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…

Effect of different foliar nitrogen applications on the must amino acids and glutathione composition in Cabernet Sauvignon vineyard

Cabernet Sauvignon is one of the most important winegrape varieties in Chile. However, temperature raise and decreased rainfall due to climate change can lead to grape quality decrease in certain areas. Amino acids are essential as nitrogen source for yeast but also directly affect grape quality serving as precursors of certain volatile compounds that enhance the wine bouquet. Besides, glutathione is an important tripeptide acting as antioxidant, preventing the appearance of browning pigments in must and exerts a protective effect in volatile compounds.

Comparison of destructive and non-destructive measurements of table grape berries to assess quality parameters using spectroscopy

The quality of table grapes is critically influenced by several parameters, including sugar content, acidity, firmness, and overall appearance.

Rapporti tra diverse tipologie di terreno e risposte produttive e qualitative delle uve Merlot e Carmenère nell’area DOC Piave

Da anni la ricerca viticola sta orientando le sue attenzioni verso lo studio della vocazionalità degli ecosistemi viticoli, perché fulcro della produttività della vite e qualità dei suoi frutti.

Better understand the soil wet bulb formation with subsurface or aerial drip irrigation in viticulture

The gradual change in rainfall patterns experienced in the south of France vineyards, especially around the Mediterranean sea, means that the vines are increasingly subject to summer drought. The winegrowers developped the use of irrigation techniques to ensure the maintenance of competitive yields in the production of wines under Protected Geographical Indication label. In practice, drip irrigation pipes can be installed above the ground or buried into the soil as well as at different distances from the vine row. The objective of this study was to examine the profiles of the wet bulbs of the soil obtained from two drip irrigation systems : aerial drip located under the vine row and subsurface drip placed in the middle of the inter-row. This experiment took place over two consecutive seasons (2020-2021) on a 3.4 ha Viognier plot in the Mediterranean region (PGI Oc, France) on sandy clay soil. The annual rainfalls were less than 400 mm. Soil water content probes were installed at different depths (20 – 40 – 60 – 80 cm) and at different lateralities from the vine row (30 – 60 – 90 – 120 cm) to control the formation of the soil wet bulb during irrigation. The mapping and the analysis of the data allowed a better understanding and differentiation of the water percolation when irrigating with subsurface or aerial drip. For the same amount of water and without differences of vine water status, it is shown that in a subsurface drip irrigation situation, the size of the wet bulb formed is larger than in aerial drip irrigation system.

Contribution of Piperitone to the mint nuances perceived in the aging bouquet of red Bordeaux wines

During the tasting of a fine, old wine, the aromas generated in the glass are intertwined in an intimate, complex manner, expressing the fragrance of the aging bouquet. This aging bouquet, which develops during bottle storage through a complex transformation process, may result in a broad palette of nuances. Among these, undergrowth, truffle, toasted, spicy, licorice, fresh red- and black-berry fruit and mint descriptors were recently identified as features of its olfactory representation for red Bordeaux wines. Although a targeted chemical approach focusing on volatile sulfur compounds revealed the role played by dimethyl sulfide, 2-furanmethanethiol, and 3-sulfanylhexanol as molecular markers of the typicality of the wine aging bouquet of red Bordeaux wines, its chemical transcription has only partially been elucidated.