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…

An analysis of wine geographical indications from the perspective of the theory of industrial organizations: what are the trade off?

From Porto and then through Bordeaux, Champagne and Bourgogne, wine geographical indications (gi) were the driving models for this form of protection of distinctive signs for collective use. Many studies present the benefits of recognizing a gi for a given region, the challenges of its implementation, as well as the possibilities of promoting territorial development.

Read More

PRODUCTION OF A FUNCTIONAL BEVERAGE FROM WINEMAKING BY-PRODUCTS: A NEW WAY OF VALORISATION

In the challenge of transforming waste into useful products that can be re-used in a circular economy perspective, winery by-products can be considered as a source of potentially bioactive molecules such as polyphenols. The wine industry generates each year 20 million tons of by-products. Kombucha fermentation is an ancestral process which allow to increase the biological properties of tea by the action of a microbial consortium formed by yeasts and bacteria called SCOBY. It belongs to the field of healthy food for which the interest of consumers is growing. The objective of this work was to propose a new functional beverage made from winemaking by-products fermented by a Kombucha SCOBY.

Read More

Coping with heatwaves: management strategies for berry survival and vineyard resilience

Climate change is leading to an increase in average temperature and in the frequency and severity of heatwaves that is already significantly affecting grapevine phenology and berry composition (Webb et al., 2010). This is compounded by water stress, which is well known to increase the vulnerability of grapevines and berries to heatwaves. In hot climate regions like australia, grape production is only possible due to relatively secure supplies of water for irrigation. However, the upper temperature limits for berry survival of well-watered grapevines remains to be tested.

Read More

Spectral features of vine leaves are influenced by their mineral content

The reflectance spectra of vegetation carry potentially useful information that can be used to determine chemical composition and discriminate between vegetation classes. If compared with analytical methods such as conventional chemical analysis, reflectance measurement provides non-destructive, economic, near real-time data. 

Read More

Oak wood influence on the organoleptic perception of red wine

Some wood substances such as ellagitannins (vescalagin, castalagin, grandinin, roburins (A, B, C, D, E)…) can be extracted during wine ageing in oak barrels. The level of these hydrolysable tannins in wine depends of the species and origin of oak wood as well as its treatment during barrel realization.

Read More