Staff View: An optimized YOLO-based object detection model for crop harvesting system

An optimized YOLO-based object detection model for crop harvesting system

The adoption of automated crop harvesting system based on machine vision may improve productivity and optimize the operational cost. The scope of this study is to obtain visual information at the plantation which is crucial in developing an intelligent automated crop harvesting system. This paper ai...

Full description

Saved in:

Bibliographic Details
Main Authors:	Junos, Mohamad Haniff, Mohd Khairuddin, Anis Salwa, Thannirmalai, Subbiah, Dahari, Mahidzal
Format:	Article
Published:	Wiley 2021
Subjects:	TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://eprints.um.edu.my/26781/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.26781
record_format	eprints
spelling	my.um.eprints.267812022-04-14T04:27:06Z http://eprints.um.edu.my/26781/ An optimized YOLO-based object detection model for crop harvesting system Junos, Mohamad Haniff Mohd Khairuddin, Anis Salwa Thannirmalai, Subbiah Dahari, Mahidzal TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering The adoption of automated crop harvesting system based on machine vision may improve productivity and optimize the operational cost. The scope of this study is to obtain visual information at the plantation which is crucial in developing an intelligent automated crop harvesting system. This paper aims to develop an automatic detection system with high accuracy performance, low computational cost and lightweight model. Considering the advantages of YOLOv3 tiny, an optimized YOLOv3 tiny network namely YOLO-P is proposed to detect and localize three objects at palm oil plantation which include fresh fruit bunch, grabber and palm tree under various environment conditions. The proposed YOLO-P model incorporated lightweight backbone based on densely connected neural network, multi-scale detection architecture and optimized anchor box size. The experimental results demonstrated that the proposed YOLO-P model achieved good mean average precision and F1 score of 98.68% and 0.97 respectively. Besides, the proposed model performed faster training process and generated lightweight model of 76 MB. The proposed model was also tested to identify fresh fruit bunch of various maturities with accuracy of 98.91%. The comprehensive experimental results show that the proposed YOLO-P model can effectively perform robust and accurate detection at the palm oil plantation. Wiley 2021-07 Article PeerReviewed Junos, Mohamad Haniff and Mohd Khairuddin, Anis Salwa and Thannirmalai, Subbiah and Dahari, Mahidzal (2021) An optimized YOLO-based object detection model for crop harvesting system. IET Image Processing, 15 (9). pp. 2112-2125. ISSN 1751-9659, DOI https://doi.org/10.1049/ipr2.12181 <https://doi.org/10.1049/ipr2.12181>. 10.1049/ipr2.12181
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	TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering Junos, Mohamad Haniff Mohd Khairuddin, Anis Salwa Thannirmalai, Subbiah Dahari, Mahidzal An optimized YOLO-based object detection model for crop harvesting system
description	The adoption of automated crop harvesting system based on machine vision may improve productivity and optimize the operational cost. The scope of this study is to obtain visual information at the plantation which is crucial in developing an intelligent automated crop harvesting system. This paper aims to develop an automatic detection system with high accuracy performance, low computational cost and lightweight model. Considering the advantages of YOLOv3 tiny, an optimized YOLOv3 tiny network namely YOLO-P is proposed to detect and localize three objects at palm oil plantation which include fresh fruit bunch, grabber and palm tree under various environment conditions. The proposed YOLO-P model incorporated lightweight backbone based on densely connected neural network, multi-scale detection architecture and optimized anchor box size. The experimental results demonstrated that the proposed YOLO-P model achieved good mean average precision and F1 score of 98.68% and 0.97 respectively. Besides, the proposed model performed faster training process and generated lightweight model of 76 MB. The proposed model was also tested to identify fresh fruit bunch of various maturities with accuracy of 98.91%. The comprehensive experimental results show that the proposed YOLO-P model can effectively perform robust and accurate detection at the palm oil plantation.
format	Article
author	Junos, Mohamad Haniff Mohd Khairuddin, Anis Salwa Thannirmalai, Subbiah Dahari, Mahidzal
author_facet	Junos, Mohamad Haniff Mohd Khairuddin, Anis Salwa Thannirmalai, Subbiah Dahari, Mahidzal
author_sort	Junos, Mohamad Haniff
title	An optimized YOLO-based object detection model for crop harvesting system
title_short	An optimized YOLO-based object detection model for crop harvesting system
title_full	An optimized YOLO-based object detection model for crop harvesting system
title_fullStr	An optimized YOLO-based object detection model for crop harvesting system
title_full_unstemmed	An optimized YOLO-based object detection model for crop harvesting system
title_sort	optimized yolo-based object detection model for crop harvesting system
publisher	Wiley
publishDate	2021
url	http://eprints.um.edu.my/26781/
_version_	1735409457376002048
score	13.211869

An optimized YOLO-based object detection model for crop harvesting system

Similar Items