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…

WHEY protein hydrolysates enhance grapevine resilience to abiotic and biotic stresses

Context and purpose of the study. The growing need for sustainable solutions in viticulture has led to increased interest in biostimulants that can enhance plant resilience to both abiotic and biotic stresses.

Are Farm to fork strategy goals reasonable and achievable? State of the art of Península de Setubal’s winegrowers

The European Union’s “farm to fork” strategy sets out several objectives to be achieved by farmers, who, among others, relate to increasing biodiversity, protecting soils and reducing the use of pesticides. At a time when the amendments to the national plans of Sustainable Use of pesticides are being discussed, it is important to understand what the Setúbal Peninsula region status is.

Effects of stress memory on grapevine resilience in response to recurrent drought and recovery events 

Plants have evolved different strategies to cope with environmental stresses and, although still debated, it was observed that they can remember past stress occurrence.
Anatomical and physiological adjustments have been observed in different grapevine cultivars after repeated drought exposure, however epigenetic, transcriptional and biochemical changes associated with drought-primed ecological memory have been poorly studied.
This work was conceived to test whether exposure to recurring events of mild drought could prime vines to endure severe drought stress. Particularly, we investigated whether the expected improved stress tolerance of Vitis vinifera cv Nebbiolo plants subjected over years to moderate and long-lasting water stress events (WS-primed) depended on molecular memory phenomena or on resetting of stress-induced signals.

Zonage vitivinicole: recherches et considérations initiales sur une proposition de “nouvelle” méthodologie d'”évaluation de la qualité” du produit tel qu’élément base pour le zonage aussi

Si on part de l’introduction que l’activité vitivinicole maintenant plus que jamais doit être une activité d’entreprenariat introduite de mieux en mieux sur le territoire et donc effectuée pour rendre maximal le Profit

Grapevine responses to red blotch disease – a structural-functional perspective of symptomatology development and fruit quality

Red Blotch disease caused by Grapevine red blotch-associated virus (GRBaV) is a severe concern to grape growers and winemakers in major grape-growing regions worldwide. One key aspect of all viruses, including Red Blotch, is their intimate association with cell components and anomalous structures following infection. Therefore, the objective of this study was to analyze symptomatology, vine function, fruit quality and ultrastructure of various tissues and document the relationship of ultrastructural cytopathology with the GRBaV infection in Pinot Noir and Merlot employing various microscopy techniques.