Détail de l'auteur
Auteur Etienne David |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
The challenge of robust trait estimates with deep learning on high resolution RGB images / Etienne David (2021)
Titre : The challenge of robust trait estimates with deep learning on high resolution RGB images Type de document : Thèse/HDR Auteurs : Etienne David, Auteur ; Frédéric Baret, Directeur de thèse Editeur : Avignon : Université d'Avignon Année de publication : 2021 Importance : 145 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université d'Avignon, spécialité Sciences AgronomiquesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] apprentissage profond
[Termes IGN] base de données d'images
[Termes IGN] blé (céréale)
[Termes IGN] céréales
[Termes IGN] comptage
[Termes IGN] cultures
[Termes IGN] densité de la végétation
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] image à haute résolution
[Termes IGN] image captée par drone
[Termes IGN] image RVB
[Termes IGN] jeu de données
[Termes IGN] surveillance agricoleIndex. décimale : THESE Thèses et HDR Résumé : (auteur) High throughput plant phenotyping, especially in the context of open field acquisitions, relies on the interpretation of data from different sensors implemented on various vectors such as tractors, robots or drones. Initially, these data were interpreted using remote sensing algorithms that exploit the spatial resolution of the signal. Since 2015, however, progresses of ”Deep Learning”, based on the training on examples, has already obtained promising results for measuring the rate of cover, counting plants or organs. It uses learned convolution layers, can take advantage of the spatial organization of the signal. The advantage of these methods is that they are based on Red-Green-Blue (RGB) sensors, which are much less expensive than multi- or hyperspectral imagers. However, these methods are sensitive to changes in the distribution between the data used in training and the predicted data. In practice, variable prediction errors from site to site can be observed using these methods. The objective of the thesis is to understand the causes of these variations and propose solutions for reliable phenotypic trait estimates using Deep Learning. The study focuses on detecting plants and organs from high-resolution RGB images acquired in the field. Our work first focused on the constitution of diversified image databases from different locations and stages of development for plant emergence (maize, beet, sunflower) and wheat ears, which allowed the publication of two annotated databases, grouping 27 acquisition sessions for thedrone and 47 for the ear detection. The datasets demonstrate the performances difference between the published results and ours due to the change in distribution. To go beyond the limits of the usual methods, we organized two data competitions, the Global Wheat Challenges, in 2020 and 2021, which allowed us to obtain solutions trained for robustness on a different data set than the training one. The analysis of the solutions showed the importance of the training strategies for robustness beyond the architectures used. We have also shown that these solutions can be effectively deployed as a replacement for manual counting. Finally, we have demonstrated the inefficiency of training functions designed for robust training. Our work opens the prospect of a better evaluation of Deep Learning in the context of high-throughput phenotyping and thus of confidence in its use in real-life conditions. Note de contenu : 1- Introduction
2- Evaluation of the robustness of handcrafted and deep learning methods for plant density estimation
3- Design of a large and diverse dataset for training and evaluating deep learning models: application to wheat head detection
4- Competition design to train robust Deep Learn model: the example of the Global Wheat Challenges
5- GlobalWheat-Wilds: Global Wheat Head Dataset as a benchmark of in-the-wild distribution shifts
6- Conclusion and perspectivesNuméro de notice : 15244 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Sciences Agronomiques : Avignon : 2021 Organisme de stage : Laboratoire EMMAH DOI : sans En ligne : https://hal.inrae.fr/tel-03431192v2/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100610