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…

Toasting and grain effect on Tempranillo red wine aged in Quercus petraea barrels

The barrel-making process is widely recognized as a crucial practice that affects the composition of barrel-aged wine. After the drying process, the staves are considered ready for barrel assembly, which includes the processes of bending and toasting the barrel structure. Toasting is considered one of the most critical stages in determining the physical and chemical composition of the staves, which can influence the chemical and sensory composition of the wine aged in barrels made from them [1].

Strategies for sample preparation and data handling in GC-MS wine applications

It is often said that wine is a complex matrix and the chemical analysis of wine with the thousands of compounds detected and often measured is proof. New technologies can assist not only in separating and identifying wine compounds, but also in providing information about the sample as a whole. Information-rich techniques can offer a fingerprint of a sample (untargeted analysis), a comprehensive view of its chemical composition. Applying statistical analysis directly to the raw data can significantly reduce the number of compounds to be identified to the ones relevant to a particular scientific question. More data can equal more information, but also more noise for the subsequent statistical handling.

The relationship between wind exposure and viticultural performance of Vitis vinifera L. cv. Merlot in a coastal vineyard (South Africa)

The South Western Cape of South Africa is exposed to strong southerly and south easterly synoptic winds during the growth period of the grapevine. The development of sea breezes in the afternoon is also a phenomenon associated with the ripening period of grapes cultivated in this coastal area. Wind is one of the environmental variables having the greatest spatial variation but the implications of regular exposure to wind for the performance of the grapevine has not yet been determined for vineyards in the South Western Cape. This study was initiated to meet this need.
The study was conducted in a hedge-trellised vineyard of Vitis vinifera L. cv Merlot with north east – south west row direction. Thirty experimental sites, each consisting of 14 vines, were identified as being exposed to wind or sheltered based on hand-held anemometer readings during the 2001/2002 season. Four stationary anemometers were strategically positioned between the thirty sites. Stomatal conductance and leaf temperature were measured with a PP systems porometer. Vegetative and yield measurements were performed during the 2002/2003 season. The t-test of equal variance was used to determine significant differences in measured parameters between exposed and sheltered grapevines.
Stomatal conductance and leaf area were significantly reduced by exposure to wind. This was associated with a significant reduction in the leaf area of primary shoots, related to shorter shoots, but a significant augmentation of secondary shoot leaf number and area. The number of bunches per vine and yield were also reduced for exposed vines. The berry potassium content was significantly increased for exposed grapevines.
This demonstrates that exposure to wind can result in significant within-vineyard, and potentially between-vineyard, variability in grapevine physiology, vegetative growth, yield and berry composition, with implications for wine style and quality.

Stem growth disorder and xylem anatomy modifications during esca pathogenesis in grapevines

Esca is a grapevine vascular disease with detrimental consequences on vineyard yield and longevity. Recently, esca leaf symptom development has been shown to result in the occlusion of xylem vessels by tyloses in leaves and stems, leading to hydraulic failure. However, little is known regarding the response of xylem anatomy and stem growth to esca in different varieties . Here we studied the impact of esca leaf symptom development on grapevine physiology, stem growth, and xylem anatomy in two widespread cultivars, Cabernet sauvignon and Sauvignon blanc.

Soil and nutritional survey of Greek vineyards from the prefecture of Macedonia, Northern Greece, and from the island of Santorini

Vitis vinifera L. is one of the most important cultures for the soil and
climate conditions of Northern Greece and Santorini. However, very little information is provided with regard to its nutritional requirements and critical levels of nutrient deficiencies and toxicities. The aim of this study was to provide an integrated nutritional survey for the Greek conditions of wine and table varieties.