Sustainable Waste Management through ML-based Real-Time Trash Bin Prediction

 

Sandeep Kumar1, Vikrant Shokeen2, Amit Sharma3, Prabhat K. Srivastava4, Upasana Dugal5, Aditi Sharma6,*

1,2Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, New Delhi, India

3Department of Information Technology, IMS Engineering College, Ghaziabad, UP, India

4Department of Computer Science and Engineering, IMS Engineering College, Ghaziabad, UP, India

5Department of Computer Science and Engineering, Babu Banarasi Das University, Lucknow, India

6*Department of Computer Science and Engineering, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, India

 

Emails: san.jaglan@gmail.com; shokeen18@gmail.com; amit.faculty@gmail.com; sri_prab@rediffmail.com; upasana_gupta31@bbdu.ac.in; aditi.sharma@ieee.org  

 

 

Received: August 17, 2023 Revised: November 29, 2023 Accepted: April 13, 2024

Text Box: Abstract Waste management has been an issue due to low awareness among people of any country to lead major environmental contamination, tragic accidents, and unfavorable working conditions for landfill workers. The Lack of precise and efficient object detection could be a barrier in the growth of computer vision-based systems. As per the latest research articles, pre-trained models could be used for Trash Bin detection in real time and for recommending appropriate actions after detection. Using a unique validation dataset made up of predicted trash items, the two classes of acceptable object identification models, YOLO (You Only Look Once) and SSD (Single Shot Multibox Detector), are then contrasted. It is concluded that SSD performs noticeably better than YOLO in identifying trash objects based on several performance metrics computed utilizing multiple open-source research projects. The model is then built up to recognize several trash object types after being pre-trained using Microsoft's COCO (Common Objects in Context) dataset. Our initiative intends to enhance sustainable waste management, make trash sorting incredibly simple, and guard against serious illnesses and accidents at landfill and garbage disposal sites.

 

Keywords: Garbage detection; Machine Learning; Waste management; You Only Look Once Mode; Single Shot Multibox Detector; Common Objects in Context