Real-Time Detection and Classification of Traffic Signs using YOLOv5s object detection algorithm. This project incorporates multilingual voice alerts and a user-friendly Tkinter-based GUI with various camera options for enhanced road safety.

Real-Time Traffic Sign Detection and Classification with Voice Alert

An advanced real-time traffic sign detection and classification system with voice alert capabilities. The project employs YOLOv5 for accurate and swift detection, providing multilingual voice alerts through a user-friendly Tkinter GUI. Enhance road safety and driving experience with this comprehensive solution.

Features
Multilingual Alerts and Tkinter GUI
Technologies Used
System Requirement
Installation
Usage
Contributing

Features

Real-Time Detection: Achieve up to 45 fps for swift and accurate traffic sign detection.
Multilingual Voice Alerts: Receive alerts in English, Hindi, and Marathi for diverse user communication.
Tkinter GUI: Intuitive graphical interface providing clear visual and audio feedback.
Multiple Camera Options: Support for default laptop camera, USB camera, and wireless or IP camera.

Multilingual Alerts and Tkinter GUI

The project provides voice alerts in English, Hindi, and Marathi using the gtts library. The Tkinter-based GUI ensures a user-friendly interface, offering visual and audio notifications for identified traffic signs.

Technologies Used

YOLOv5
OpenCV
gtts (Google Text-to-Speech)
Tkinter

System Requirement

Operating System: Windows 10/11
Python Version: 3.8 to 3.11.5 (preferably 3.11.5)
Internet Connectivity: Required for voice alerts using gtts library
Camera: Default camera of laptop/USB camera/wireless or IP camera

Installation

Clone the repository:

  git clone https://github.com/onkaryemul/Real-Time-Traffic-Sign-Detection-and-Classification-with-Voice-Alert.git

Navigate to the project directory:

  cd Real-Time-Traffic-Sign-Detection-and-Classification-with-Voice-Alert

Install dependencies:
```
  pip install -r requirements.txt
```

Installation instructions for `playsound` library:

If you encounter issues with automatic installation, you can install playsound manually by following these steps:

Download the source code from the playsound GitHub repository: playsound on GitHub.
Extract the downloaded archive.
Open a command prompt or terminal in the extracted directory.
Run the following command to install playsound:
```
  python setup.py install
```

Usage

Navigate to the Codes directory inside main project Real-Time-Traffic-Sign-Detection-and-Classification-with-Voice-Alert :
```
  cd Codes
```
Run the detection script with the desired parameters For running on the Default Webcam of the laptop, run:
```
  python detect.py --source 0
```
OR

Run the Python TKinter GUI Application script by executing following command:
```
   python gui.py
```

Instructions for providing Wireless or IP Camera Streaming URL:

In the streaming URL entry, you can use the following format for an IP camera:

  For general format: http://username:password@IP:PORT/video
  Example: http://admin:your_password@192.168.1.100:8080/video

Make sure to replace 'username', 'password', 'IP', 'PORT', and 'your_password' with the actual credentials and details of your IP camera.

For more details on accessing IP cameras in Python using OpenCV, refer to the following Stack Overflow post: Access IP Camera in Python OpenCV

Testing:

Navigate to the Codes directory:
```
  cd Codes
```
For testing: Before running the next command, put your test file in the directory named Test.
```
  python detect.py --source ../Test/(name of your file)
```
For example, if your image name is test.jpg, then put your image in the directory named Test and run:
```
  python detect.py --source ../Test/test1.jpeg
```
Above, the same step can also be used to test the model on video files.

Contributing

Contributions are welcome! Feel free to fork the repository, make improvements, and submit a pull request. Please follow best practices and maintain code clarity.

If you would like to contribute to the project, follow these steps:

Fork the repository.

Create a new branch:

  git checkout -b feature/your-feature-name

Make your changes and commit:
```
  git commit -m "Add your feature"
```

Push to your branch:

  git push origin feature/your-feature-name

Create a pull request on GitHub.

onkaryemul/Real-Time-Traffic-Sign-Detection-and-Classification-with-Voice-Alert