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.

Download the abstract

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…

Influence du terroir et de la conduite du verger sur la composition des pommes à cidre

L’économie cidricole française est concentrée dans les régions du grand Ouest avec environ 40% de la production nationale de pommes à cidre pour la seule région Bas-Normande où le Pays d’Auge occupe

Read More

IMPACT OF MINERAL AND ORGANIC NITROGEN ADDITION ON ALCOHOLIC FERMENTATION WITH S. CEREVISIAE

During alcoholic fermentation, nitrogen is one of essential nutrient for yeast as it plays a key role in sugar transport and biosynthesis of and wine aromatic compounds (thiols, esters, higher alcohols). The main issue of a lack in yeast assimilable nitrogen (YAN) in winemaking is sluggish or stuck fermentations promoting the growth of alteration species and leads to economic losses. Currently, grape musts are often characterized by low YAN concentration and an increase of sugars concentration due to global warming, making alcoholic fermentations even more difficult. YAN depletion can be corrected by addition of inorganic (ammonia) or organic (yeast derivatives products) nitrogen during alcoholic fermentation.

Read More

Light-struck taste in white wine: enological approach for its prevention

Light-struck taste is a defect prevalent in white wines bottled in clear glass light-exposed for a considerable amount of time leading to a loss of color and appearance of sulfur-like odors. The reaction involves riboflavin (RF), a highly photosensitive compound that undergoes to intermolecular photoreduction by the uptake of two electron equivalents from an external donor, the methionine. The reaction includes different steps forming methional which is extremely unstable and decomposes to methane thiol and acrolein. The reaction of two molecules of methane thiol yields dimethyl disulfide. Methane thiol is highly volatile, has a low perception threshold (2 to 10 µg/L in wine) and confers aroma-like rotten eggs or cabbage.

Read More

Exploring the genomic diversity of yeast involved in spontaneous fermentation. from studies to select autochthonous strains of different italian’s wineries to extensive phylogenetic survey about the italians’ population of s. cerevisiae

Modern winemakers must ensure effective alcoholic fermentation without losing the intrinsic biodiversity of the different oenological contexts. In this sense, the population of saccharomyces cerevisiae characteristic of wineries that traditionally do not use selected yeasts can represent an interesting reservoir of biodiversity.

Read More

Viticultural zoning of the country of Mendoza, Argentina. Study of the first zone : department of Luján de Cuyo. Statement of the study year 2002

La région viticole de Mendoza est la principale zone vitivinicole d’Argentine qui se compose de 3 oasis (Nord, Valle de Uco, Sud). La première zone vitivinicole, située dans l’oasis Nord, est composée par les département de Luján de Cuyo et Maipu. C’est la zone de production la plus ancienne et la plus reconnue pour la qualité de sa production. Ce travail se porte plus particulièrement sur le département de Luján de Cuyo qui constitue le lieu traditionnel de production du Malbec argertin. Ce travail propose de caractériser les terroirs et de mettre en avant leurs typicités.

Read More