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…

Methodology of climate modelling using land surface temperature downscaling: case study case of Gironde (France)

Aim: Climate modelling in viticulture introduced new challenges such as high spatio-temporal monitoring and the use of dependable time series and robustness modelling methods. Land surface temperature (LST) is widely used and particularly MODIS thermal satellite images due to their high temporal resolution (four images per day).

Read More

Mousy off-flavor detection: a rapid LCMS/MS method

These days, consumers are interested in food products linked to the environment and the concept of naturalness. They prefer “free” products, such as those with no pesticide residues or no added sulfur dioxide (so2) in wines. In fact, so2 is the most widely used preservative in winemaking, as it has multiple properties at low cost: it is antioxidant, antioxidasic and antimicrobial.

Read More

Evaluation of spraying effects of plant protection unmanned aerial vehicle on two different training systems of vine in Northeast China

In recent years, the application of plant protection unmanned aerial vehicle (UAV) in agricultural pest control has become more and more popular. However, there are few reports about the application of plant protection UAV for wine grapes, and there are no studies comparing the spraying effect of plant protection UAV with that of manual operation in vineyards. In this context, the objective of this study was to explore the feasibility of using plant protection UAV in vineyards instead of manual operations by evaluating the effectiveness of UAV spray in two common grape training systems in Northeast China.

Read More

Production and technological characteristics of some French clones of the Chardonnay variety in Yugoslavia

L’observation est effectuée entre 1996 et 1998. L’expérience a commencé avec des clones numérotés: 75, 95, 96 et 227 de la variété Chardonnay. Le porte greffe est le Kober 5 BB. La forme de conduite est le cordon. La taille est longue. La densité de plantation est 3,5 x 1 mètre (2857 ceps par 1/ha).

Read More

WINE SWIRLING: A FIRST STEP TOWARDS THE UNLOCKING OF THE WINE’STASTER GESTURE

Right after the pouring of wine in a glass, a myriad of volatile organic compounds, including ethanol, overwhelm the glass headspace, thus causing the so-called wine’s bouquet [1]. Otherwise, it is worth noting that during wine tasting, most people automatically swirl their glass to enhance the release of aromas in the glass headspace [1]. About a decade ago, Swiss researchers revealed the complex fluid mechanics underlying wine swirling [2]. However, despite mechanically repeated throughout wine tasting, the consequences of glass swirling on the chemical space found in the headspace of wine glasses are still barely known.

Read More