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…

Protection of genetic diversity: maintenance and developements of a grapevine genebank in Hungary

Among the items preserved in gene banks, the old standard and autochthonous varieties represent an increasing value, since these varieties may have properties to make their cultivation more effective under changing climatic conditions. The increasingly extreme weather is a huge challenge for the viticulture. Collectional varieties can also play important role in protection against pests and pathogens. A genebank ensures not only the preservation of rare varieties, but also gives the opportunity for more knowledge and research of these varieties.

Read More

Influence of irrigation on water status, productivity, yield and must composition in Tempranillo grapevine under Duero Valley zone conditions

Cette étude a pour but d’évaluer la modification de l’état hydrique (potentiel hydrique foliaire), le comportement productif (matière sèche et rendement) et la expression qualitative (poids de baie, degrée Brix, pH, acidité totale, concentration polyphénolique) de la varieté Tempranillo dans la Vallée du Douro, à l’A.O. Cigales, comme conséquence de l’application d’une irrigation modérée. Pour développer l’essai on a appliqué les suivantes

Read More

Synthesis of the contribution of the Giesco (group of international experts of vitivinicultural systems for cooperation) to the study of terroirs

Since 1998, the GiESCO (previously named GESCO: Groupe d’Etude des Systèmes de COnduite de la vigne) has provided the scientific community with relevant contributions to the study of terroirs. Here is a synthesis of the main terroir-related fields and the major ideas the GiESCO has developed: Basic Terroir Unit and climate, Vine Ecophysiology and microclimate – moderate drought, Vineyard heterogeneity and new technologies, Viticultural Terroir Unit and canopy management, Terroir – Territory and man.

Read More

Does foliar fertilization with Seaweed improve the productivity and quality of ‘Merlot’ grape must?

Developing technologies that help vines survive and produce in quantity and quality within current times is mandatory. In this sense, in the 2021/2022 agricultural harvest, the influence of the foliar application of seaweed – Laminaria japonica was studied, aiming at productivity and quality of the must in the ‘Merlot’ grape. In the city of “Santana do Livramento”, “Rio Grande do Sul” (RS), Brazil; in a 15-year-old commercial vineyard of ‘Merlot’ clone ENTAV-INRA® 347, grafted onto ‘SO4’ rootstock, the following treatments were applied on 6 occasions: No treatment (control) and; Foliar application of Laminaria japonica seaweed (commercial product: Exal (ALAS), 2 kg ha-1).

Read More

Study of the oenological potential of varieties resistant to cryptogamic diseases and drought to anticipate varietal selection in Occitanie

In the context of climate change and the growing need to reduce the use of phytosanitary products, the exploration of disease-resistant grape varieties and/or adapted to drought conditions is becoming crucial for the wine industry in certain regions of France, such as Occitanie. Currently, exploring the oenological potential of varieties by analyzing their biochemical composition before and after winemaking comes rather late in the varietal selection process.

Read More