Related Experiment Video
Updated: Aug 7, 2026
08:25
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
Published on: May 7, 2019
9.0K
A Real-Time License Plate Detection and Recognition Model in Unconstrained Scenarios
Lingbing Tao1, Shunhe Hong1, Yongxing Lin1,2
1School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China.
Sensors (Basel, Switzerland)
|May 11, 2024
Summary
This study introduces YOLOv5-PDLPR, a new model for vehicle license plate recognition. It achieves accurate and fast real-time recognition, even in complex environments.
Area of Science:
- Computer Vision
- Artificial Intelligence
- Machine Learning
Background:
- Vehicle license plate recognition is vital but challenging in natural scenes.
- Current methods struggle with complex environments, leading to performance degradation.
Purpose of the Study:
- To propose a novel and robust license plate detection and recognition model.
- To enhance accuracy and speed for real-time applications in complex scenarios.
Main Methods:
- Utilized YOLOv5 for efficient license plate detection.
- Developed the PDLPR algorithm featuring Multi-Head Attention for character recognition.
- Incorporated a global feature extractor and a parallel decoder for improved performance and efficiency.
Main Results:
- The YOLOv5-PDLPR model demonstrated superior accuracy and speed compared to existing algorithms.
- Achieved real-time vehicle license plate recognition capabilities.
- Exhibited high efficiency and robustness in complex natural scene images.
Conclusions:
- The proposed YOLOv5-PDLPR model offers a significant advancement in vehicle license plate recognition.
- It provides a reliable solution for real-time applications facing environmental complexities.
