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…

IMPACT OF METSCHNIKOWIA PULCHERRIMA DURING FERMENTATION ON AROMATIC PROFILE OF VIDAL BLANC ICEWINE

Non-Saccharomyces yeasts not only increase microbial diversity during wine fermentation, but also have a positive effect on improving wine aroma. Among these non-Saccharomyces yeast species, Metschnikowia pulcherrima is often studied and used in winemaking in recent years, but its application in icewine has been rarely reported. In this study, indigenous M. pulcherrima strains and Saccharomyces cerevisiae strains (commercial and indigenous strains) were sequentially inoculated for icewine fermentations; meanwhile, pure S. cerevisiae fermentations were used as the control; indigenous strains used above were screened from spontaneous fermentations of Vidal blanc icewine.

Xylem vessel blockages in grape pedicel growing in tropical climate observed by microtomography

In grape berry pedicel, xylem hydraulic conductance can be impaired by blockage deposition in the lumen of xylem elements. However, the varietal difference of the interruptions has not yet been characterized. In this preliminary work, we utilized synchrotron x-ray computed microtomography experiments performed at MOGNO beamline (LNLS – Brazil) to identify possible blockage sites in natural grape pedicel xylem. For this, we imaged dehydrated pedicel’s stem portion from the Niagara Rosada variety in three different phenological stages (Pre-veraison (PreV), veraison (V) and post-veraison (PostV). The reconstructed tridimensional images with a voxel size of 1.16 µm were segmented for the identification of xylem vessel lumens. After analysing one pedicel stem per stage, we identified 658 vessels without occlusion throughout his axial plane and 41 in which we could identify possible interruptions.

Novel table grape varieties as “ready-to-eat” products

Consumers are increasingly requesting ready-to-eat products, which are time-saving and convenient. Offering ready-to-eat fruits and vegetables represents a quick and easy way for any consumer to add healthy products to their diet. In this study, we evaluated the aptitude of several table grape varieties to be included in the processing and packaging lines of ready-to-eat products. The following work was based on the characterization of genetic materials and varietal innovation.

REMEDIATION OF SMOKE TAINTED WINE USING MOLECULARLY IMPRINTED POLYMERS

In recent years, vineyards in Australia, the US, Canada, Chile, South Africa and Europe have been exposed to smoke from wildfires. Wines made from smoke-affected grapes often exhibit unpleasant smoky, ashy characters, attributed to the presence of smoke-derived volatile compounds, including volatile phenols (which occur in free and glycosylated forms). Various strategies for remediation of smoke tainted wine have been evaluated. The most effective strategies involve the removal of smoke taint compounds via the addition of adsorbent materials such as activated carbon, which can either be added directly or used in combination with nanofiltration. However, these treatments often simultaneously remove wine constituents responsible for desirable aroma, flavour and colour attributes.

Phenolic composition of Cabernet Sauvignon wines from Argentina, Portugal and Spain

Grape and wine phenolic compounds have been shown to be highly related to both wine quality (color, flavor, and taste) and health-promoting properties (antioxidant and cardioprotective, among others). The aim of this work was to evaluate and compare the phenolic contents of Cabernet Sauvignon wines from different geographical areas and climatic conditions, namely from Argentina, Portugal and Spain vintage 2022. In addition, the phenolic profiles of the Portuguese wines from three vintages (2020, 2021, 2022) was compared.