Light-YOLOv3: License Plate Detection in Multi-Vehicle Scenario

Yuchao SUN; Qiao PENG; Dengyin ZHANG

doi:10.1587/transinf.2020EDP7260

Light-YOLOv3: License Plate Detection in Multi-Vehicle Scenario

Yuchao SUN, Qiao PENG, Dengyin ZHANG

Full Text Views

1

Cite this

Summary :

With the development of the Internet of Vehicles, License plate detection technology is widely used, e.g., smart city and edge senor monitor. However, traditional license plate detection methods are based on the license plate edge detection, only suitable for limited situation, such as, wealthy light and favorable camera's angle. Fortunately, deep learning networks represented by YOLOv3 can solve the problem, relying on strict condition. Although YOLOv3 make it better to detect large targets, its low performance in detecting small targets and lack of the real-time interactively. Motivated by this, we present a faster and lightweight YOLOv3 model for multi-vehicle or under-illuminated images scenario. Generally, our model can serves as a guideline for optimizing neural network in multi-vehicle scenario.

Publication: IEICE TRANSACTIONS on Information Vol.E104-D No.5 pp.723-728

Publication Date: 2021/05/01

Publicized: 2021/02/22

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2020EDP7260

Type of Manuscript: PAPER

Category: Artificial Intelligence, Data Mining

Authors

Yuchao SUN
  Nanjing University of Posts and Telecommunications
Qiao PENG
  Nanjing University of Posts and Telecommunications
Dengyin ZHANG
  Nanjing University of Posts and Telecommunications

Keyword

plate detection, YOLOv3, multi-vehicle scenario

Cite this

Copy

Yuchao SUN, Qiao PENG, Dengyin ZHANG, "Light-YOLOv3: License Plate Detection in Multi-Vehicle Scenario" in IEICE TRANSACTIONS on Information, vol. E104-D, no. 5, pp. 723-728, May 2021, doi: 10.1587/transinf.2020EDP7260.
Abstract: With the development of the Internet of Vehicles, License plate detection technology is widely used, e.g., smart city and edge senor monitor. However, traditional license plate detection methods are based on the license plate edge detection, only suitable for limited situation, such as, wealthy light and favorable camera's angle. Fortunately, deep learning networks represented by YOLOv3 can solve the problem, relying on strict condition. Although YOLOv3 make it better to detect large targets, its low performance in detecting small targets and lack of the real-time interactively. Motivated by this, we present a faster and lightweight YOLOv3 model for multi-vehicle or under-illuminated images scenario. Generally, our model can serves as a guideline for optimizing neural network in multi-vehicle scenario.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7260/_p

Copy

@ARTICLE{e104-d_5_723,
author={Yuchao SUN, Qiao PENG, Dengyin ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Light-YOLOv3: License Plate Detection in Multi-Vehicle Scenario},
year={2021},
volume={E104-D},
number={5},
pages={723-728},
abstract={With the development of the Internet of Vehicles, License plate detection technology is widely used, e.g., smart city and edge senor monitor. However, traditional license plate detection methods are based on the license plate edge detection, only suitable for limited situation, such as, wealthy light and favorable camera's angle. Fortunately, deep learning networks represented by YOLOv3 can solve the problem, relying on strict condition. Although YOLOv3 make it better to detect large targets, its low performance in detecting small targets and lack of the real-time interactively. Motivated by this, we present a faster and lightweight YOLOv3 model for multi-vehicle or under-illuminated images scenario. Generally, our model can serves as a guideline for optimizing neural network in multi-vehicle scenario.},
keywords={},
doi={10.1587/transinf.2020EDP7260},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Light-YOLOv3: License Plate Detection in Multi-Vehicle Scenario
T2 - IEICE TRANSACTIONS on Information
SP - 723
EP - 728
AU - Yuchao SUN
AU - Qiao PENG
AU - Dengyin ZHANG
PY - 2021
DO - 10.1587/transinf.2020EDP7260
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2021
AB - With the development of the Internet of Vehicles, License plate detection technology is widely used, e.g., smart city and edge senor monitor. However, traditional license plate detection methods are based on the license plate edge detection, only suitable for limited situation, such as, wealthy light and favorable camera's angle. Fortunately, deep learning networks represented by YOLOv3 can solve the problem, relying on strict condition. Although YOLOv3 make it better to detect large targets, its low performance in detecting small targets and lack of the real-time interactively. Motivated by this, we present a faster and lightweight YOLOv3 model for multi-vehicle or under-illuminated images scenario. Generally, our model can serves as a guideline for optimizing neural network in multi-vehicle scenario.
ER -