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…

Development of a standardized method for metabolite analysis by NMR to assess wine authenticity

The wine sector generates a considerable amount of wealth but is facing a growing problem of fraud. Wine counterfeiting is one of the oldest and most common cases of food fraud worldwide. Therefore, the authenticity and traceability of wine are major concerns for both the industry and consumers. To address these issues, robust and reliable analysis and control methods are necessary. Several methods have been developed, ranging from simple organoleptic tests to more advanced methodologies such as isotopic techniques or residual radioactivity measurements.

Monitoring the establishment of a synthetic microbial community with a potential biocontrol activity against grapevine downy mildew using a microfluidic qPCR chip

Grapevine downy mildew, caused by the oomycete Plasmopara viticola, is responsible for significant economic losses each year and for a large proportion of the fungicides used in viticulture.

Plant regeneration via somatic embryogenesis and preliminary trials for the application of the DNA-free genome editing in grapevine cv. Corvina veronese

Grapevine (Vitis spp.) is a globally significant fruit crop, and enhancing its agronomic and oenological traits is crucial to meet changing agricultural conditions and consumer demands. Conventional breeding has played a key role in domesticating grapevine varieties, but it is a time-consuming process to develop new cultivars with desirable traits for cultivation.
New plant breeding techniques (NpBTs) offer a potential revolution in grapevine cultivation, and genome editing has shown promise for targeted mutagenesis. The success of these biotechnological approaches relies on efficient in vitro regeneration protocols, particularly through somatic embryogenesis (SE).

Analysis of mousy off-flavour wines

Winemakers are increasingly experimenting with new techniques, such as spontaneous fermentation, prolonged yeast contact, higher pH, minimal sulphur dioxid, filtration and clarification or oxidative ageing. Along with this, the risk of microbial spoilage increases, and so the off-flavour mousiness, long time underestimated, is becoming more frequent. Characteristic of the mousy off-flavour is the delayed perception after swallowing the wine. After a few seconds the flavour appears, reminiscent of a dirty mouse cage. There are three known compounds that cause mousy off-flavor: 2-ethyltetrahydropyridine, 2-acetyltetrahydopyridine, and 2-acetylpyrroline. Yeasts such as Dekkera/Brettanomyces and heterofermentative lactic acid bacteria like Lactobacillus hilgardii can release these compounds.

The use of fluorescence spectroscopy to develop a variability index and measure grape heterogeneity

AIM This work aims to investigate fluorescence spectroscopy as a tool to assess grape homogenates to discriminate between samples of varying maturities and to develop an index to objectively characterise the level of grape heterogeneity present in any given vineyard.