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…

Fractionation of copper and iron in wine: Assessment of potential macromolecule and sulfur binding agents

Copper and iron are known to substantially impact wine stability through oxidative, reductive or colloidal phenomena. However, the binding of metal ions to different wine components under wine conditions, and the impact of this binding on the ability of the metal ions to induce spoilage processes, is not well understood. This study surveyed a range of red and white wines for an understanding of the variability of broad metal categories within the wines. The techniques utilized included an electrochemical constant current stripping potentiometry technique (ccSP), and solid phase extraction (SPE) fractionation of wine with subsequent analysis of the metal content of each fraction by inductively coupled plasma – optical emission spectroscopy (ICP-OES).

Chemical and sensory evolution of total and partial dealcoholized wine in a can

In recent years, wine consumption has been evolving towards new trends. On the one hand, awareness of health and responsible consumption has been growing, and with it, the demand for wines with lower or without alcohol content [1].

Sensory profile: a tool to characterize originality of wines produced without sulfites

A trend to reduce chemical inputs in wines exists, especially sulfur dioxide (SO2). This additive is widely used due to its antioxidant, antiseptic and antioxidasic properties. During without sulfites vinification, bioprotection by adding yeast on harvest could be a sulfites alternative. With extension of this wine market, sensory impact linked to sulfites absence and/or sulfites alternative should be evaluated. That’s what this approach proposes to do, focusing on sensory characteristics of wines produced with or without SO2 addition during the winemaking process. METHODS: Wines were elaborated from Merlot grapes of two maturity levels according to three modalities: SO2, without SO2 and bioprotection on harvest (mix of Torulaspora delbrueckii and Metschnikowia pulcherrima). SO2 modality was sulfited throughout the winemaking and aging processes whether other modalities received any addition. After two years of aging, sensory studies were carried out with a specific panel for one month. First, descriptors were generated to differentiate the wines, then panelists were trained on these specific descriptors for five sessions and finally wines sensory profiles were elaborated

Water use efficiency of Chardonnay under different grafting combinations in the viticultural area of Franciacorta

Drought poses a challenge to future viticulture, exacerbated by climate change, which increases the frequency and severity of water shortages.

Big data analysis of pesticides from the vine to the winery

Of biocontrol products and resistant grape varieties, synthetic pesticides are still widely used to control fungal diseases and protect vines from potential damage caused by pests. The use of pesticides is strictly regulated, and their use can sometimes lead to transfer from the grapes to the must and then into the wine. The study of pesticide residues in grapes and wines is commonly carried out by wine producers in order, among other things, to optimize treatment routes, check that products comply with regulations, and ultimately guarantee the food safety of the wine.