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…

Terroir effects on wine aromatic metabolomics in the eastern foot of Helan Mountain, Ningxia, China

Aim: The eastern foot of Helan Mountain, Ningxia, China is one of the most important wine production regions in China and grape cultivation has spread in several sub-regions with different soils and cultivars. Large diversity in wine aromas have been observed at Ningxia region but which terroir factors drive those diversity in aromas remain to uncover. This study aims to investigate the impacts of grape varieties and soil chemical properties on wine aromas at Ningxia, in order to characterize the aromatic typicality of Ningxia wines and provide foundation for developing a ‘Protected Designation of Origin’ system. 

Impacts of environmental variability and viticultural practices on grapevine behaviour at terroir scales

Climate change poses several challenges for the wine-industry in the 21st century. Adaptation of viticultural and winemaking practices are therefore essential to preserve wine quality and typicity. Given the complex interactions between physical, biological and human factors at terroir scales, studies conducted at these fine scales allow to better define the local environment and its influences on grapevine growth and berry ripening.

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

Effects of post-fermentative cold maceration on chemical and sensory characteristics of Syrah, Cabernet Franc and Montepulciano wines

Astringency sensation decreases slowly during the aging of red wine. Complex reactions of condensation and precipitation of wine polyphenols are involved in this phenomenon. Wine composition and conditions of aging, such as temperature and oxygen availability, strongly influence evolution of the phenol matrix. Recently, a Post-Fermentative cold Maceration (PFM) technique was tested with the aim of accelerating reactions leading to the reduction of astringency and exploiting chemical compounds not extracted from the solid parts of grapes during the previous traditional maceration phase. To this purpose, an innovative maceration system was engineered and used to perform PFM trials on marc derived from vinification of different varieties of red grapes.

Effects of the biodynamic preparations 500 and 501 on vine and berry physiology, pedology and the soil microbiome

In the pursuit of increasing sustainability, climate change resiliency and independence of synthetic pesticides in agriculture, the interest of consumers and producers in organic and biodynamic farming is steadily increasing. This is in particular the case for the vitivinicultural industry in Europe, where more and more producers are converting from organic to biodynamic farming. However, clear scientific evidence showing that biodynamic farming improves vine physiology, vine stress resilience, berry or wine quality, or is more sustainable for the environment is still lacking although this issue has been addressed by several research teams worldwide.