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…

Development of a LC-FTMS method to quantify natural sweeteners in red wines

The quality of a wine is largely related to the balance between its sourness, bitterness and sweetness. Recently, molecules coming from grapes have been showed to notably contribute to sweet taste of dry wines. To study the viticultural and oenological parameters likely to affect their concentration, their quantification appears of high interest and subsequently requires powerful analytical techniques. Therefore, a new method using liquid chromatography coupled to high resolution mass spectrometry (LC-HRMS) was developed and validated to quantify epi-DPA-3′-O-β-glucopyranoside acid (epi-DPA-G) and astilbin, sweet molecules identified in wine. Three gradients were tested on five different C18 columns (Hypersil Gold, HSS T3, BEH, Syncronis and Kinetex).

The effect of management practices and landscape context on vineyard biodiversity

Intensification is considered one of the major drivers of biodiversity loss in farmland. The more intensive management practices that have been adopted the last decades, contributed to species declines from all taxonomic groups. Moreover, agricultural intensification has led to an important change of land use. Complex, mixed agro-ecosystems with cultivated and non-cultivated habitats have been converted to simplified, intensive and homogeneous ones with severe effects on biodiversity.

Importance of the Terror Variability Map (TVM) in Precision viticulture (PV): choice of methodology for soil classification

The Precision Viticulture (PV) is defined “as a management system that is information and technology based, is site specific and uses one or more of the following sources of data: soils, vigour, nutrients, pests, moisture, and yield among others, for optimum profitability, sustainability, and protection of the environment” (OIV, 2018, in process). The elements mentioned in the definition are an important part of the terroir components. The terroir is a tool In Viticulture, it is the analysis and study unit, and the variability of a certain situation can be due to any difference in every element or property of each factor that constitutes it, including the management.The soil and its management are those that bring the most variability to terroir.

Determinazione della frazione aromatica dei vini, quale strumento per-la valorizzazione del territorio viticolo

La caratterizzazione della frazione volatile aromatica dei vini attraverso l’analisi quali­quantitativa dei diversi composti, ha portato corne primo risultato la netta differenziazione delle annate in prova.

Storia del prosecco e del suo territorio di produzione: un percorso di studi in continuo progresso

Nella realtà viticola Italiana il Prosecco è uno degli esempi più evidenti di un percorso storico che ha saputo valorizzare lo stretto legame tra vitigno e territorio d’origine.