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…

Differentiating and grouping of oltrepo’ pavese environments according to grape maturation

The maturation patterns process has been very studied. In particular the modelization of the sugars and titratable acidity during the ripening period was an important approach, in particular for the prediction of harvest date (Barillere et al., 1988; Jourion et al.,1987; Maujean et al., 1983; Scienza, 1989). In Oltrepò Pavese, the widest viticultural district of Lombardy – Northern Italy – (about 15000 hectares), grape maturation trends shows high variability, due to the large variation in environmental characteristics of vineyards (altitude, exposure, soil type, mesoclimate) and to “cultivar x environment” interaction.

Read More

A 4D high resolution vineyard soil assessment for soil-hydrological interpretation in combination with automated data analysis and visualization to manage site-specific grape and wine quality

A Visual Information eNvironment for Effective agricultural management and Sustainability (VINES) is under development, which can provide significant competitive advantages to winegrowers by sustaining their appellation-specific grape and wine qualities and yields while measurably conserving water resources.

Read More

Un Système d’Informations à Références Spatiales sur le Vignoble. Un outil performant d’aide aux recherches sur la caractérisation des terroirs viticoles

The “Terroirs d’Anjou” project led by the Agronomy sector of the Vine and Wine Research Unit of the INRA center in Angers aims to characterize the viticultural terroirs in a study area which includes 29 municipalities in the Maine et Loire and cuts across the Anjou, Coteaux du layon and Coteaux de l’Aubance appellation areas.

Read More

THE EFFECT OF DIFFERENT TERROIRS ON AROMA COMPOUNDS OF ‘KALECIK KARASI’ WINES

Kalecik Karası is a domestic grape variety of Turkey, originating from Kalecik district, 80 km from Ankara. Although there is no definite evidence, it is known that it was used in wine production by many civilizations that lived in the Anatolian region, especially the Hittites. Compared to other black wine grapes, it stands out with its low tannin content, rich fruity aroma and complex structure. In good vintages, red fruits such as strawberries, cherries and raspberries stand out in the aroma profile. Although its structure is elegant, it has the potential to age and develop similar to the ‘Pinot Noir’ wine of the Burgundy region. This offers a complex aroma structure including red flowers, earth and ripe fruits.

Read More

Identification of riboflavin low producer yeasts to prevent the light-struck taste in white wines

Wine quality maintenance during the storage is a fundamental aspect for both wine producers and consumers. Nowadays, great attention has been given to the light effect

Read More