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…

Using combinations of recombinant pectinases to elucidate the deconstruction of the polysaccharide‐rich grape cell wall during winemaking

The effectiveness of enzyme-mediated maceration processes in red winemaking relies on a clear picture of the target (berry cell wall structure) to achieve the optimum combination of specific enzymes to be used. However, we lack the information on both essential factors of the reaction (i.e. specific activities in commercial enzyme preparation and the cell wall structure of berry tissue). In this study, the different combinations of pure recombinant enzymes and the recently validated high throughput cell wall profiling tools were applied to extend our knowledge on the grape berry cell wall polymeric deconstruction during the winemaking following a combinatorial enzyme treatment design.

Read More

From precursor identification to the study of the distribution of 3-methyl-2,4-nonanedione in red wines and spirits

Prematurely aged red wines are marked by intense prune and fig aromatic nuances that dominate the complex bouquet that can be achieved through bottle aging.

Read More

Towards a European data basis based of advanced multi-isotopic signatures and artificial intelligence: the wine in blue project

Major and trace elements are essential for the development of grapes used for the wine. They are primarily originating from the soil. Some elements are also seldomly added during the wine making process. Therefore, the largest spectrum of major, trace and ultra-trace elements in the final wine product is a good signature of its geographical origin. In the frame of the European tracewindu, we have developed a very original multi-isotopic dilution method using triple quadrupole icp/ms.

Read More

Sensory impacts of the obturator used for the Chasselas: study over the time

Many parameters affect the organoleptic characteristics of wine: internal parameters like the chemical composition or polyphenol content and external as for example storage conditions or the type of obturator. The aim of this study was to characterize sensorally the impacts of several type of obturator on a white wine: Chasselas. To determine the organoleptic characteristics of this wine, a quantitative descriptive analysis could be used. But rapid sensory methods were preferred in this project. Indeed these methods are an appropriate alternative to conventional descriptive methods for quickly assessing sensory product discrimination.

Read More

Phenolic compounds of wine spirits resulting from different ageing technologies: behaviour during the storage in bottle

Phenolic compounds are released from the wood into the wine spirit (WS) during the ageing process, and are of utmost importance to the colour, flavour, taste and the overall quality acquired by this spirit drink.1 Their concentrations in the WS and the related effects mainly depend on the kind of wood (oaks vs chestnut), toasting level and ageing technology (traditional using wooden barrels vs alternative).1,2,3

Read More