• M Ramya
• Shinde Vaibhav
• Kisshore N
• Amara Chidvi Sri Sanjana
• B Himanth

Addressing the critical need for improved waste management practices, this work presents a novel system integrating AI-powered object detection with an incentive-based recycling program. The methodology employs a YOLOv8l object detection model trained on a comprehensive dataset of waste images, webcam integration for real-time waste identification, and a user-friendly Streamlit interface connected to a MongoDB database for user management and transaction tracking. The system incorporates barcode scanning for precise waste item identification and assigns monetary rewards for each waste item disposed properly, effectively gamifying the recycling process. Results demonstrate high object detection accuracy, increased user participation in recycling, significant waste diversion from landfills, and a reduction in carbon footprint. Predictive modeling showcases the potential for forecasting future waste generation and carbon emission trends. The system represents a significant step towards sustainable waste management, offering scalability and adaptability for integration into existing infrastructure.

Waste Management, Object Detection, YOLOv8l, Recycling Incentives, Carbon Footprint, Streamlit, MongoDB, Gamification.

"Optimizing Waste Management Through AI-Powered Object Detection and Incentive-Based Recycling Programs", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.b67-b71, March-2025, Available :http://www.jetir.org/papers/JETIR2503109.pdf

"Optimizing Waste Management Through AI-Powered Object Detection and Incentive-Based Recycling Programs", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppb67-b71, March-2025, Available at : http://www.jetir.org/papers/JETIR2503109.pdf