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…

Water status response of Vitis vinifera L. cv Cabernet-Sauvignon during the first years within the long-term VineyardFACE (Free Air Carbon dioxide Enrichment) study

Understanding the water-use responses of grapevines to increasing atmospheric carbon dioxide concentrations is mandatory when assessing the impact of climate change on viticulture as it is a critical part of the adaptation process.

Read More

Climatic zoning and viticulture in Galicia (North West Spain)

Galicia is situated in the NW of the Iberian Peninsula, just north of Portugal and so sharing a mild, maritime climate, certain vine species and a number of long-standing viticultural traditions. In Galicia about 18,000 has are dedicated to wine growing, of which roughly half (46%) correspond to the 6 DOs in the area.

Read More

The use of unripe frozen musts for modulating wine characteristics throughout acidity correction – effects on volatile and amino acid composition

As environmental issues come more to the fore, vineyards residues are being looked at as solutions rather than problems. Aiming to develop a sustainable methodology for musts acidity correction in the process of winemaking, much needed in warm regions, the present study was performed according to Circular Economy values.

Read More

STATISTICAL COMPARISON OF GROWTH PARAMETERS OF NINE BIOPROTECTION STRAINS IMPLEMENTED ON ARTIFICIALLY CONTAMINATED SYNTHETIC MUST

In recent years, consumer demand for products without chemical additives increased, becoming a priority for the wine sector. SO₂ is widely used for its multiple properties including antiseptics, antioxidants and antioxidasics and the strategy of bioprotection in winemaking represents now an alternative to this chemical additive. In oenology, results have highlighted the interest of bioprotection to limit the development of microorganisms like Hanseniaspora uvarum and thus reduce the doses of sulphite. Indeed, this species is considered because of its acetic acid and methyl butyl acetate production, the latter can cover the varietal character of wines.

Read More

The combined use of Lachancea thermotolerans and lactic bacteria in wine technology

The production of most red wines that are sold involves an alcoholic fermentation carried out by yeasts of the Saccharomyces genus, and a subsequent fermentation carried out by lactic bacteria of the Oenococus oeni species after the first one is fully completed. However, the traditional process can face complications, which can be more likely in grape juices with high levels of sugar and pH. Because of climate change, these situations are more frequent in the wine industry. The main hazards in those scenarios are halts or delays in the alcoholic fermentation or the growth of unwanted bacteria while the alcoholic fermentation is not done yet and the wine still has residual sugars.

Read More