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…

Defining the mechanisms and impact of winemaking treatments on tannin and polysaccharides in red wine: recent progress in creating diverse styles

Tannin and polysaccharide concentration and composition is important in defining the texture of red wines, but can vary due to factors such as cultivar, region, grape ripeness, viticultural practices and winemaking techniques. However, the concentration and composition of these macromolecules is dependent not only on grape tannin and polysaccharide concentration and composition, but also their extractability and, in the case of polysaccharides, their formation by yeast. Through studies into the influence of grape maturity, winemaking and sensory impacts of red grape polysaccharides, seed and skin tannins, recent research in our laboratory has shown that the processes involved in the extraction of these macromolecules from grapes and their retention in wine are very complex.

Read More

Genetic identification of 200-year-old Serbian grapevine herbarium

Botanist Andreas Raphael Wolny collected a grapevine herbarium from 1812-1824 in Sremski Karlovci (wine region of Vojvodina, Serbia), which represents local cultivated grapevine diversity before the introduction of grape phylloxera in the region. The herbarium comprises over 100 samples organized into two subcollections based on berry colour (red and white varieties), totaling 47 different grape varieties. The objective of this study was to investigate the historical varietal assortment of Balkan and Pannonian winegrowing areas with long viticulture traditions.

Read More

Evolution of grapeseed composition during maturation and characterization of its impact on wine compound using molecular networks

Usually the winemaker consider the grapeberry maturity as an actor of the wine quality. Grape seed are frequently used as a marker to assess the grape maturity. The first aim of this study is to obtain a better understanding of the impact of grape seed maturity on the grape seed and grape berry composition.

Read More

“Terroir” studies in the Côtes du Rhône controlled appellation: from zoning to application

This work gives a summary of the most important programmes about viticultural « terroirs », developed on the « Côtes du Rhône » controlled appellation area for about twenty years.

Read More

Histoire des Vitis depuis leurs origines possibles sur la Pangée jusqu’aux cépages cultivés : un exemple de résilience liée à la biodiversité des espèces

The first forms of life on earth were bacteria and single-celled blue-green algae. They evolved into land plants around 500 million years ago, developing mechanisms for surviving on land, such as roots, stems and leaves. This evolution also led them to coexist with other organisms, such as insects and animals, for pollination and seed dispersal, as well as to resist environmental factors such as drought and disease.

Read More