terclim by ICS banner
IVES 9 IVES Conference Series 9 A novel dataset and deep learning object detection benchmark for grapevine pest surveillance

A novel dataset and deep learning object detection benchmark for grapevine pest surveillance

Abstract

Flavescence dorée (FD) stands out as a significant grapevine disease with severe implications for vineyards. The American grapevine leafhopper (Scaphoideus titanus) serves as the primary vector, transmitting the pathogen that causes yield losses and elevated costs linked to uprooting and replanting. Another potential vector of FD is the mosaic leafhopper, Orientus ishidae, commonly found in agroecosystems. The current monitoring approach involves periodic human identification of chromotropic traps, a labor-intensive and time-consuming process.

Therefore, there is a compelling need to develop an automatic pest detection system, leveraging the recent progress in computer vision and deep learning techniques. However, the current progress in developing such a system is hindered by the lack of effective datasets to serve as ground-truth data for the training process.

To fill this gap, our study contributes a fully annotated dataset of S. titanus and Or. ishidae from yellow sticky traps. The dataset comprises more than 400 images, with 1000 identification per class. Guided by entomologists, the annotation task involved defining bounding boxes around relevant insects with corresponding class labels.

We trained and compared the performance of state-of-the-art object detection algorithms (YOLOv8 and Faster R-CNN). Pre-processing included automatic cropping to eliminate irrelevant background information and image enhancements to improve overall quality. Additionally, we tested the impact of altering image resolution, data augmentation, and single-class detection. Preliminary results achieved a high detection accuracy, with mAP@50 and F1-score above 90%, and mAP@50-95 around 70%, allowing a first deployment as an automatic annotation support tool.

DOI:

Publication date: June 14, 2024

Issue: Open GPB 2024

Type: Poster

Authors

Giorgio Checola1*, Paolo Sonego1, Valerio Mazzoni2, Franca Ghidoni3, Alberto Gelmetti3, Pietro Franceschi1

1 Research and Innovation Centre, Digital Agriculture Unit, Fondazione Edmund Mach, S. Michele all’Adige, TN, Italy
2 Research and Innovation Centre, Plant Protection Unit, Fondazione Edmund Mach, S. Michele all’Adige, TN, Italy
3 Technology Transfer Centre, Viticulture Unit, Fondazione Edmund Mach, S. Michele all’Adige, TN, Italy

Contact the author*

Keywords

insect detection, deep learning, smart pest monitoring, flavescence dorée, insect traps

Tags

IVES Conference Series | Open GPB | Open GPB 2024

Citation

Related articles…

PROBING GRAPEVINE-BOTRYTIS CINEREA INTERACTION THROUGH MASS SPECTROMETRY IMAGING

Plants in their natural environment are in continuous interaction with large numbers of potentially pathogenic and beneficial microorganisms. Depending on the microbe, plants have evolved a variety of resistance mechanisms that can be constitutively expressed or induced. Phytoalexins, which are biocidal compounds of low to medium molecular weight synthesized by and accumulated in plants as a response to stress, take part in this intricate defense system.1,2
One of the limitations of our knowledge of phytoalexins is the difficulty of analyzing their spatial responsiveness occurring during plant- pathogen interactions under natural conditions.

Comportement du cépage Mourvèdre dans l’aire d’Appellation d’Origine Contrôlée de Bandol

The Appellation d’Origine Contrôlée of Bandol covers an area of ​​1365 ha, 83% of which are planted with vines, the annual production being around 40,000 hl. Among the wines produced, there are mainly reds which assert themselves over time, but also rosés characterized by their pale colour, generally orange; the whites represent a small part of the production. The main grape variety of this AOC is Mouvèdre, of Spanish origin, which is also found in Provence and Languedoc.

Influence of the unité de terroir base on the typicity of winesin the AOC Priorat in Tarragona

L’AOC Priorat, située derrière les montagnes du pré littoral de Tarragone, se caractérise par un climat méditerranéen avec une tendance à la continentalité et très peu de précipitation pendant le cycle végétatif. Les sols sont secs, pauvres et caillouteux, formés par des schistes. Au cours des années 2000 et 2001, une étude de l’influence du terroir sur la typicité des vins du Priorat a été réalisée en prenant comme référence trois cépages cultivés dans différentes parceIles pour mesurer l’effet du terroir et du mésoclimat sur la qualité des vins:

The relationship between enzyme treatment and polysaccharide extraction in wine making, and subsequent sensory effects in Cabernet Sauvignon wines

AIM To determine the effect of both ripeness and enzyme maceration on the astringency and bitterness perception of Cabernet Sauvignon winesRecent work has contributed to a more detailed understanding of the grape cell wall deconstruction process from ripening through crushing and fermentation, providing a better understanding of what role polysaccharides play in post-harvest fermentation of grapes(1,2). Current research on glycomics in red wine making suggest polysaccharides are important sensory impact molecules (3–6). METHODSOur experimental system harvests Cabernet Sauvignon grapes at three different ripeness levels and makes wine both with and without enzyme treatment.

Sensory and physicochemical impact of proanthocyanidic tannins on red wine fruity aroma

AIM: Previous research on the fruity character of red wines highlighted the role of esters [1]. Literature provides evidence that, besides these esters, other compounds that are not necessarily volatiles may have an important impact on the overall fruity aroma of wine, contributing to a masking effect [2][3]. The goal of this work was to assess the olfactory consequences of a mixture between esters and proanthocyanidic tannins, through sensory and physico-chemical approaches.