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…

Territoire, terroir et marché du vin à la production

Work aimed at understanding the relationship between a terroir, in the agronomic sense, and the physico-chemical characteristics of grapes or wine are numerous today, as evidenced by the program of this symposium. But for an economist, the central question remains to know how the terroir can intervene in the construction of the economic value of wine and in the differentiation of its prices. Is the terroir effect recognized by the end consumer or is it only an internal adjustment variable in the production systems? Through which indicators can this terroir effect be managed by the various operators in the sector? In the end, isn’t it better to invoke a “territorial effect” that the actors can build, and of which the terroir would be one of the possible components?

Read More

Politics meets terroir. The story of Prosecco – Are GI’s just a protectionist racket?

The recent Free Trade Agreement negotiations between Australia and the European Union have again put the issue of Geographical Indications (GIs) in the spotlight. Australia has long demonstrated its understanding of GIs and maintains a clear and rigorous GI protection system for wine. For many years, Australia’s wine sector was a strong advocate for GIs and a strong system to protect the

Read More

Preliminary results on the effect of different organic mulching on wine polyphenol content

Soil mulching is an interesting strategy to reduce soil evaporation, assist in weed control, improve soil structure and organic content, increase soil water infiltration, and decrease diurnal temperature fluctuations

Read More

Fractal analysis as a tool for delimiting guarantee of quality areas

The pioneering work of Mandelbrot in the 70’s for building the fractal theory lead rapidly to many interesting applications in different fields such as earth sciences and economy.

Read More

Comparative proteomic analysis of wines made from Botrytis cinerea infected and healthy grapes reveal interesting parallels to the gushing phenomenon in sparkling wine

In addition to aroma compounds also protein composition strongly influences the quality of wines. Proteins of wine derive mainly from the plant Vitis vinifera and may be influenced by abiotic stress as well as fermentation conditions or fining. Additionally, fungal infections can affect the protein content as well by introducing fungal proteins or affecting grape protein composition. An infection of the vine with the plant pathogenic fungus Botrytis (B.) cinerea was shown to cause a degradation of proteins in the resulting wine. Moreover, it influences the foaming properties in sparkling wine.

Read More