Built for SSC Campus Traffic During Large-Scale Events
This project aims to solve traffic management issues during large-scale events by automating license plate detection and reading. It reduces the need for manual traffic direction, making the process more efficient and less labor-intensive.
- Camera Source Detection: Automatically detects available camera sources on the system.
- Camera Selection: Allows the user to select a camera source for license plate detection.
- License Plate Detection: Utilizes the Haar Cascade classifier for Russian license plate detection.
- OCR: Extracts text from detected license plates using the EasyOCR engine.
- Video Stream Display: Displays the video stream with detected license plates highlighted and the extracted text.
automated_traffic_event_managment_system/
├── Main.py
├── README.md
├── LICENSE
└── requirements.txt
- Python: Version 3.8.20 or later
To build the project from source:
-
Clone the repository:
git clone https://github.com/keyframesfound/ATEMS
-
Navigate to the project directory:
cd ATEMS -
For Linux installations only:
source myenv/bin/activate -
Install required packages:
pip install opencv-python torch easyocr yolov5 numpy flask python-Levenshtein
To run the project, execute the following command:
python3 Main.py- Task 1: Add OCR engine to code
- Task 2: Achieve 80% accuracy in the system
- Task 3: Achieve 99% accuracy and connect light/traffic direction signs
- Task 4: Full automatic test for large-scale events
This project is licensed under the MIT License.
- automatic-number-plate-recognition-python-yolov8
- Car-Number-Plate-Recognition-System
- DetectCarDistanceAndRoadLane
- Huggingface Model