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…

CHEMICAL DRIVERS OF POSITIVE REDUCTION IN NEW ZEALAND CHARDONNAY WINES

According to winemakers, wine experts and sommeliers, aromas of wet stone, mineral, struck match and flint in white wines styles, such as those produced from Vitis vinifera L. cv. Chardonnay, are considered to be hallmarks of positive reduction.1,2 In recent years, the production of Chardonnay styles defined by aroma characteristics related to positive reduction has become more desirable among wine experts and consumers. The chemical basis of positive reduction is thought to originate from the concentration of specific volatile sulfur compounds (VSCs), including methanethiol (MeSH) imparting mineral and chalk notes,3 and benzenemethanethiol (BMT) responsible for struck match and flint.1,4

Read More

Adaptive winemaking technologies using PIWI varieties in the wine industry of Ukraine

In recent years, the impact of climate change has been pushing agriculture toward the implementation of innovative production methods aimed at countering the negative consequences of climate change.

Read More

Legal protection of the vitivinicultural terroirs in Yamanashi Prefecture, Japan

This study analyses the actual situation regarding the legal protection of the vitivinicultural terroirs in Yamanashi Prefecture, the centre of Japanese wine industry with more than 150 years of wine-making tradition.

Read More

Intra-varietal diversity in cv. ‘Tempranillo Tinto’: phenological stages

‘Tempranillo Tinto’ is one of the most relevant grapevine cultivars worldwide. Despite its early ripening and relatively short vegetative cycle, which may not be ideal for high-quality grape and wine production in warming conditions, its long-standing cultivation has led to an intense multiplication by cuttings, which originated the high level of clonal variation currently available. Now, this intra-varietal diversity provides an interesting opportunity for cultivar improvement by identifying genotypes with better adaptation potential.

Read More

Une méthode d’étude synthétique du paysage

a) wine, a qualitative and user-friendly product, favors a visual support, even for a scientific study because it refers to the image of the terroir, in particular by its visible landscape. b) the vineyard landscape, which is fairly open by definition, favors this type of approach. c) the framework of the Terroir Test conducted by the URVV (INRA – Angers) comprises 15 micro-plots of 100 strains, and requires at this scale precise surveys of the environment, hence systematic shots, of the center of the plot, over 360°, at 50 mm intervals, at 1.70 m from the ground and horizontally.

Read More