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 dynamics of δ13C and δ18O in musts during berries development

Aim: Many processes or reactions that occur in plants involved isotopic discrimination. Water availability, for example, affects the isotopic ratio of carbon (δ13C) and oxygen (δ18O). In viticulture, δ13C is used in experiments related to water relations and irrigation in vineyards. δ18O is used much less but it could be a good complement to δ13C. The aim of this study was to generate knowledge on how these isotopic ratios, measured in musts, could help to better understand the water behavior of grape varieties. 

Read More

Effect of regulated deficit irrigation on vegetative growth, yield, fruit quality, and reserves accumulation of superior seedless

Superior Seedless is a table grape cultivar mainly produced in San Juan.

Read More

Assessing the effect of oak derived aromas on mouthfeel perception in Chardonnay wine

Mouthfeel is an important quality parameter for Chardonnay wines, particularly those aged in oak. While research on mouthfeel has traditionally focused on the impact of non-aromatic compounds, the role of aroma compounds has largely been over looked. However, in wine as well as other food interactions between retronasal aroma and mouthfeel have been noted. The goal of this research was to investigate the impact of wine aroma on the perception of mouthfeel. Because of the importance of oak aging in the development of Chardonnay mouthfeel, the impact of oak aromas on perceived mouthfeel was explored. Aroma compounds associated with oak (ethyl palmitate, eugenol, furfural, isoeugenol, syringaldehyde, vanillin and whiskey lactone) were added to two different Chardonnay wines; one with no oak influence and one fermented in neutral oak. Low and high concentrations of the compounds were added based on concentrations typically found in barrel aged Chardonnay wine.

Read More

Use of pectinolytic yeast in wine fermentations

The use of pectinolytic enzymes in winemaking is state of the art. These enzymes catalyse the degradation of pectic substances through depolymerization (hydrolases and lyases) and de-esterification. As a result, it supports the extraction of juice and facilitates filtration. It has also been shown in winemaking that the presence of pectinolytic enzymes improves the stability, taste, texture, colour and aroma of products. With regard to enzymes currently applied in winemaking, enzymes derived from filamentous fungi dominate the enzyme industry. Fungal-based pectinolytic enzymes specifically require purification from the culture medium to eliminate unwanted side reactions, which is poorly sustainable. Some non-traditional yeast strains have been reported to exhibit pectinolytic activities. Therefore, the direct use of pectinolytic yeast during wine fermentation process can be an attractive and alternative source for the use of enzymes as input.

Read More

Unexpected relationships between δ13C, water deficit, and wine grape performance

Water nutrition is crucial for wine grape performance. Thus soil investigation aims at characterizing spatial and temporal variability of available water. A possible strategy

Read More