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…

The potential of new selection and indigenous grape varieties for sparkling wine production

In the context of climate change, it is essential to provide producers with alternatives based on local grape varieties capable of meeting modern quality and sustainability requirements.

Read More

Entomopathogenic nematodes application for controlling Lobesia botrana in grapevine and their impact on grapevine quality 

Entomopathogenic nematodes (EPN) are well-known biological control agents combined with specific adjuvants that now allow their use against aerial pests. Lobesia botrana (Lepidoptera: Tortricidae) is one of the major harmful pests detected in worldwide vineyards. Previous studies demonstrated that the EPNs Steinernema feltiae and S. carpocapsae could control L. botrana. The hypothesis was that the best combination of EPN-adjuvant/timing (season/temperatures) will support the use of EPN in the vineyard against L. botrana with no impact on the grape performance.

Read More

Three new Apulian seedless varieties available for the table grape supply chain

The table grape industry in Europe is undergoing significant changes. For instance, in Italy, the national register of vine varieties was established in 1969, and since then, many varieties of table grapes have been registered. In the first thirty years, from 1969 to 1999, 62 seeded and 24 seedless varieties were registered. In the subsequent period, from 2000 to the present day, 23 seeded varieties and 99 seedless varieties were registered.

Read More

SUB-CRITICAL WATER: AN ORIGINAL PROCESS TO EXTRACT ANTIOXIDANTS COMPOUNDS OF WINE LEES

Wine lees are quantitatively the second most important wine by-product after grape stems and marc [1]. In order to recycle, distilleries recovered ethanol and tartaric acid contained in wine lees but yeast biomass is often unused. It has already been demonstrated that this yeast biomass could be upcycled to produce yeast extracts of interest for wine chemical stabilization [2]. In addition, it is well known that lees, during aging, release compounds that preserve wine from oxidation.

Read More

Effect of scion-rootstock combinations on the performance of a near-infrared (NIR) spectroscopy method for determining vine water status

In the context of sustainable viticulture, modern and efficient techniques to determine water status are required to optimize irrigation practices. Proximal techniques such as thermography and spectroscopy have shown promising results. When these techniques are incorporated into mobile systems is possible to evaluate the water status on-the-go, offering the possibility to generate variability maps. However, in most cases, complex protocols of data acquisition and analysis are required. Also, the inherent physiological behaviour of the plants under certain water stress conditions needs to be considered. Therefore, the aim of this study was to evaluate the effect of scion-rootstock combinations on the performance of a predefined plant-based method based on proximal near-infrared (NIR) spectroscopy.

Read More