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…

DNA-free editing to improve stress resilience of wine grape genotypes recalcitrant-to-regeneration

Wine viticulture, being firmly linked to the vine-terroir relationship, has always encountered significant bottlenecks to genetic innovation. Nonetheless, the development of new breeding strategies leading to the selection of stress resilient genotypes is urgent, especially in viticulture, where it would allow reducing the use of chemical treatments adopted to control fungal diseases. Genome editing represents an extremely promising breeding technique. Unfortunately, the well-known recalcitrance of several wine grape cultivars to in vitro regeneration strongly limits the exploitation of this approach, which to our knowledge has so far been developed on table grape genotypes with high regeneration potential.

Measurement of synthetic solutions imitating alcoholic fermentation by dielectric spectroscopy

Having the possibility to use a wide spectrum of elecromagnetic waves, dielectric spectroscopy is a technique commonly used for electrical characterization of dielectrics or that of materials with high energy storage capacity, just to name a few. Based on the electrical excitation of dipoles (polymer chains or molecules) or ions in relation to the characteristics of a weak external electric field, this method allows the measurement of the complex permittivity or impedance of polarizable materials, each component having a characteristic dipole moment.In recent years, the food industry has also benefited from the potential offered by this technique, whether for the evaluation of fruit quality or during the pasteurization of apple juice [1-3]. As the tests are fast and do not destroy the products, dielectric spectroscopy proved to be an experimental tool suitable for online measurements as well as long-term monitoring.

Chemical and sensory evaluation of Bordeaux wines (Cabernet sauvignon and Merlot) and correlation with wine age

This study was carried out on 24 vintages of Cabernet sauvignon and on 7 vintages of Merlot produced by two different Bordeaux growing areas. Proanthocyanidin monomers and oligomers, and several parameters of the proanthocyanidin fraction were analytically assessed.

Impact of cover crop in vineyard on the musts volatile profile of Vitis vinifera L. Cv Syrah

rape aromatic characteristics are very important for the production of quality wines. The concentrations of volatile compounds in grape berries from vines with cover crops have been scarcely studied.

PHENOTYPIC DIVERSITY AND BIO-PROTECTION CAPABILITY OF METSCHNIKOWIA SP. IN OENOLOGY

Nowadays, the trend is to reduce the use of chemical inputs in the food sector, including in oenology. One of the inputs widely used in the wine making process are sulfites, for its several properties: antimicrobial and antioxidiant. This use isn’t without consequences on consumer’s health and environment, it can lead for example to allergic reactions and pollution. To limit the addition of chemical inputs, microbial alternatives are used. It consists to inoculate in grape must, a micro-organism able to inhibit the growth of the negative indigenous flora during the phase before the fermentation and to guarantee the sensory qualities of wines.