Work

Exploring the Performance of YOLOv11: Detecting Compostable and Non-Compostable Kitchen Waste in Real-Time Applications

Year: 2025

Type: conference-paper

Abstract: This paper investigates the advancements of YOLOv11, the latest model in the YOLO series in real-time object detection tasks on small datasets of compostable and non-compostable kitchen waste.Using a custom compostable and non-compostable kitchen waste dataset, YOLOv11 achieves an accuracy of 90.7% and a mean Average Precision (mAP) of 0.91, with a reduced inference time of 10.5 milliseconds.The study highlights YOLOv11's architectural enhancements, training methodology, and potential applications in waste management.While YOLOv11 sets a new benchmark in object detection, challenges like high computational demands, paving the way for future research on optimization for edge devices

Source: Proceedings of International Conference on Artificial Life and Robotics

DOI: 10.5954/icarob.2025.os13-3

Authors: Ain Atiqa Mustapha, Sarah Atifah Saruchi, Mahmud Iwan Solihin, Fatima Karam Aldeen, Ammar A Al-Talib

Institutions: Universiti Malaysia Pahang Al-Sultan Abdullah, UCSI University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Responsible consumption and production

Open Access status: bronze

Funder: Universiti Malaysia Pahang