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…

Methyl Jasmonate Versus Nano-Methyl Jasmonate: Effect On The Stilbene Content In Monastrell Variety

Stilbenes, a kind of non-flavonoid phenolic compounds, have been reported to be responsible for various beneficial effects. Their biological properties include antibacterial and antifungal effects, as well as cardioprotective, neuroprotective and anticancer actions (Guerrero et al. 2009).Several strategies can be used to increase stilbene content in grapes and one of them could be the use of elicitors such as methyl jasmonate. The use of this elicitor has been proven to be efficient in the production of secondary metabolites which increases the quality of wines, but its use also has some drawbacks such as its low water solubility, high volatility, and its expensive cost (Gil-Muñoz et al. 2021).

Vineyard soils and landscapes of the Burgundy Côte (France): a historical construction worth preserving

The construction of vineyard landscapes along the Burgundy Côte is the result of geological processes and of human labour. Substratum diversity in this vineyard is the result of a very long history explained by the diversity of Jurassic sedimentary facies and Tertiary tectonic activity. The nature and thickness of Quaternary deposits (Weichselian scree debris and alluvial fans) reflect sediment dynamics concurrent with the last glaciation.

HAZE RISK ASSESSMENT OF MUSCAT MUSTS AND WINES : WHICH LABORATORY TEST ALLOWS A RELIABLE ESTIMATION OF THE HEATWAVE REALITY?

Wines made from Muscat d’Alexandria grapes exhibit a high haze risk. For this reason, they are systematically treated with bentonite, on the must and sometimes also on wine. In most oenological labora-tories and in companies (trade, cooperatives, independent winegrowers), the test that is by far the most widely used, on a worldwide scale, remains the heat test at 80°C for 30 minutes to 2 hours (and some-times up to 6 hours). The tannin test (sometimes coupled with a heat treatment) and the Bentotest are still used. In this study, we show that all these tests give much higher estimates of the haze risk than the risk assessed by a 24-48h treatment at 42°C, which represents a heat wave.

Physiological and performance responses of grapevine rootstocks to water deficit and recovery 

Rootstocks play a key role in the grapevine’s adaptation to the increasing soil water scarcity related to climate change. A pot experiment carried out in 2022 aimed at assessing the physiological responses of seven ungrafted rootstocks to a progressive soil water deficit and a subsequent recovery to field capacity.

New insight the pinking phenomena of white wine

Pinking of white wine is an undesired change potentially occurring over storage, leading to the turning of color from yellow into salmon-red hue.