OS12-18 A Research on Front-End Garbage Classification Based on Machine Vision

Title:	OS12-18 A Research on Front-End Garbage Classification Based on Machine Vision
Publication:	ICAROB2021
Volume:	26
Pages:	720-723
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2021.OS12-18
Author(s):	Longyu Gao, Zhiqing Xiao, Junlong Hao, Luqi Shen, Manqian Hu
Publication Date:	January 21, 2021
Keywords:	machine vision, intelligent classification, convolutional neural network
Abstract:	Adding a machine vision recognition module to the traditional smart trash can can effectively improve the efficiency of trash recognition. The intelligent garbage classification model constructed by the convolutional neural network can accurately identify the types of garbage, with an average accuracy rate of 0.87. Deploy the trained model on openMV and test it on the produced physical trash can. After the system is stable, the average time to complete a sorting and recovery is 2s. Experiments show that the system can effectively identify the types of garbage and complete garbage classification and recycling.
PDF File:	https://alife-robotics.co.jp/members2021/icarob/data/html/data/OS/OS12/OS12-18.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/