Enhanced YOLOv8-Based System for Automatic Number Plate Recognition
Усовершенствованная система распознавания автомобильных номерных знаков на основе YOLOv8
2024-09-13
SCID: 54.1/dy8qj3c8
Discuss with AI
Qatar license platesYOLOv8automatic number plate recognitionedge computinglicense plate detection
Figures from the paper
Abstract (AI)
This paper presents an advanced automatic number plate recognition (ANPR) system designed specifically for Qatar’s diverse license plate landscape and challenging environmental conditions. Leveraging the YOLOv8 deep learning model, particularly the YOLOv8s variant, we achieve state-of-the-art accuracy in both license plate detection and number recognition. Our innovative approach includes a comprehensive dataset enhancement technique that simulates adverse conditions, significantly improving the model’s robustness in real-world scenarios. We integrate edge computing using a Raspberry Pi with server-side processing, demonstrating an efficient solution for real-time ANPR applications. The system maintains greater than 93% overall performance across various environmental conditions, including night-time and rainy scenarios. We also explore the impact of various pre-processing techniques, including edge detection, k-mean thresholding, DBSCAN, and Gaussian mixture models, on the ANPR system’s performance. Our findings indicate that modern deep learning models like YOLOv8 are sufficiently robust to handle raw input images and do not significantly benefit from additional pre-processing. With its high accuracy and real-time processing capability, the proposed system represents a significant advancement in ANPR technology and is particularly suited for Qatar’s unique traffic management needs and smart city initiatives.
Key Findings
1
Additional preprocessing methods, including edge detection, k-means thresholding, DBSCAN, and Gaussian mixture models, provide no significant benefit over raw images with YOLOv8.
2
Combining Raspberry Pi edge computing with server-side processing enables real-time ANPR deployment.
3
Dataset enhancement through simulated adverse conditions significantly improves robustness in real-world ANPR scenarios.
4
The YOLOv8s-based ANPR system is tailored to Qatar’s diverse license plates and challenging environmental conditions.
5
The system achieves greater than 93% overall performance across varied conditions, including nighttime and rain.
Research Object
Qatar license plates in real-world environmental conditions
Research Subject
the accuracy, robustness, and real-time performance of automatic number plate detection and recognition under diverse and adverse conditions
Publication Details
Publication Date
2024-09-13
Journal
Publisher
ISSN
Cited by
26
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest