo

Praha

ISBN

978-989-758-513-5

Kniha

Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS

Strany od

13

Strany do

21

Strany počet

9

BibTex

@inproceedings{BUT175774,
  author="Roman {Juránek} and Petr {Musil} and Pavel {Zemčík}",
  title="Unconstrained License Plate Detection in Hardware",
  booktitle="Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS",
  year="2021",
  pages="13--21",
  publisher="SciTePress - Science and Technology Publications",
  address="Praha",
  doi="10.5220/0010174000130021",
  isbn="978-989-758-513-5"
}