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…

Chenin Blanc Old Vine character: evaluating a typicality concept by data mining experts’ reviews and producers’ tasting notes

Concepts such as typicality are difficult to demonstrate using the limited set of samples that can be subjected to sensory evaluation. This is due both to the complexity of the concept and to the limitations of traditional sensory evaluation (number of samples per session, panel fatigue, the need for multiple sessions and methods, etc.). On the other hand, there is a large amount of data already available, accumulated through many years of consistent evaluation. These data are held in repositories (such as Platter’s Wine Guide in the case of South Africa Wine, wineonaplatter.com) and in technical notes provided by the producers.

Optimisation de la fertilisation du Cot sur le Causse de l’Appellation d’Origine Contrôlée Cahors

The Appellation d’Origine Contrôlée area of ​​Cahors (Lot) covers an area of ​​21,700 ha, spread over 45 municipalities, of which only 4,300 are planted with vines. The main grape variety of this AOC is the Cot noir which represents 70% of the grape varieties, thus giving their typicality to the wines of this region; but despite this importance, to our knowledge, its physiology has remained relatively unstudied.

Using elicitors in different grape varieties. Effect over their phenolic composition

Phenolic compounds are very important in crop plants and have been the subject of a large number of studies. Three main reasons can be cited for optimizing the level of phenolic compounds in crop plants: their physiological role in plants, their technological significance for food processing, and their nutritional characteristics1 Indeed, an enormous diversity of phenolic antioxidants is found in fruits and vegetables, and their presence and roles can be affected or modified by several pre- and postharvest cultural practices and/or food processing technologies (Ruiz-García et al. 2012, Goldman et al. 1999, Tudela et al. 2002). In winegrapes, the technological importance of phenolic compounds, mainly flavonoids, is well-known.

SSR analysis of some Vitis sylvestris (GMEL.) accessions of the Szigetköz and Fertő-hanság national park, Hungary

The evolution of cultivated plants played important role in the ascent of humanity. Research of their origin and evolution started at the beginning of the20th century, but till nowadays a lot of questions remain open. A large number of theories exist about the evolution of the European grapevine (Vitis vinifera L.). The Vitis sylvestris GMEL. in Hungary is a protected species.

Developing an integrated viticulture in the upper part of the hill Somló

The hill Somló looks like a huge island wich jumps out of the see, a few kilometers away from the slope of Bakony highland and on the edge of the Hungarian small plane.