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…

Flooding responses on grapevine: a physiological, transcriptional and metabolic perspective

Studies on model plants have shown that temporary soil flooding exposes roots to a significant hypoxic stress resulting in metabolic re-programming, accumulation of toxic metabolites and hormonal imbalance. To date, physiological and transcriptional responses to flooding in grapevine are poorly characterized. To fill this gap, we aimed to gain insights into the transcriptional and metabolic changes induced by flooding on grapevine roots (K5BB rootstocks), on which cv Sauvignon blanc (Vitis vinifera L.) plants were grafted.

Does the location of wine cellars have significant impact on the evolution of madeira wine polyphenols?

Unlike table wines, Madeira Wine (MW,17-22% ABV) benefits from a long aging period under thermo-oxidative aging conditions, during which it gains its unique and complex flavour. A broad study is ongoing and aims to assess if the differences in the storage conditions impact significantly the evolution of MWs during canteiro aging. Considering that polyphenols have a significant role in the wine aging, we intended to appraise if there are significant differences in the evolution trends of polyphenols of MWs aging in different cellars under canteiro. Different MWs were aged into brand-new oak casks in two different wine cellars, one in Funchal (B) and other in Caniçal (Z). Temperature and humidity data were sensor recorded. RP-HPLC-DAD was used to perform the identification and quantification of polyphenols [1]. CIELab parameters were also assessed, using an UV-Vis spectrophotometer.

Better understanding on the fungal chitosan and derivatives antiseptic effect on Brettanomyces bruxellensis in wine.

The addition of fungal chitosan in wine is allowed since 2009 to release some spoilage microorganisms such as Brettanomyces bruxellensis (OIV/OENO 338A/2009; EC 53/2011).

Protein stabilization of white wines by stabilizing filtration: pilot studies

Protein stabilization is an important part of the winemaking process of white wines, and in this work we present the results of protein stabilization of different monovarietal wines (Xarel.lo, Chardonnay, and Muscat) by a continuous stabilizing filtration process using a column packed with zirconium oxide operating in a continuous regime in a closed loop at pilot scale.

Novel ATR-FTIR and UV-Vis spectral markers for assessing the Prooxidant/Antioxidant Balance (PAB) in white wines

The browning index (BI), based on the absorbance at 420 nm, is a common oxidation marker in white wines, typically measured after thermal stress (50–60 °C for 5 up to 12 days) in air-saturated wines.