This project implements an AI-powered garbage detection and sorting system using the YOLOv8 model for precise waste classification. The system is designed to enhance waste sorting efficiency and promote sustainable waste management practices.
- Real-time garbage detection and classification
- Supports six categories: cardboard, plastic, glass, paper, metal, and biodegradable waste
- User-friendly interface using Streamlit
- Easy integration with camera systems for live detection
- Scalable and adaptable for various environments
-
Clone the repository:
git clone https://github.com/binguliki/Garbage-Detection.git cd Garbage Detection
-
Install the required dependencies:
pip install -r requirements.txt
-
Start the Streamlit application:
streamlit run app.py
-
Click the "Start Camera" button to begin the live detection.
-
The system will display detected objects and their classifications in real-time.
-
Click the "Stop Camera" button to stop the live feed.
- Description: The dataset includes images of various waste types, categorized into cardboard, plastic, glass, paper, metal, and biodegradable waste.
- Source: Waste Sorting Dataset (Replace with actual source)
- Preprocessing: Images are resized, normalized, and augmented for better training performance.
Garbage.Detection.sample.mp4
- Municipal Waste Authorities: Streamline waste sorting processes, reduce contamination, and improve overall efficiency.
- Recycling Facilities: Automate sorting, enhance recycling rates, and separate materials more effectively.
- Large Businesses: Improve waste management practices, minimize waste generation, and optimize recycling efforts.
We welcome contributions to improve the project! To contribute, please follow these steps:
- Fork the repository.
- Create a new branch (
git checkout -b feature-branch
). - Make your changes.
- Commit your changes (
git commit -m 'Add new feature'
). - Push to the branch (
git push origin feature-branch
). - Create a pull request.
Thanks to the following people who have contributed to this project: