Staff View: An automatic garbage detection using optimized YOLO model

An automatic garbage detection using optimized YOLO model

Garbage pollution is an increasing global concern. Hence, the adoption of innovative solutions is important for controlling garbage pollution. In order to develop an efficient cleaner robot, it is very crucial to obtain visual information of floating garbage on the river. Deep learning has been acti...

Full description

Saved in:

Bibliographic Details
Main Authors:	Zailan, Nur Athirah, Mohd Khairuddin, Anis Salwa, Hasikin, Khairunnisa, Junos, Mohamad Haniff, Khairuddin, Uswah
Format:	Article
Published:	Springer Science and Business Media Deutschland GmbH 2024
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://eprints.um.edu.my/44817/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.44817
record_format	eprints
spelling	my.um.eprints.448172024-07-09T08:22:49Z http://eprints.um.edu.my/44817/ An automatic garbage detection using optimized YOLO model Zailan, Nur Athirah Mohd Khairuddin, Anis Salwa Hasikin, Khairunnisa Junos, Mohamad Haniff Khairuddin, Uswah TK Electrical engineering. Electronics Nuclear engineering Garbage pollution is an increasing global concern. Hence, the adoption of innovative solutions is important for controlling garbage pollution. In order to develop an efficient cleaner robot, it is very crucial to obtain visual information of floating garbage on the river. Deep learning has been actively applied over the past few years to tackle various problems. High-level, semantic, and advanced features can be learnt by deep learning models based on visual information. This is extremely important to detect and classify different types of floating garbage. This paper proposed an optimized You Only Look Once v4 Tiny model to detect floating garbage, mainly by improving the spatial pyramid pooling with average pooling, mish activation function, concatenated densely connected neural network, and hyperparameters optimization. The proposed model shows improved results of 74.89 mean average precision with a size of 16.4 MB, which can be concluded as the best trade-off among other models. The proposed model has promising results in terms of model size, detection time and memory space, which is feasible to be embedded in low-cost devices. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature. Springer Science and Business Media Deutschland GmbH 2024 Article PeerReviewed Zailan, Nur Athirah and Mohd Khairuddin, Anis Salwa and Hasikin, Khairunnisa and Junos, Mohamad Haniff and Khairuddin, Uswah (2024) An automatic garbage detection using optimized YOLO model. Signal, Image and Video Processing, 18 (1). 315 – 323. ISSN 1863-1703, DOI https://doi.org/10.1007/s11760-023-02736-3 <https://doi.org/10.1007/s11760-023-02736-3>. 10.1007/s11760-023-02736-3
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering Zailan, Nur Athirah Mohd Khairuddin, Anis Salwa Hasikin, Khairunnisa Junos, Mohamad Haniff Khairuddin, Uswah An automatic garbage detection using optimized YOLO model
description	Garbage pollution is an increasing global concern. Hence, the adoption of innovative solutions is important for controlling garbage pollution. In order to develop an efficient cleaner robot, it is very crucial to obtain visual information of floating garbage on the river. Deep learning has been actively applied over the past few years to tackle various problems. High-level, semantic, and advanced features can be learnt by deep learning models based on visual information. This is extremely important to detect and classify different types of floating garbage. This paper proposed an optimized You Only Look Once v4 Tiny model to detect floating garbage, mainly by improving the spatial pyramid pooling with average pooling, mish activation function, concatenated densely connected neural network, and hyperparameters optimization. The proposed model shows improved results of 74.89 mean average precision with a size of 16.4 MB, which can be concluded as the best trade-off among other models. The proposed model has promising results in terms of model size, detection time and memory space, which is feasible to be embedded in low-cost devices. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
format	Article
author	Zailan, Nur Athirah Mohd Khairuddin, Anis Salwa Hasikin, Khairunnisa Junos, Mohamad Haniff Khairuddin, Uswah
author_facet	Zailan, Nur Athirah Mohd Khairuddin, Anis Salwa Hasikin, Khairunnisa Junos, Mohamad Haniff Khairuddin, Uswah
author_sort	Zailan, Nur Athirah
title	An automatic garbage detection using optimized YOLO model
title_short	An automatic garbage detection using optimized YOLO model
title_full	An automatic garbage detection using optimized YOLO model
title_fullStr	An automatic garbage detection using optimized YOLO model
title_full_unstemmed	An automatic garbage detection using optimized YOLO model
title_sort	automatic garbage detection using optimized yolo model
publisher	Springer Science and Business Media Deutschland GmbH
publishDate	2024
url	http://eprints.um.edu.my/44817/
_version_	1805881171214598144
score	13.211869

An automatic garbage detection using optimized YOLO model

Similar Items