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…

Relation entre les caractéristiques des fromages d’Appellation d’Origine Contrôlée et les facteurs de production du lait

Les fromages d’Appellation d’Origine Contrôlée (AOC) représentent un enjeu économique important pour la filière laitière (11 % des fromages produits en France sont des fromages d’AOC, et dans certaines régions de montagne, cette proportion dépasse 50 %). Les spécificités de ces fromages et leurs liaisons avec les caractéristiques du terroir constituent un système complexe où interagissent en particulier la technologie fromagère et les caractéristiques des laits (composition chimique en particulier). Ces dernières dépendent elles-mêmes des caractéristiques des animaux (origine génétique, facteurs physiologiques, état sanitaire) et de leur mode de conduite (alimentation, hygiène, traite…) (fig. 1). L’influence de ces facteurs de production (alimentation et type d’animal en particulier) sur les caractéristiques des fromages est fréquemment mise en avant par les fromagers, sur la base d’observations empiriques. Il existe cependant très peu de travaux expérimentaux sur le sujet, en raison, entre autres, de la difficulté de séparer correctement les effets propres de ces facteurs d’amont de ceux liés à la technologie fromagère.

Read More

Zonazione dell’area viticola doc durello

Il lavoro di zonazione riveste un ruolo importante per capire le potenzialità e la vocazionalità di una specifica area viticola. La viticoltura dovrebbe essere vista in funzione dell’obiettivo enologico che si vuole realizzare e quindi particolare importanza riveste il risultato delle vinificazioni delle uve provenienti dai vigneti delle diverse aree della zona di produzione oggetto d’indagine. La zonazione dell’area a DOC Monti Lessini Durello ha preso in esame la varietà “Durella”, vitigno autoctono del territorio, che rappresenta la maggior parte della produzione vitivinicola della zona.

Read More

Rapid optical method for tannins estimation in red wines

In this work, an innovative analytical method has been proposed for fast and reliable in-line analysis of tannins in wines; the method is fast, does not require sample preparation and is based on the selective reactivity of tannins in a mixture containing proteinaceous matter (i.e. gelatin), under pH 3.5, resulting in the formation of white cloudiness.

Read More

Soil mineral nitrogen dynamics in cover-cropped irrigated vineyards with contrasting soil textures

Context and purpose of the study. Cover cropping in vineyards supports grape yield, quality, and soil health.

Read More

qNMR metabolomics a tool for wine authenticity and winemaking processes discrimination

qNMR Metabolomic applied to wine offers many possibilities. The first application that is increasingly being studied is the authentication of wines through environmental factors such as geographical origin, grape variety or vintage (Gougeon et al., 2019).

Read More