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…

Impact of oenological tannins on microvinifications affected by downy mildew

AIM: Vine diseases are still responsible for economic losses. Previous study in our laboratory, have shown effects of oenological tannins against Botrytis cinerea1,2. According to this, the aim was to evaluate the wine protection by oenological tannins against an another disease, the downy mildew. METHODS: During the 2020 vintage, infected grapes by downy mildew (Vitis vinifera cv. Merlot) were collected from the dispositive ResIntBio. The 100 kg were crushed, destemmed and dispatch into 10 aluminium tanks. SO2 was added at 3 g/hL. Oenological tannins (grape, quebracho, ellagitannin or gallotannin) were added at 100 g/hL into eight different tanks (4×2 tanks). The two last tanks were considered as control without addition of oenological tannins. Alcoholic fermentation was achieved with Actiflore 33® at 20 g/hL. Malolactic fermentation was achieved with Lactoenos B7at 1 g/hL. Finished wines were sulfited to obtain 45 mg/L of total SO2.

How do we describe wine imagery? Expertise shapes language usage and multimodal imagery for wine

The acquisition of wine expertise is a multi-faceted and multisensory process with implications for sensory perception, attention, memory, and language production. With the prevalence of the predictive model of brain functioning, one area of burgeoning research interest involves wine mental imagery, since the brain relies on imagined experiences to build predictions for the future. Recent evidence has shown that, for instance, those with higher imagery vividness are more susceptible to wine advertising. However, little is known about the association between mental imagery and other associated cognitive processes, such as the ability to produce words that describe such imagery. 

Comparison of the skin resistance of several grape varieties in relation to their physico-chemical properties

The purpose of this study is to compare the skin resistance (SR) of the grapes with physico-chemical propertiess using a stong dataset and multidimentional statistical analysis .
A recent study has shown the role skin resistance plays against pest invasion but skin resistance could be a useful agronomic parameter, for example in the choice of the type of winemaking, by influencing the quantity of juice during crushing and maceration.

Adaptability of grapevines to climate change: characterization of phenology and sugar accumulation of 50 varieties, under hot climate conditions

Climate is the major factor influencing the dynamics of the vegetative cycle and can determine the timing of phenological periods. Knowledge of the phenology of varieties, their chronological duration, and thermal requirements, allows not only for the better management of interventions in the vineyard, but also to predict the varieties’ behaviour in a scenario of climate change, giving the wine producer the possibility of selecting the grape varieties that are best adapted to the climatic conditions of a certain terroir. In 2014, Symington Family Estates, Vinhos, established two grape variety libraries in two different places with distinctive climate conditions (Douro Superior, and Cima Corgo), with the commitment of contributing to a deeper agronomic and oenological understanding of some grape varieties, in hot climate conditions. In these research vineyards are represented local varieties that are important in the regional and national viticulture, but also others that have over time been forgotten — as well as five international reference cultivars. From 2017 to 2021, phenological observations have been made three times a week, following a defined protocol, to determine the average dates of budbreak, flowering and veraison. With the climate data of each location, the thermal requirements of each variety and the chronological duration of each phase have been calculated. During maturation, berry samples have been gathered weekly to study the dynamics of sugar accumulation, between other parameters. The data was analysed applying phenological and sugar accumulation models available in literature. The results obtained show significant differences between the varieties over several parameters, from the chronological duration and thermal requirements to complete the various stages of development, to the differences between the two locations, confirming the influence of the climate on phenology and the stages of maturation, in these specific conditions.

Consequences of apical leaf removal on grapevine water status, heat damage, yield and grape ripening on Pinot n and Chardonnay

Climate change presents a significant challenge to grape growing worldwide as increased temperatures lead to wines with increased sugar and pH levels. Manipulation of the exposed leaf area is a powerful lever governing the assimilation and storage of non-structural carbohydrates in grapevines. Reducing the leaf-to-fruit ratio is now considered as a tool for adapting to hotter and dryer grape growing conditions.