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…

Chemical and biochemical formation of polysulfides in synthetic and real wines using UHPLC-HRMS

ulfur compounds in wine have been studied for several years due to their impact on wine flavour, but the role of polysulfides is a recent topic. Polysulfides in wine are formed when two sulfhydryl groups oxidize, especially in presence of elemental sulfur or metal catalysts from field treatment residues (Ugliano et al. 2011). These compounds are odourless, but can degrade during storage and affect the wine quality. The mechanism of their formation is still largely unknown but different chemical and biochemical pathways have been suggested. Disulfides from cysteine (Cys) and glutathione (GSH) have been revealed in model wines (Kreitman et al. 2016) and more recently also higher polymerized forms in real wines (Van Leeuwen et al. 2020). Volatile varietal thiols like 3-mercaptohexanol (3MH) and 4-mercaptopentanone (4MMP) – flavour compounds with tropical or fruity notes – could undergo similar reactions, also with Cys and GSH, subsequently losing their flavour property (fate). Even more concerning is the possible release of H2S from polysulfides during storage, leading to undesired off-flavours (Sarrazin et al. 2010).

Developing and assessing different cordon establishment techniques for long-term vineyard management

Aim: The aim of this research is to quantify the impacts of different cordon establishment techniques on vine health and longevity. It is hypothesised that wrapping developing cordon arms tightly around the cordon wire will cause a constriction of the vascular system, becoming worse over time and disrupting the flow of water and nutrients.

Characterization of the thiol aromatic potential of a new resistant grape variety: Floreal

Aims: Due to climate change and the desire to decrease enological inputs (organic farming), the vineyard has to be modified and the selection of new resistant grape varieties as an alternative is researched intensively today. From January 2018, four new grape varieties that are resistant against mildew and odium have been added to the official

Evidence of successful wine business strategies: customer acquisition, value or retention?

This presentation illustrates a series of successful wine businesses, which have managed to counter the downward trend impacting the global industry. How these businesses have been successful is explained through the planning and execution of strategies that focused on a clear and consistent aim in attracting new consumers. These cases add weight to the ehrenbergian position that for a business to be successful it must target new customers as a priority over alternative options like increasing value or improving customer retention.

Effect of soil particle size on vine water status, leaf abscisic acid content and berry quality in nebbiolo grapes

AIM: We investigated the effect of soil texture on grapevine response to water stress, leaf abscisic acid concentration and berry quality, in two adjacent vineyards located in the renewed Cannubi hill of Barolo (Langhe area, CN, North-West Italy).