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…

Characterization of “territoires” throughout the production of wines obtained with withered grapes: the cases of “Terra della Valpolicella” (Verona) and “Terra della Valle del Piave” (Treviso) in Northern Italy

Dans la définition et la description d’un “territoire” (“terra” en italien), avec les facteurs du milieu et génétiques, un rôle important est joué par ceux agronomiques, techniques et de culture qui contribuent à caractériser le produit d’une zone spécifique.

Impact of crop load management on terpene content in gewürztraminer grapes

Context and purpose of the study ‐ Crop load management by cluster thinning can improve ripening and the concentration of key metabolites for grape and wine quality. However, little work has been done on testing the impact of crop load management on terpene content of white grapes. The goal of the study was to assess if by reducing crop load via cluster thinning growers can increase terpene concentration of grapes, as well as to test if the timing of thinning application affects terpene concentration.

Chemical and biochemical formation of polysulfides in synthetic and real wines using UHPLC-HRMS

ulfur compounds in wine have been studied for several years due to their impact on wine flavour, but the role of polysulfides is a recent topic. Polysulfides in wine are formed when two sulfhydryl groups oxidize, especially in presence of elemental sulfur or metal catalysts from field treatment residues (Ugliano et al. 2011). These compounds are odourless, but can degrade during storage and affect the wine quality. The mechanism of their formation is still largely unknown but different chemical and biochemical pathways have been suggested. Disulfides from cysteine (Cys) and glutathione (GSH) have been revealed in model wines (Kreitman et al. 2016) and more recently also higher polymerized forms in real wines (Van Leeuwen et al. 2020). Volatile varietal thiols like 3-mercaptohexanol (3MH) and 4-mercaptopentanone (4MMP) – flavour compounds with tropical or fruity notes – could undergo similar reactions, also with Cys and GSH, subsequently losing their flavour property (fate). Even more concerning is the possible release of H2S from polysulfides during storage, leading to undesired off-flavours (Sarrazin et al. 2010).

VOLTAMETRIC PROFILING OF RED WINE COMPOSITION DURING MACERATION: A STUDY ON FOUR GRAPE VARIETIES

During red wine vinification, maceration allows the must, and consequently the wine, to be enriched with several compounds that contribute to the creation of the typical organoleptic characteristics of red wines. Among these, extraction of polyphenols (PPs) during maceration is a major process of enological interest.
The purpose of this study was the evaluate the suitability of a rapid analytical approach based in linear sweep voltammetry to monitor PPs extraction during vinification.

Winemaking processes discrimination by using qNMR metabolomics

AIM: Metabolomics in food science has been increasingly used over the last twenty years. Among the tools used for wine, qNMR has emerged as a powerful tool to discern wines based on environmental factors such as geographical origin, grape variety and vintage (Gougeon et al., 2019a).