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…

ANTIOXIDANT CAPACITY OF INACTIVATED NON-SACCHAROMYCES YEASTS

The importance of the non-Saccharomyces yeasts (NSY) in winemaking has been extensively reviewed in the past for their aromatic or bioprotective capacity while, recently their antioxidant/antiradical potential has emerged under winemaking conditions. In the literature the antioxidant potential of NSY was solely explored through their capacity to improve glutathione (GSH) content during alcoholic fermen- tation [1], while more and more studies pointed out the activity of the non-glutathione soluble fraction released by yeasts [2].

Studio per la caratterizzazione delle produzioni vitivinicole dell’area del Barbera d’Asti DOC

Il Barbera rappresenta sicuramente uno dei più importanti vitigni autoctoni del Piemonte occu­pando circa il 50% della superficie vitata regionale. Esso è ancora diffuso su un’area molto vasta, che si estende per oltre 200.000 ha, dando origine a diverse produzioni vinicole tutelate da denominazioni d’origine.

Cover crop management and termination timing have different effects on the maturation and water potentials of Glera (Vitis vinifera L.) in Friuli-Venezia Giulia

Inter-row soil tillage in vineyards, stimulates vigor and production due to the absence of competition for water and nutrients, however negatively affects organic matter content, soil erosion, and compaction, resulting in reduced fertility. In this study, we investigated the effects of different cover crop management approaches, including cultivation type and termination timing, on the physiological and productive responses of a Glera vineyard.
The experimental trial was conducted in Precenicco (UD) from 2019 to 2021. A commercial mixture for autumn cover cropping was sown in alternating rows, and the sowing pattern was changed each year.

Biosynthetic evolution of galloilated polyphenols in Tannat grapes during ripening, potential applications of grape thinning

Galloylated flavan-3-ols are a class of polyphenolic compounds present in various plants, including grape seeds. These compounds are formed through the condensation of flavan-3-ols, such as catechins, although the precise mechanism by which gallic acid is incorporated into the molecule remains unclear.

Geospatial technologies in spatially defined viticulture: case study of a vineyard with Agiorgitiko variety in Koutsi, Nemea, Greece

Geospatial technologies have significant contribution to viticulture, especially in small-scale vineyards, which require precise management. Geospatial data collected by modern technologies, such as Unmanned Aerial Vehicle (UAV) and satellite imagery, can be processed by modern software and easily be stored and transferred to GIS environments, highlighting important information about the health of vine plants, the yield of grapes and the wine, especially in wine-making varieties. The identification of field variability is very important, particularly for the production of high quality wine. Modern geospatial data management technologies are used to achieve an easy and effortless localization of the fields’ variability.