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…

Effects of post-veraison irrigation dose on Cabernet-Sauvignon vines in a dry and warm season in Valencia, Spain

In the old-world viticulture, there is a common but most often not scientifically proved consideration that supplemental irrigation should detrimentally affect berry and wine composition. In the semi-arid

Read More

Induced mutagenesis as a tool for intra-varietal improvement: increased diversity in vegetative, fruit and phenological traits in Vitis vinifera cv. Pinotage

Climate variability and rising biotic pressure threaten global viticulture. Modern wine production depends on a limited number of grapevine cultivars, represented by multiple clones that differ slightly in their agronomic, oenological, or stress-tolerance traits.

Read More

Study of the vine performance and the wine composition of Tannat on the terroir of Colonia del Sacramento – Uruguay

Grape-growing terroirs were defined according to the method proposed by Falcetti and Asselin (1996) near of Colonia de Sacramento, a city of Uruguay situated on the left of the “Rio de la Plata”.

Read More

Functional characterization of grapevine MLO genes to define their roles in Powdery mildew susceptibility by CRISPR/Cas9 genome editing

Successful powdery mildew (PM) infection in plants relies on Mildew Resistance Locus O (MLO) genes, which encode susceptibility factors essential for fungal penetration. In Arabidopsis, loss-of-function mutations in three clade-V MLOs, AtMLO2, 6, and 12 confer complete resistance to PM infection. Since then, efforts are on to discover MLO genes contributing to PM susceptibility in many species to introduce mlo-based PM-resistance. Earlier studies in tomato and grapevine, using the RNAi approach, attributed PM susceptibility to SlMLO1, 5, and 8 and VvMLO3, 13, and 17, respectively indicating likely functional redundancy among MLOs.

Read More

Experimental vinification of withered grapes of Vitis vinifera “Muscat of Alexandria”

The objective of the present work is to investigate wine produced from dehydrated grapes and vinified according to classical Roman manuals.

METHODS – Locally produced Muscat of Alexandria’s grapes were used for the sweet wine production, grown in the experimental vineyard of Instituto Superior de Agronomia (Lisbon, Portugal). The grapes were harvested manually slightly over-ripe and subjected to greenhouse drying. After 7-10 days dried grapes were transported to an experimental winery for various operations (e.g., grape weighing, sorting, crushing/destemming). Several maceration protocols were used comprising the addition of saltwater and white wine to whole bunches or destemmed grapes. Fermentation was conducted with the addition of commercial yeast. The standard physico-chemical parameters of wines were determined according to the OIV standards.

Read More