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…

A mechanistic investigation of H/D scrambling processes in flavonoids

Several classes of flavonoids, such as anthocyanins, flavonols, flavanols and flavones, undergo a slow H/D exchange on aromatic ring A, leading to full deuteration at positions C(6) and C(8). Within the flavanol class, H-C(6) and H-C(8) of catechin and epicatechin are slowly exchanged in D2O to the corresponding deuterated analogues; even quercetin, a relevant flavonol representative, shows the same behaviour in a D2O/DMSOd6 1:1 solution. Detailed kinetic measurements of these H/D scrambling processes are here reported by exploiting the time-dependent changes of their peak areas in the 1H-NMR spectra taken at different temperatures. A unifying reaction mechanism is also proposed based on our detailed kinetic observations, even taking into account pH and solvent effects. Molecular modelling and QM calculations were also carried out to shed more light on several molecular details of the proposed mechanism.

The landscape in the development of vineyard regions: an application to the ACO Dão and ACO Bairrada (Central Portugal)

The aim of this paper is to analyse the impact of landscapes in the notoriety and marketing of wines and in tourism promotion, specifically in the case of two centenary Portuguese demarcated regions

NEW TREATMENTS FOR TEMPRANILLO WINES BY USING CABERNET SAUVIGNON VINE-SHOOTS AND MICRO-OXYGENATION

Toasted vine-shoots as enological additive represents a promising topic due to their significant effect on wine profile. However, the use of this new enological tool with SEGs varieties different than wine and combined with others winemaking technologies, such as micro-oxygenation (MOX), has not been studied so far, despite this combination could result in wine with high chemical and organoleptic quality.

Influence of maturity on grape tyrosinase activity

Enzymatic browning of grape must remains a major issue in winemaking, especially when grapes are affected by grey rot.

BIOPROTECTION BY ADDING NON-SACCHAROMYCES YEASTS : ADVANCED RESEARCH ON THIS PROMISING ALTERNATIVE TO SO₂

Sulphur dioxide has been used for many years for its antimicrobial, antioxidant and antioxydasic properties in winemaking but nowadays, it is a source of controversy. Indeed, consumers are more attentive to the naturalness of their foods and beverages and the legislation is changing to reduce the total SO₂ levels allowed in wines. To limit and replace the doses of sulphur dioxide applied, winemakers can now use bioprotection consisting in live yeast addition as alternative,seems to be promising. This process, lightly used in from the food industry, allows to colonize the environment and limit the development or even eliminate undesirable microorganisms without altering the sensory properties of the product.