WASTE OBJECT DETECTION USING YOLOV5 (KEY IJP************648)

• Pavithra M

Abstract

Waste object detection plays a pivotal role in efficient waste management systems, contributing to environmental sustainability and resource optimization. This paper presents a novel approach to waste object detection utilizing the You Only Look Once (YOLO) deep learning framework. YOLO offers real-time object detection capabilities, making it suitable for deployment in waste management systems where timely detection and classification of waste objects are essential. Our methodology involves the training of a YOLO model on annotated waste object datasets, enabling the model to accurately detect various types of waste items such as plastics, paper, glass, and organic materials. We evaluate the performance of the proposed approach using standard metrics such as precision, recall, and F1 score, demonstrating its effectiveness in identifying waste objects in diverse environmental conditions and cluttered scenes. Furthermore, we discuss potential applications and implications of waste object detection using YOLO, including automated sorting in recycling facilities, monitoring waste disposal sites, and guiding autonomous waste collection systems. Overall, our research contributes to the advancement of smart waste management systems by leveraging stateof-the-art deep learning techniques for efficient waste object detection.