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…

Environmental sustainability in the production of grappa with the use of mould-resistant grape varieties: the aroma characterisation of distillates

Grappa is the most important italian spirit and its production includes elements of history, tradition, and culture of the transalpine country. In accordance with EU laws, grappa is obtained from the fermentation and distillation of the pomace, eventually added with fermentation lees and water. Grappa is one of the richest fruit distillates in volatile compounds that confer to the product its characteristic flagrance. The aroma is largely due to the volatile compounds present in the raw materials, in particular alcohols, esters and carbonyl compounds formed during the alcoholic fermentation, but also to grape aromas such as terpenols and norisoprenoids, that confers grappa the distinctive floral scents.

Metabolomics screening of Vitis sp. interspecific hybrids to select natural ingredients with cosmetic purposes

Introducing natural ingredients using green chemistry practices is a major challenge in cosmetics industry to follow the market trend. Among the plants of cosmetic interest, vine products show a remarkable diversity of natural substances with high potential for the cosmetic and dermatological sectors. To date, research focuses on well-known compounds like E-resveratrol and E-ε-viniferin,

Towards an ecological architecture inspired by underground cellars: An example of the thermal inertia of Moldovan underground cellars and new geothermal and Canadian well approaches

The search for underground shelters is one of the oldest forms of human habitation, providing refuge in extreme environments such as deserts and polar regions.

Defoliation combined with exogenous ABA application results in slower ripening and improved anthocyanin profile

Reducing sugar accumulation in grape (Vitis vinifera L.) berries may be a way to mitigate the effect of climate change. Managing canopy and crop load is an effective way to do so, however, reducing canopy size has been demonstrated to induce undesirable effects on anthocyanins. The aim of this study was to test if an application of exogenous ABA on the grape berries of defoliated vines (⅔ of the leaves removed) can result in slower sugar accumulation while maintaining grape and wine quality. An experiment with defoliation and exogenous ABA application on directly on clusters (factorial design 2×2) was performed with ‘Tempranillo’ fruit-bearing cuttings.

Wine ageing: Managing wood contact time.

Barrel ageing is a transformative process that alters a wine’s organoleptic properties and consequently its price. Even though it is considered beneficial mostly for red wines, ageing can also be used for white wines but for shorter time periods. Due to barrel costs, space requirements and the markets’ demands for fast release of each new vintage, new products such as oak chips or shavings have been developed to help minimize the time needed for the extraction of essential wood compounds.