Automated Carrot Harvesting Machine With YOLOv8 for Precision and Optimal Efficiency

Zeeshan, S; Malik, MAI

Automated Carrot Harvesting Machine With YOLOv8 for Precision and Optimal Efficiency

Zeeshan, S Malik, MAI

Permalink

Publisher:: WILEY
Publication Type:: Journal Article
Citation:: Journal of Engineering United Kingdom, 2025, 2025, (1)
Issue Date:: 2025-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (5.08 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zeeshan, S
dc.contributor.author	Malik, MAI
dc.contributor.editor	Angiulli, G
dc.date.accessioned	2026-01-28T01:06:22Z
dc.date.available	2026-01-28T01:06:22Z
dc.date.issued	2025-01-01
dc.identifier.citation	Journal of Engineering United Kingdom, 2025, 2025, (1)
dc.identifier.issn	2314-4904
dc.identifier.issn	2314-4912
dc.identifier.uri	http://hdl.handle.net/10453/192456
dc.description.abstract	Carrots are a key staple in Pakistan’s agriculture, yet harvesting practices remain predominantly manual, resulting in high labor costs, inefficiencies, and considerable postharvest losses. The current study presents the design and fabrication of a cost-effective, intelligent carrot harvesting machine, modeled in SolidWorks and optimized for key operational parameters: claw belt speed of 4 m/s, roller speed of 1.2 m/s, and a taper angle of 26°, to maximize pick-up efficiency and minimize crop damage. A YOLOv8-based quality assessment model, trained on a region-specific annotated dataset of local carrot varieties, was integrated for real-time defect detection. The model achieved high accuracy (approximately 0.98), F1-score (approximately 0.95), and mAP@0.5 (approximately 0.94), ensuring the reliable sorting of high-quality produce. Laboratory evaluations demonstrated significant performance gains over manual harvesting methods in terms of speed (3–5 acres/day vs. 0.2–0.5 acres/day), efficiency (80%–92%), and reduced physical strain. These findings support the adoption of mechanized harvesting aligned with precision agriculture to enhance productivity, safety, and sustainability.
dc.language	English
dc.publisher	WILEY
dc.relation.ispartof	Journal of Engineering United Kingdom
dc.relation.isbasedon	10.1155/je/7098166
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	09 Engineering
dc.subject.classification	40 Engineering
dc.title	Automated Carrot Harvesting Machine With YOLOv8 for Precision and Optimal Efficiency
dc.type	Journal Article
utslib.citation.volume	2025
utslib.for	09 Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Civil and Environmental Engineering
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/Engineering and IT Related HDR Students
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2026-01-28T01:06:20Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	2025
utslib.citation.issue	1

Abstract:

Carrots are a key staple in Pakistan’s agriculture, yet harvesting practices remain predominantly manual, resulting in high labor costs, inefficiencies, and considerable postharvest losses. The current study presents the design and fabrication of a cost-effective, intelligent carrot harvesting machine, modeled in SolidWorks and optimized for key operational parameters: claw belt speed of 4 m/s, roller speed of 1.2 m/s, and a taper angle of 26°, to maximize pick-up efficiency and minimize crop damage. A YOLOv8-based quality assessment model, trained on a region-specific annotated dataset of local carrot varieties, was integrated for real-time defect detection. The model achieved high accuracy (approximately 0.98), F1-score (approximately 0.95), and mAP@0.5 (approximately 0.94), ensuring the reliable sorting of high-quality produce. Laboratory evaluations demonstrated significant performance gains over manual harvesting methods in terms of speed (3–5 acres/day vs. 0.2–0.5 acres/day), efficiency (80%–92%), and reduced physical strain. These findings support the adoption of mechanized harvesting aligned with precision agriculture to enhance productivity, safety, and sustainability.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/192456