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…

Fermentations management: tools for the preservation of the wine specificity

Development of the indigenous microflora is not insignificant on the wine quality. S. cerevisiae indigenous strains are low tolerant to ethanol.

Read More

The effect of ozonated water treatment on the metabolic profile and resistance of vines to Downy and powdery mildew 

Ozone is a potent oxidizing compound that quickly decomposes into oxygen without residues. Previous works reported that ozone is not only a disinfectant that directly harms the pathogens of the vine but also activates systemic defense systems in the plant by activating oxidative stress. We assume these systemic defense mechanisms are essential to the vines’ resistance to downy and powdery mildew (Plasmopara viticola & Erysiphe necator, respectively). The goals of the research are to examine the effect of spraying with ozone water on the plant’s resistance against the mentioned pathogens as well as to characterize the metabolic profile of the plants treated with ozone as well as physiological characteristics in the vines such as the level of Photosynthesis and crop yield. Vines in the vineyard sprayed with ozone water at concentrations of 2 and 4 PPM weekly and biweekly, untreated control & conventional spray. Leaves were taken from vines 2,4,7,9 and 11 days after exposure to ozone and inoculated with the pathogens.

Read More

Contribution of seeds to red wine phenolic composition

Tannin composition is an important attribute in red wine quality, and it is therefore critical to understand the factors influencing tannin extraction during alcoholic fermentation. Tannins contribute to the mouthfeel of wines, but they also form pigmented polymers...
Read More

Typicality of Rioja wines: identification of sensory profiles for the three subregions of DOCa Rioja

Within the DOCa Rioja three main production areas are differentiated: Rioja Alta (RA), Rioja Alavesa (RAv) and Rioja Oriental (RO). They are three diverse territories with particular characteristics that are claimed to give rise to differentiated profiles. The present work aims at evaluating the sensory diversity of young commercial red wines in these three subregions. Therefore 30 young red wines (mainly Tempranillo and vintage 2021), ten from each subregion, were sensory described following a non-verbal free sorting task and a verbal free comment task by 32 well-established Rioja winemakers.

Read More

Soil survey and chemical parameters evaluation in viticultural zoning

The most recent methodological developments in soil survey and land evaluation, that can be taken as reference in the viticultural field, go over usage of the GIS and database. These informatic tools, which begin to be widely utilised, consent to realise evaluations at different geographic scale and with different data quality and quantity in entrance.

Read More