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.

Download the abstract

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…

The wine microbial consortium: a real terroir characteristic

Yeast, bacteria, species and strains play a key role in the winemaking process by producing metabolites which determine the sensorial qualities of wine. Therefore microbial population numeration, species identification and strains discrimination from berry surface at harvest to storage in bottle are fundamental.

Read More

Determination of selected phenolics, carotenoids and norisoprenoids in Riesling grapes after treatment against sunburn damage

Riesling represents the most widely cultivated grape variety in Germany and is therefore of particular economic interest. During recent years an increase in the petrol-note as well as in undesirable bitter and adstringent notes has been reported. These changes are most likely linked to increasing temperature and sunlight exposure of grapes due to climate changes.
The “petrol note” is caused by the formation of the C13-norisoprenoid 1,1,6-trimethyl-1,2-dihydronaphthalin (TDN), which originates from acid-labile precursors formed by the carotenoid degradation in the grape.

Read More

EVALUATION OF INDIGENOUS CANADIAN YEAST STRAINS AS WINE STARTER CULTURES ON PILOT SCALE FERMENTATIONS

The interactions between geographical and biotic factors, along with the winemaking process, influence the composition and sensorial characteristics of wine¹. In addition to the primary end products of alcoholic fermentation, many secondary metabolites contribute to wine flavor and aroma and their production depends predominantly on the yeast strain carrying out the fermentation. Commercially available strains of S. cerevisiae help improve the reproducibility and predictability of wine quality. However, most commercial wine strains available on the market have been isolated from Europe, are genetically similar, and may not be the ideal strain to reflect the terroir of Canadian vineyards².

Read More

VOLATILE AND GLYCOSYLATED MARKERS OF SMOKE IMPACT: EVOLUTION IN BOTTLED WINE

Smoke impact in wines is caused by a wide range of volatile phenols found in wildfire smoke. These compounds are absorbed and accumulate in berries, where they may also become glycosylated. Both volatile and glycosylated forms eventually end up in wine where they can cause off-flavors. The impact on wine aroma is mainly attributed to volatile phenols, while in-mouth hydrolysis of glycosylated forms may be responsible for long-lasting “ashy” aftertastes (1).

Read More

Sviluppo di una metodologia di tracciabilità e definizione dell’impronta petrochimica in suoli e vini della Sicilia occidentale nella piana di Marsala (TP)

I risultati delle ricerche condotte in un vigneto sperimentale di Marsala (TP), scelto per omogeneità di fattori bio-agronomici (età, tecniche colturali, potenzialità vegetativa e produttiva)

Read More