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…

Estudios de zonificación vitícola en España

La delimitación y caracterización de zonas vitícolas plantea en España problemas específicos no sólo por las características peculiares del territorio sino también por el tamaño

Vitamin content of grape musts and yeast nutrition: A review

The management of yeast nutrition is an essential approach for a better control over wine fermentation process. Most of the researches on this subject in the last decades focused on nitrogen nutrition. However, vitamins, while being key compounds for yeast metabolism as co-factors for numerous enzymatic activities, were left mostly unexplored.

Characterization and biological effects of extracts from winery by-products

Pomace, stem, grapevine leaves, and vine shoots arise as so called winery by-products during the wine production process.

Tropical fruit aroma in white wines: the role of fermentation esters and volatile thiols

Volatile thiols are impact aroma compounds, well-known in the literature for imparting tropical fruit aromas such as passion fruit, guava, grapefruit, and citrus in white wines [1]. More recent evidence suggests that tropical fruit aromas are also caused by other aroma compounds besides thiols, such as fermentation esters, or the interaction between these volatile families. Therefore, the objective of this study was to investigate the effects of combining esters and/or thiols to determine their impact on the fruitiness aroma perception of white wines. Pinot gris wine was produced at the OSU research winery and was dearomatized using Lichrolut® EN. Combinations of fermentation volatile compounds were added to the wine, forming the aroma base. Treatment wines were composed of additions of different concentrations and combinations of thiols and/or esters. Samples were subjected to sensory analysis where forty-six white wine consumers evaluated the orthonasal aroma of the wines and participated in Check-All-That-Apply (CATA).

Effectiveness of “curettage” and rootstock over-grafting in the control of esca

Context and purpose of the study. The grapevine domestication requested the need of pruning, which expose the vines to trunk pathogens, leading to the spread of vine trunk diseases.