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…

AOC Saint-Romain, Hautes-Côtes-de-Beaune, Burgundy: analysis of a “terroir”

The abbreviation AOC designates, since 1905 in France, wines which characteristics and reputation are due to a proper “terroir”. The delimitation of such “terroirs” consists in a technical and statutory procedure which has developed by steps.

Read More

Viticultura protegida: uso de mallas sombreadoras fotoselectivas como una herramienta para enfrentar la crisis climática en uva de mesa en el norte de Chile

The production of table grapes in Chile is of great importance, being one of the main established fruit crops with over 43,000 hectares distributed across a diverse climate range, from the southern limit of the Atacama desert to the mediterranean zone. Chile is also one of the leading exporters of table grapes. producers must confront the challenges posed by the climate crisis, such as decreased rainfall, increased heatwaves, and extreme temperature events during the growing season, mainly associated with desertification in northern Chile (Atacama and Coquimbo regions).

Read More

Influence of Lactiplantibacillus plantarum and Oenococcus oeni strains on sensory profile of sicilian nero d’avola wine after malolactic fermentation.

AIM: Malolactic fermentation is a process of decarboxylation of L-malic acid into L-lactic acid and carbon dioxide that leads to deacidification, modification of odors and flavors of wines [1]

Read More

Dimethyl sulfide: a compound of interest from grape to wine glass

The overall quality of fine wines is linked to the development of “bouquet” during wine bottle ageing1. Several chemical reactions, occurring in atmosphere protected from oxygen, are favourable to the formation and preservation of sulphur compounds such as dimethyl sulfide (DMS). DMS accumulate in wines thanks to hydrolysis of its precursors (DMSp) mainly constituted by S-

Read More

Reconstructing ancient microbial fermentation genomes from the wine residues of Herod, Roman king of Judea

The fortress of the Herodium, built towards the end of the first century BCE/ante Cristo, on the orders of Herod the Great, Roman client king of Judea, attests the expansion of Roman influence in the eastern Mediterranean. During archaeological excavations of the Herodium in 2017[1], a winery was discovered on the ground floor of the palace, with an assortment of clay vessels in situ, including large dolia – clay fermentation vessels each capable of fermenting up to 300-400 L of wine. Thanks to the recent progresses in the field of paleogenomics[2], we could analyse the organic material consistent with grape pomace at the bottom of these vessels, by extracting and sequencing the DNA using shotgun metagenomics and targeted capture, aiming for enrichment of DNA from fermentation associated microbes.

Read More