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…

The impact of postharvest cooling of Sauvignon blanc grapes on the sensory profile and the chemical composition of the wines

Rapid processing of grapes after harvest has always been considered essential for achieving a balanced sensory wine profile.

Read More

Correlative study between degradation of rosé wine under accelerated conditions and under normal conditions

Several studies have tried to develop different methods to study the photodegradation of wine in an accelerated way, trying to elucidate the effect of light on the wine compounds[1]. In a previous study, our team developed a chamber that speeds up the photodegradation of rosé wine[2]. In the present work we have tried to establish a correlation between irradiation times in accelerated conditions and the natural exposure to the cycles of light that usually exist in markets or at home.

Read More

HYDROXYTYROSOL PRODUCTION BY DIFFERENT YEAST STRAINS: SACCHAROMYCES AND NON-SACCHAROMYCES AND THE RELATION WITH THE NITROGEN CONSUMPTION

Hydroxytyrosol (HT) is a phenolic compound with extensive bioactive properties. It is present in olives, olive oil and wines. Its occurrence in wines is partly due to yeast synthetise tyrosol from tyrosine by the Ehrlich pathway, which is subsequently hydroxylated to .
The aim of the present work is to study how different yeast strains can influence in the HT production and, how the different nitrogen consumption of each strain can interfere the production of bioactive compounds.

Read More

Déterminisme de l’effet terroir: influence de la surface foliaire primaire de la vigne en début de cycle sur le potentiel vendange

ln the Mid-Loire Valley, in France, for the fast twenty years a network of experimental plots has been used to analyse the terroir effect on the behaviour of the Cabernet franc variety of grape. The study of the primary leaf area (SFI) for several vintages shows that it differs greatly from one terroir to another.

Read More

Aroma characterization of mold resistant base wines for sparkling wine produced in a warm-temperate area at two different altitudes

In a recent context where consumers pay an increasing attention to sustainability and eco-friendly aspects in the decision-making process, the use of the resistant varieties in the wine sector have returned to the attention. In this context, the use of mould-resistant grape varieties would be an opportunity for sparkling wine producers as it can reduced the pesticide utilization in grape management and hence production costs.
However, the use of the resistant varieties to produce the base wine may be strongly influenced due to its requirements for a particular balance between sugars and acidity to ensure the quality of the final product. In addition, the aromatic profile of base wine plays a crucial role in the perception of the quality of the sparkling wine.

Read More