PlatePatrol

demo.mp4

Description

This project develops a real-time vehicle detection and license plate recognition system using advanced deep learning techniques. By integrating the YOLO (You Only Look Once) model for object detection and the SORT (Simple Online and Realtime Tracking) algorithm for tracking, the system efficiently identifies and tracks vehicles in video footage. Additionally, it utilizes a specialized model for accurately detecting and reading license plate numbers.

Data

The video I used in this tutorial can be downloaded here.

Model

A Yolov8 pre-trained model (YOLOv8n) was used to detect vehicles.

A licensed plate detector was used to detect license plates. The model was trained with Yolov8 using this dataset.

Dependencies

The sort module needs to be downloaded from this repository.

Installation

To get started, follow these steps:

1. Clone the repository:

   git clone https://github.com/arij01/automatic-number-plate-recognition.git

2. Navigate to the project directory:

   cd automatic-number-plate-recognition

3. Install dependencies:

   pip install -r requirements.txt

4. Run main.py:

   python main.py

5. Run the add_missing_data.py file:

   python add_missing_data.py

6. Run the visualize.py file:

   python visualize.py