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…

Potential of new genetic resources to improve drought adaptation of grapevine rootstocks

Grapevines are grown mainly as grafts worldwide, but the rootstocks most commonly used were selected between the late 19th and early 20th centuries and are based on reduced genetic diversity[1]. In the context of climate change, it is indeed urgent to diversify the range of rootstocks with genotypes much more adapted to drier environments, than the existing ones[2]. The aim of this study was to evaluate the potential of new genetic resources for grapevine rootstock breeding programs. For this purpose, 12 American and Asian wild Vitis species (3 to 5 accessions per species = 50 accessions) were evaluated for their rooting ability and drought response.

Impact of changing climatic factors on physiological and vegetative growth

Scientific information on grapevine response to predicted levels of climate parameters is scarce and not sufficient to properly position the Wine Industry for the future. It is critical that the combined effects of increased temperature and CO2 on grapevines should be examined, without omitting the important link to soil water conditions. The purpose of this study is to quantify the effects of envisioned changes in climatic parameters on the functioning and growth of young grafted grapevines under controlled conditions, simulating expected future climate changes. Scientific knowledge of precisely how the newly-planted grapevine will react morphologically, anatomically and physiologically (at leaf, root and whole plant level) to the expected changes in important climatic parameters will enable producers to make better-informed decisions regarding terroir, cultivar and rootstock choices as well as the adaptation of current cultivation practices.

Digital PCR: a tool for the early detection of brettanomyces in wine

Brettanomyces bruxellensis is found in various ecological niches, but particularly in fermentative processes: beer, kombucha, cider and wine. In the oenological sector, this yeast is undesirable, as it can produce ethyl phenols, thus altering wine quality. These compounds are characterized by stable or horse-sweat aromas, unpleasant for consumers.

Primary results on the characterisation of “terroir” in the certified denomination of origin Rioja (Spain)

La integración de variables referentes al clima, la litología y la morfología del relieve y el suelo en la D.O. Ca Rioja permite la configuración de un modelo a través de cuya validación se obtiene la delimitación de zonas vitícolas.

Moscatel vine-shoot extracts as grapevine biostimulant to increase the varietal aroma of Airén wines

There is a growing interest in the exploitation of vine-shoots waste, since they are often left or burned. Sánchez-Gómez et al. [1] have shown that vines-shoots aqueous extracts have significant contents of bioactive compounds, among which several polyphenols and volatiles are highlighted. Recent studied had demonstrated that the chemical composition of vine-shoots is enhanced when vine-shoots are toasted
[2,3]. The application of vegetable products in the vineyards has led to significant changes towards a more “Sustainable Viticulture”. An innovative foliar application for Airén vine-shoot extracts have been carried out to the vineyard. It has been shown that they act as grape biostimulants, improving certain wine quality characteristics [4].