Terroir 2020 banner
IVES 9 IVES Conference Series 9 International Terroir Conferences 9 Terroir 2020 9 History and innovation of terroir 9 Detection of spider mite using artificial intelligence in digital viticulture

Detection of spider mite using artificial intelligence in digital viticulture

Abstract

Aim: Pests have a high impact on yield and grape quality in viticulture. An objective and rapid detection of pests under field conditions is needed. New sensing technologies and artificial intelligence could be used for pests detection in digital viticulture. The aim of this work was to apply computer vision and deep learning techniques for automatic detection of spider mite symptoms in grapevine under field conditions. 

Methods and Results: RGB images of grapevine canopy attacked by the spider mite (Eotetranychus carpini Oud) were manually taken in commercial vineyard (Etxano, Basque Country, Spain) under natural day light conditions. Leaf segmentation in images was performed based on computer vision techniques, isolating target leaves with spider mite visual symptoms from the vineyard canopy. HSV colour space was used to consider colour variations representing symptoms on the leaves, separating these values from those of saturation and brightness of the image. Spider mite detection was done using Convolutional Neural Networks (CNN) models with an artificially augmented dataset for the classification of leaves with this pest symptoms. An accuracy surpassing 75% was obtained using a hold-out validation.

Conclusions: 

High accuracy proves the effectiveness of the trained model in the classification of grapevine leaves. Computer vision techniques were useful to image classification on the relevant pixels. Additionally, deep learning techniques provided a robust model to find complex features of spider mite visual symptoms.

Significance and Impact of the Study: Non-invasive technology and artificial intelligence shown promising results in the automatic detection of pests in commercial vineyards.

Download the PDF

DOI:

Publication date: March 23, 2021

Issue: Terroir 2020

Type: Video

Authors

Inés Hernández1, Salvador Gutiérrez2, Sara Ceballos1, Ignacio Barrio1, Fernando Palacios1, Ana M. Diez-Navajas3, Javier Tardáguila1*

1Televitis Research Group. University of La Rioja, 26007 Logroño, Spain 
2Department of Computer Science and Engineering, University of Cádiz, 11519 Puerto Real, Spain 
3Department of Plant Production and Protection, NEIKER-Basque Institute for Agricultural Research and Development, Basque Research and Technology Alliance (BRTA), 01192 Arkaute, Spain

Contact the author

Keywords

Deep learning, computer vision, pests, grapevine, crop protection

Tags

IVES Conference Series | Terroir 2020

Citation

Related articles…

Characterization of bunch compactness and identification of associated genes in a diverse collection of cultivars of Vitis vinifera L.

Compactness is a complex trait of V. vinifera L. and is defined ultimately by the portion of free space within the bunch which is not occupied by the berries. A high degree of compactness results in poor ventilation and consequently a higher susceptibility to fungal diseases, diminishing the quality of the fruit. The easiness to conceptualize the trait and its importance arguably contrasts with the difficulty to measure and quantify it. However, recent technical advancements have allowed to study this attribute more accurately over the last decade. Our main objective was to explore the underlying genetics determining bunch compactness by applying updated phenotyping methods in a collection of V. vinifera L. cultivars with a wide genetic diversity.

Read More

Observatoire Grenache en vallée du Rhône : démarche et premiers résultats après une année d’étude

Face à l’enjeu d’affirmer et de mieux comprendre la spécificité des vins en relation avec leur origine, la notion de « terroir », avec la richesse de sens et la diversité des perspectives qui l’éclairent, se révèle la clef de voûte de la production et de la valorisation de vins personnalisés et typiques. Asseoir la connaissance des principaux terroirs de la Vallée du Rhône sur des bases autres que celles, jusqu’alors essentiellement empiriques, invoquées dans la seconde grande région française productrice de vins d’AOC, constitue un projet conforme à l’intérêt voué à cet enjeu d’actualité.

Read More

Evaluation de différents clones du Chardonnay pendant la maturation dans un terroir viticole du Friuli-Venezia Glulia (Nord-Est de l’Italie)

La diffusion récente et “explosive” du Chardonnay dans pratiquement toutes les zones de culture viticole du monde a fait penser, à tort, que cette variété s’adapte facilement à toutes les conditions pédo-climatiques ou presque. Cette thèse a été confirmée par la grande faculté d’adaptation dont a fait preuve le vignoble et par la popularité dont jouit le vin auprès des consommateur du monde entier.

Read More

Impact of nitrogen addition timing on the synthesis of fermentative aromas in alcoholic fermentation

Among the different compounds present in the must, nitrogen is an essential nutrient for the management of the fermentation kinetics but it also plays an important role in the synthesis of fermentative aromas.

Read More

Identification and characterization of polyphenols in fining precipitate

Polyphenols are secondary metabolite widely distributed in plant kingdom such as in fruits, in grapes and in wine. During the winemaking process, polyphenols are extract from the skin and seed of the berries.

Read More