Please use this identifier to cite or link to this item:
|Title:||Multispectral vineyard segmentation: A deep learning comparison study||Authors:||Barros, T.
Ferreira, C. S. S.
Nunes, U. J.
|Keywords:||Multispectral; Vineyard segmentation; Deep learning; Precision agriculture||Issue Date:||2022||Project:||info:eu-repo/grantAgreement/FCT/3599-PPCDT/MIT-EXPL/TDI/0029/2019/PT/Intelligent Automation in Precise Agriculture AI+Green
info:eu-repo/grantAgreement/EC/H2020/781086/EU/Crux Agribotics: The future of cucumbers harvesting - robot for automated agriculture labors
info:eu-repo/grantAgreement/FCT/POR_CENTRO/2021.06492.BD/PT/Multi-modal perception for long-term localization in human-centered robotics
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB/00048/2020/PT/INSTITUTE OF SYSTEMS AND ROBOTICS - ISR - COIMBRA
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB/00308/2020/PT/Institute for Systems Engineering and Computers at Coimbra - INESC Coimbra
|Serial title, monograph or event:||Computers and Electronics in Agriculture||Volume:||195||Abstract:||Digital agriculture has evolved significantly over the last few years due to the technological developments in automation and computational intelligence applied to the agricultural sector, including vineyards which are a relevant crop in the Mediterranean region. In this work, a study is presented of semantic segmentation for vine detection in real-world vineyards by exploring state-of-the-art deep segmentation networks and conventional unsupervised methods. Camera data have been collected on vineyards using an Unmanned Aerial System (UAS) equipped with a dual imaging sensor payload, namely a high-definition RGB camera and a five-band multispectral and thermal camera. Extensive experiments using deep-segmentation networks and unsupervised methods have been performed on multimodal datasets representing four distinct vineyards located in the central region of Portugal. The reported results indicate that SegNet, U-Net, and ModSegNet have equivalent overall performance in vine segmentation. The results also show that multimodality slightly improves the performance of vine segmentation, but the NIR spectrum alone generally is sufficient on most of the datasets. Furthermore, results suggest that high-definition RGB images produce equivalent or higher performance than any lower resolution multispectral band combination. Lastly, Deep Learning (DL) networks have higher overall performance than classical methods. The code and dataset are publicly available on https://github.com/Cybonic/DL_vineyard_segmentation_study.git.||URI:||https://hdl.handle.net/10316/100144||ISSN:||01681699||DOI:||10.1016/j.compag.2022.106782||Rights:||openAccess|
|Appears in Collections:||I&D IT - Artigos em Revistas Internacionais|
Show full item record
Files in This Item:
checked on Nov 9, 2022
WEB OF SCIENCETM
checked on Dec 2, 2023
checked on Nov 28, 2023
checked on Nov 28, 2023
This item is licensed under a Creative Commons License