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…

Analysis of the daily minimum temperatures variability in the Casablanca Valley, Chile

The Casablanca Valley (CV) has a complex topography and is located near the Pacific Ocean. These factors generate important climatic differences in relation to other wine producing zones of Central Chile.

Challenges and opportunities for increasing organic carbon in vineyard soils: perspectives of extension specialists

Context description and research question: an increasing number of farmers are considering the impact of conservation practices on soil health to guide sustainable management of vineyards. Understanding impacts of soil management on soil organic carbon (SOC) is one lever for adoption of agroecological practice with potential to help maintain or improve soil health while building SOC stocks to mitigate climate change (Amelung et al., 2020).

Life cycle assessment (LCA) to move towards more environmentally friendly winegrowing

As six on the nine planetary boundaries have already been crossed, putting our safe life on Earth at risk (Rockström et al., 2024) and agriculture is significantly responsible for it (Campbell et al., 2017), viticulture, faces the challenge of reducing its environmental impacts through fundamental changes to its practices.

HYBRID GRAPEVINE CV BACO BLANC, BETWEEN TRADITION AND MODERNISM: FOCUS ON ENDOGENOUS EUGENOL AS RESISTANCE FACTOR TO BOTRYTIS CINEREA

The well-known antifungal and antibiotic molecule, eugenol, is widely spread in various plants including clove, basil and bay. It is also abundant in the hybrid grapevine cultivar (cv) Baco blanc (Vitis vi-nifera x Vitis riparia x Vitis labrusca), created by François Baco (19th century) in the Armagnac region. This study confirmed this cv as highly resistant to Botrytis cinerea by comparing fruit rot incidence and severity with two Vitis vinifera cultivars: Folle Blanche and Ugni Blanc. We have demonstrated the efficiency of eugenol in vitro, by further investigating the effect of small concentrations of eugenol, 3 to 4 ppm (corresponding to IC10), on B. cinerea. By comparing the two major modes of action (direct or volatile antibiosis), the vapour inhibiting effect of eugenol was more powerful. In the skin of Baco blanc berry, the total eugenol concentration reached a maximum at veraison, i.e. 1118 to 1478 μg/kg.

Characterization of commercial enological tannins and its effect on human saliva diffusion

Commercial oenological tannins (TECs) are widely used in the wine industry. TECs are rich in condensed tannins, hydrolyzable tannins or a mixture of both. Wine grapes are a important source of proanthocyanidins or condensed tannins while oak wood possess a high concentration of hydrolyzable tannins (Obreque-Slier et al., 2009). TECs contribute with the antioxidant capacity of wine, catalyze oxide-reduction reactions and participate in the removal of sulfur compounds and metals.