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…

Panorama des actions d’amélioration variétale face aux challenges d’aujourd’hui et de demain, le rôle de l’IFV

In April 2024, the French official catalog includes 449 grape varieties and rootstocks. In 10 years it has been enriched with 70 varieties. It is an indisputable marker of the interest of professionals in genetic resources of all origins and the expectations they have to prepare the viticulture of the future. The scientific community has now put all irons in the fire and is not neglecting any avenue of adaptation. The regular decline in the use of phytosanitary products and the already marked effects of climate change are the targets of varietal improvement.

Investigation of the effect of gelatine and egg albumin fining and cross-flow microfiltration on the phenolic composition of Pinotage red wine

Results indicated that cross-flow microfiltration removed similarly to fining treatments the most astringent tannins, but cross-flow microfiltration also removed up to 14 % more colour. RP-HPLC and spectrophotometric results showed that egg albumin is a softer fining treatment compared to gelatine and cross-flow microfiltration.

Altered lignans accumulation in a somatic variant of Tempranillo with increased extractability of polyphenols during winemaking

Vegetative propagation of grapevines can generate spontaneous somatic variations, providing a valuable source for cultivar improvement. In this context, natural variation in the composition of phenolic compounds in grapevine berries and seeds stands as a pivotal factor in crafting wines with diverse oenological profiles from the same cultivar. To deepen on the understanding of the physiological and genetic mechanisms driving somatic variation in grape phenolics, here we characterized a somatic variant from Tempranillo Tinto, the clone VN21, that exhibits an intense reduced berry skin cuticle and increased extractability of phenolic compounds during wine fermentation.

UNTARGETED METABOLOMICS ANALYSES TO IDENTIFY A NEW SWEET COMPOUND RELEASED DURING POST-FERMENTATION MACERATION OF WINE

The gustatory balance of dry wines is centered on three flavors, sourness, bitterness and sweetness. Even if certain compounds were already identified as contributing to sweetness, some taste modifications remain largely unexplained1,2. Some empirical observations combined with sensory analyzes have shown that an increase of wine sweetness occurs during post-fermentation maceration³. This step is a key stage of red winemaking during which the juice is left in contact with the marc, that contains the solid parts of the grape (seeds, skins and sometimes stems). This work aimed to identify a new taste-active compound that contributes to this gain of sweetness.

Identification of loci associated with specialised metabolites in Vitis vinifera

Secondary (or specialised) metabolites such as terpenes and phenolic compounds are produced by plants for various roles which include defence against pathogens and herbivores, protection against abiotic stress, and plant signalling. Additionally, these metabolites influence grapevine quality traits such as colour, aroma, taste, and nutritional value. However, the biosynthesis of these metabolites is often complex and controlled by multiple genes which in grapevine are predominantly uncharacterised.