Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping
One of the most promising and difficult challenges for field phenotyping is accurate and reliable counting of sorghum panicles using drone imagery both from RGB and multispectral cameras. In this paper, we present a hybrid Machine Learning method for sorghum panicle identification and counting. The methodology first consists in building a Machine Learning classifier following the two most used methods in the literature for drone and agriculture applications: Support Vector Machine Learning (SVM) and, Artificial Neural Networks (ANN). The present dataset includes 5300 images, and 60% of the dataset were used for training and 20% for testing and validation. Following the results obtained from these models, image segmentation using super-pixel affinity propagation and k-means clustering was used based on simple linear iterative clustering. With an accuracy of 99%, SVM gave a superior performance also in terms of precision and kappa when compared to the ANN model whose accuracy was 98%. Concerning the SVM, a radial basis kernel was used, and the sigma parameter was kept constant at a value of 5.6 determined analytically.
Main Authors: | , |
---|---|
Format: | article biblioteca |
Language: | eng |
Subjects: | F01 - Culture des plantes, U30 - Méthodes de recherche, U10 - Informatique, mathématiques et statistiques, réseau de neurones, phénotype, Sorghum, intelligence artificielle, panicule, drone, identification, http://aims.fao.org/aos/agrovoc/c_37467, http://aims.fao.org/aos/agrovoc/c_5776, http://aims.fao.org/aos/agrovoc/c_7244, http://aims.fao.org/aos/agrovoc/c_27064, http://aims.fao.org/aos/agrovoc/c_24557, http://aims.fao.org/aos/agrovoc/c_3eb20052, http://aims.fao.org/aos/agrovoc/c_3791, |
Online Access: | http://agritrop.cirad.fr/604059/ http://agritrop.cirad.fr/604059/1/604059.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-cirad-fr-604059 |
---|---|
record_format |
koha |
spelling |
dig-cirad-fr-6040592024-01-29T04:32:41Z http://agritrop.cirad.fr/604059/ http://agritrop.cirad.fr/604059/ Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping. Mbaye Modou, Audebert Alain. 2021. Advances in Artificial Intelligence and Machine Learning, 1 (3) : 234-240.https://doi.org/10.54364/AAIML.2021.1115 <https://doi.org/10.54364/AAIML.2021.1115> Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping Mbaye, Modou Audebert, Alain eng 2021 Advances in Artificial Intelligence and Machine Learning F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques réseau de neurones phénotype Sorghum intelligence artificielle panicule drone identification http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_5776 http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_27064 http://aims.fao.org/aos/agrovoc/c_24557 http://aims.fao.org/aos/agrovoc/c_3eb20052 http://aims.fao.org/aos/agrovoc/c_3791 One of the most promising and difficult challenges for field phenotyping is accurate and reliable counting of sorghum panicles using drone imagery both from RGB and multispectral cameras. In this paper, we present a hybrid Machine Learning method for sorghum panicle identification and counting. The methodology first consists in building a Machine Learning classifier following the two most used methods in the literature for drone and agriculture applications: Support Vector Machine Learning (SVM) and, Artificial Neural Networks (ANN). The present dataset includes 5300 images, and 60% of the dataset were used for training and 20% for testing and validation. Following the results obtained from these models, image segmentation using super-pixel affinity propagation and k-means clustering was used based on simple linear iterative clustering. With an accuracy of 99%, SVM gave a superior performance also in terms of precision and kappa when compared to the ANN model whose accuracy was 98%. Concerning the SVM, a radial basis kernel was used, and the sigma parameter was kept constant at a value of 5.6 determined analytically. article info:eu-repo/semantics/article Journal Article info:eu-repo/semantics/publishedVersion http://agritrop.cirad.fr/604059/1/604059.pdf text cc_by info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/ https://doi.org/10.54364/AAIML.2021.1115 10.54364/AAIML.2021.1115 info:eu-repo/semantics/altIdentifier/doi/10.54364/AAIML.2021.1115 info:eu-repo/semantics/altIdentifier/purl/https://doi.org/10.54364/AAIML.2021.1115 info:eu-repo/semantics/reference/purl/https://oajaiml.com/archive/identification-and-counting-of-sorghum-panicles-using-artificial-intelligence-based-drone-field-phenotyping |
institution |
CIRAD FR |
collection |
DSpace |
country |
Francia |
countrycode |
FR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-cirad-fr |
tag |
biblioteca |
region |
Europa del Oeste |
libraryname |
Biblioteca del CIRAD Francia |
language |
eng |
topic |
F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques réseau de neurones phénotype Sorghum intelligence artificielle panicule drone identification http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_5776 http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_27064 http://aims.fao.org/aos/agrovoc/c_24557 http://aims.fao.org/aos/agrovoc/c_3eb20052 http://aims.fao.org/aos/agrovoc/c_3791 F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques réseau de neurones phénotype Sorghum intelligence artificielle panicule drone identification http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_5776 http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_27064 http://aims.fao.org/aos/agrovoc/c_24557 http://aims.fao.org/aos/agrovoc/c_3eb20052 http://aims.fao.org/aos/agrovoc/c_3791 |
spellingShingle |
F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques réseau de neurones phénotype Sorghum intelligence artificielle panicule drone identification http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_5776 http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_27064 http://aims.fao.org/aos/agrovoc/c_24557 http://aims.fao.org/aos/agrovoc/c_3eb20052 http://aims.fao.org/aos/agrovoc/c_3791 F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques réseau de neurones phénotype Sorghum intelligence artificielle panicule drone identification http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_5776 http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_27064 http://aims.fao.org/aos/agrovoc/c_24557 http://aims.fao.org/aos/agrovoc/c_3eb20052 http://aims.fao.org/aos/agrovoc/c_3791 Mbaye, Modou Audebert, Alain Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping |
description |
One of the most promising and difficult challenges for field phenotyping is accurate and reliable counting of sorghum panicles using drone imagery both from RGB and multispectral cameras. In this paper, we present a hybrid Machine Learning method for sorghum panicle identification and counting. The methodology first consists in building a Machine Learning classifier following the two most used methods in the literature for drone and agriculture applications: Support Vector Machine Learning (SVM) and, Artificial Neural Networks (ANN). The present dataset includes 5300 images, and 60% of the dataset were used for training and 20% for testing and validation. Following the results obtained from these models, image segmentation using super-pixel affinity propagation and k-means clustering was used based on simple linear iterative clustering. With an accuracy of 99%, SVM gave a superior performance also in terms of precision and kappa when compared to the ANN model whose accuracy was 98%. Concerning the SVM, a radial basis kernel was used, and the sigma parameter was kept constant at a value of 5.6 determined analytically. |
format |
article |
topic_facet |
F01 - Culture des plantes U30 - Méthodes de recherche U10 - Informatique, mathématiques et statistiques réseau de neurones phénotype Sorghum intelligence artificielle panicule drone identification http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_5776 http://aims.fao.org/aos/agrovoc/c_7244 http://aims.fao.org/aos/agrovoc/c_27064 http://aims.fao.org/aos/agrovoc/c_24557 http://aims.fao.org/aos/agrovoc/c_3eb20052 http://aims.fao.org/aos/agrovoc/c_3791 |
author |
Mbaye, Modou Audebert, Alain |
author_facet |
Mbaye, Modou Audebert, Alain |
author_sort |
Mbaye, Modou |
title |
Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping |
title_short |
Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping |
title_full |
Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping |
title_fullStr |
Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping |
title_full_unstemmed |
Identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping |
title_sort |
identification and counting of sorghum panicles using artificial intelligence based drone field phenotyping |
url |
http://agritrop.cirad.fr/604059/ http://agritrop.cirad.fr/604059/1/604059.pdf |
work_keys_str_mv |
AT mbayemodou identificationandcountingofsorghumpaniclesusingartificialintelligencebaseddronefieldphenotyping AT audebertalain identificationandcountingofsorghumpaniclesusingartificialintelligencebaseddronefieldphenotyping |
_version_ |
1792500511885230080 |