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…

Cartographie des terroirs viticoles: valorisation des résultats par un logiciel de consultation dynamique de cartes

Pour son travail de cartographie et de caractérisation des terroirs, la Cellule Terroirs Viticoles utilise la méthode développée par l’Unité Vigne et Vin du Centre INRA d’Angers. Cette méthode reconnue au niveau international est appliquée dans les vignobles du Val de Loire à l’échelle du 1/10 000e et est valorisée par des éditions d’Atlas Viticoles à destination des viticulteurs et des organismes techniques.

Read More

Impact of varying ethanol and carbonation levels on the odor threshold of 1,1,6-trimethyl-1,2-dihydronaphtalene (petrol off-flavor) and role of berry size and Riesling clones

1,1,6-trimethyl-1,2-dihydronaphtelene (TDN) evokes the odor of “petrol” in wine, especially in the variety Riesling. Increasing UV-radiation due to climate change intensifies formation of carotenoids in the berry skins and an increase of TDN-precursors1. Exploring new viticultural and oenological strategies to limit TDN formation in the future requires precise knowledge of TDN thresholds in different matrices. Thresholds reported in the literature vary substantially between 2 µg/L up to 20 µg/L2,3,4 due to the use of different methods. As Riesling grapes are used for very different wine styles such as dry, sweet or sparkling wines, it is essential to study the impact of varying ethanol and carbonation levels.

Read More

Multi-omics methods to unravel microbial diversity in fermentation of Riesling wines

Wine aroma is shaped by the wine’s chemical compositions, in which both grape constituents and microbes play crucial roles. Although wine quality is influenced by the microbial communities, less is known about their population interactions.

Read More

Ground vs trellis in rootstock cane production fields

Context and purpose of the study. The vine nursery sector is undergoing a transformation to meet growing environmental and sanitary demands.

Read More

POTENTIAL OF PEPTIDASES FOR AVOIDING PROTEIN HAZES IN MUST AND WINE

Haze formation in wine during transportation and storage is an important issue for winemakers, since turbid wines are unacceptable for sale. Such haze often results from aggregation of unstable grape proteinaceous colloids. To date, foreseeably unstable wines need to be treated with bentonite to remove these, while excessive quantities, which are often required, affect the wine volume and quality (Cosme et al. 2020). One solution to avoid these drawbacks might be the use of peptidases. Marangon et al. (2012) reported that Aspergillopepsins I and II were able to hydrolyse the respective haze-relevant proteins in combination with a flash pasteurisation. In 2021, the OIV approved this enzymatic treatment for wine stabilisation (OIV-OENO 541A and 541B).

Read More