VegAnn, Vegetation Annotation of multi-crop RGB images acquired under diverse conditions for segmentation

Madec Simon, Irfan Kamran, Velumani Kaaviya, Baret Frédéric, David Etienne, Daubige Gaetan, Bernigaud Samatan Lucas, Serouart Mario, Smith Daniel, James Chrisbin, Camacho Fernando, Guo Wei, De Solan Benoit, Chapman Scott, Weiss Marie. 2023. VegAnn, Vegetation Annotation of multi-crop RGB images acquired under diverse conditions for segmentation. Scientific Data, 10:302, 12 p.

Url - autres données associées : https://github.com/simonMadec/VegAnn

Résumé : Applying deep learning to images of cropping systems provides new knowledge and insights in research and commercial applications. Semantic segmentation or pixel-wise classification, of RGB images acquired at the ground level, into vegetation and background is a critical step in the estimation of several canopy traits. Current state of the art methodologies based on convolutional neural networks (CNNs) are trained on datasets acquired under controlled or indoor environments. These models are unable to generalize to real-world images and hence need to be fine-tuned using new labelled datasets. This motivated the creation of the VegAnn - Vegetation Annotation - dataset, a collection of 3775 multi-crop RGB images acquired for different phenological stages using different systems and platforms in diverse illumination conditions. We anticipate that VegAnn will help improving segmentation algorithm performances, facilitate benchmarking and promote large-scale crop vegetation segmentation research.

Mots-clés Agrovoc : modélisation des cultures, plante de culture, végétation, analyse d'image, apprentissage machine, réseau de neurones, indice de végétation, annotation de données

Mots-clés libres : Segmentation semantic, Deep learning, Plant Breeding, Crop, Dataset

Classification Agris : F01 - Culture des plantes
U30 - Méthodes de recherche
U10 - Informatique, mathématiques et statistiques

Champ stratégique Cirad : CTS 2 (2019-) - Transitions agroécologiques

Agences de financement hors UE : Agence Nationale de la Recherche, Ministère de l'Agriculture et de l'Alimentation

Projets sur financement : (FRA) Centre français de phénomique végétale

Auteurs et affiliations

• Madec Simon, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0002-5367-184X - auteur correspondant
• Irfan Kamran, INRAE (FRA)
• Velumani Kaaviya, INRAE (FRA)
• Baret Frédéric, INRAE (FRA)
• David Etienne, INRAE (FRA)
• Daubige Gaetan, ARVALIS Institut du végétal (FRA)
• Bernigaud Samatan Lucas, ARVALIS Institut du végétal (FRA)
• Serouart Mario, INRAE (FRA)
• Smith Daniel, University of Queensland (AUS)
• James Chrisbin, University of Queensland (AUS)
• Camacho Fernando, Universidad de Valencia (ESP)
• Guo Wei, University of Tokyo (JPN)
• De Solan Benoit, ARVALIS Institut du végétal (FRA)
• Chapman Scott, University of Queensland (AUS)
• Weiss Marie, INRAE (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/604745/)

Métriques

[ Page générée et mise en cache le 2024-04-25 ]