Vineyard Gap Detection by Convolutional Neural Networks Fed by Multi-Spectral Images
This paper focuses on the gaps that occur inside plantations; these gaps, although not having anything growing in them, still happen to be watered. This action ends up wasting tons of liters of water every year, which translates into financial and environmental losses. To avoid these losses, we sugg...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/15/12/440 |
| _version_ | 1797461812968423424 |
|---|---|
| author | Shazia Sulemane João P. Matos-Carvalho Dário Pedro Filipe Moutinho Sérgio D. Correia |
| author_facet | Shazia Sulemane João P. Matos-Carvalho Dário Pedro Filipe Moutinho Sérgio D. Correia |
| author_sort | Shazia Sulemane |
| collection | DOAJ |
| description | This paper focuses on the gaps that occur inside plantations; these gaps, although not having anything growing in them, still happen to be watered. This action ends up wasting tons of liters of water every year, which translates into financial and environmental losses. To avoid these losses, we suggest early detection. To this end, we analyzed the different available neural networks available with multispectral images. This entailed training each regional and regression-based network five times with five different datasets. Networks based on two possible solutions were chosen: unmanned aerial vehicle (UAV) depletion or post-processing with external software. The results show that the best network for UAV depletion is the Tiny-YOLO (You Only Look Once) version 4-type network, and the best starting weights for Mask-RCNN were from the Tiny-YOLO network version. Although no mean average precision (mAP) of over 70% was achieved, the final trained networks managed to detect mostly gaps, including low-vegetation areas and very small gaps, which had a tendency to be overlooked during the labeling stage. |
| first_indexed | 2024-03-09T17:24:42Z |
| format | Article |
| id | doaj.art-19970e90cc1341bab3117592cfa21410 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-09T17:24:42Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-19970e90cc1341bab3117592cfa214102023-11-24T12:48:55ZengMDPI AGAlgorithms1999-48932022-11-01151244010.3390/a15120440Vineyard Gap Detection by Convolutional Neural Networks Fed by Multi-Spectral ImagesShazia Sulemane0João P. Matos-Carvalho1Dário Pedro2Filipe Moutinho3Sérgio D. Correia4NOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, PortugalCognitive and People-Centric Computing (COPELABS), Lusófona University, Campo Grande 376, 1749-024 Lisboa, PortugalBeyond Vision, 3830-352 Ílhavo, PortugalNOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, PortugalCognitive and People-Centric Computing (COPELABS), Lusófona University, Campo Grande 376, 1749-024 Lisboa, PortugalThis paper focuses on the gaps that occur inside plantations; these gaps, although not having anything growing in them, still happen to be watered. This action ends up wasting tons of liters of water every year, which translates into financial and environmental losses. To avoid these losses, we suggest early detection. To this end, we analyzed the different available neural networks available with multispectral images. This entailed training each regional and regression-based network five times with five different datasets. Networks based on two possible solutions were chosen: unmanned aerial vehicle (UAV) depletion or post-processing with external software. The results show that the best network for UAV depletion is the Tiny-YOLO (You Only Look Once) version 4-type network, and the best starting weights for Mask-RCNN were from the Tiny-YOLO network version. Although no mean average precision (mAP) of over 70% was achieved, the final trained networks managed to detect mostly gaps, including low-vegetation areas and very small gaps, which had a tendency to be overlooked during the labeling stage.https://www.mdpi.com/1999-4893/15/12/440artificial intelligenceconvolutional neural networksimage processingYou Only Look Oncesemantic segmentationprecision agriculture |
| spellingShingle | Shazia Sulemane João P. Matos-Carvalho Dário Pedro Filipe Moutinho Sérgio D. Correia Vineyard Gap Detection by Convolutional Neural Networks Fed by Multi-Spectral Images Algorithms artificial intelligence convolutional neural networks image processing You Only Look Once semantic segmentation precision agriculture |
| title | Vineyard Gap Detection by Convolutional Neural Networks Fed by Multi-Spectral Images |
| title_full | Vineyard Gap Detection by Convolutional Neural Networks Fed by Multi-Spectral Images |
| title_fullStr | Vineyard Gap Detection by Convolutional Neural Networks Fed by Multi-Spectral Images |
| title_full_unstemmed | Vineyard Gap Detection by Convolutional Neural Networks Fed by Multi-Spectral Images |
| title_short | Vineyard Gap Detection by Convolutional Neural Networks Fed by Multi-Spectral Images |
| title_sort | vineyard gap detection by convolutional neural networks fed by multi spectral images |
| topic | artificial intelligence convolutional neural networks image processing You Only Look Once semantic segmentation precision agriculture |
| url | https://www.mdpi.com/1999-4893/15/12/440 |
| work_keys_str_mv | AT shaziasulemane vineyardgapdetectionbyconvolutionalneuralnetworksfedbymultispectralimages AT joaopmatoscarvalho vineyardgapdetectionbyconvolutionalneuralnetworksfedbymultispectralimages AT dariopedro vineyardgapdetectionbyconvolutionalneuralnetworksfedbymultispectralimages AT filipemoutinho vineyardgapdetectionbyconvolutionalneuralnetworksfedbymultispectralimages AT sergiodcorreia vineyardgapdetectionbyconvolutionalneuralnetworksfedbymultispectralimages |