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…

Non-targeted analysis of C13-norisoprenoid aroma precursors in Riesling

Significant wine aroma can be formed from non-volatile precursors that are linked to sugars, including but not limited to grape-derived monoterpene and C13-norisoprenoid glycosides.

Read More

Un jour, l’AOD (Appellation d’Origine viticole Durable), fusion de l’origine et de la durabilité

The evolution of wine quality issues is historically expressed by the passage from wine quality (what is a wine?) to wine quality (what is a good wine?). Perhaps the next question could be: what is a good sustainable wine? To contribute to reflection on this theme, it may be worthwhile to undertake an exercise in prospective fiction, which we have identified in the hypothesis of the AOD, the “appellation d’origine durable”, a scenario we will develop in the light of developments in the wine industry and the regulation on geographical indications.

Read More

Is early defoliation a sustainable management practice for mediterranean vineyards? Case studies at the portuguese lisbon winegrowing region

Context and purpose of the study ‐ Recently early defoliation (ED) has been tested in several high‐ yielding grapevine varieties and sites aiming at reducing cluster compactness and hence, regulating yield and susceptibility to botrytis bunch rot infection. The reported results have been generally positive, encouraging growers to use this canopy management technique as an alternative for replacing the conventional time‐consuming cluster thinning and, simultaneously, as a sustainable practice to reduce the use of fungicides. However, ED increases berry sunburn risks and/or can induce carry‐over effects on vigor and node fruitfulness as shown in the two case studies reported in this work.

Read More

Mucoadhesive properties of typical wine phenolic compounds and their capacity to modulate oral aroma retention under simulated wine tasting conditions

Phenolic compounds play a key role in wine sensory properties, traditionally associated with colour, taste attributes (e.g., bitterness) and trigeminal sensations such as astringency.

Read More

Oxygen transfer through cork stoppers

During wine conservation in a bottle, the control of oxygen transfer from the outside environment to the wine inside the bottle is a key parameter that determines the wine quality. Many other factors can also influence the evolution of wine during postbottling aging,

Read More