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…

Physico-chemical properties of vine pruning residues with potential as enological additive

Grapes are one of the world’s primary fruit crops, and pruning activities generate high amounts of annual wood wastes [1]. These pruning shoots contain valuable phenolic compounds and could have numerous potential applications [1,2]. Consequently, the aim of this work was to evaluate the physico-chemical properties of vine pruning residues with potential as enological additives. For this purpose, grapevine shoots from 12 varieties grown in Chile were collected during the winter of 2021.

Molecularly imprinted polymers: an innovative strategy for harvesting polyphenoles from grape seed extracts

Multiple sclerosis (MS) is a multifactorial autoimmune disease associating demyelination and axonal degeneration developing in young adults and affecting 2–3 million people worldwide. Plant polyphenols endowed with many therapeutic benefits associated with anti-inflammatory and antioxidant properties represent highly interesting new potential therapeutic strategies. We recently showed the safety and high efficiency of grape seed extract (GSE), a complex mixture of polyphenolics compounds comprising notably flavonoids and proanthocyanidins, in an experimental autoimmune encephalomyelitis (EAE) mouse model of MS.

Advancing wine authentication: non-invasive near-infrared spectroscopy and machine learning for vintage and quality traits assessment

Wine fraud, encompassing counterfeiting and adulteration, poses a significant threat to the wine industry, resulting in annual losses totalling billions of dollars.

From soil to canopy, the diversity of adaptation strategies  to abiotic constraints in grapevine

Climate change is here. One of the main consequences is an increase in the frequency and severity of abiotic stresses which mostly occur in a combined manner. Grapevine, which grows in a large diversity of pedo-climatic conditions, has presumably evolved different mechanisms to allow this widespread adaptation. Harnessing the genetic diversity in these mechanisms will be central to the future of viticulture in many traditional wine growing areas. The interactions between the scion and the rootstock through grafting add an additional level of diversity and adaptive potential to explore.
At the physiological level, these mechanisms are related to processes such as root system development and functioning (water and nutrient uptake), interactions with the soil microbiome, gas exchange regulation, hydraulic properties along the soil-plant-atmosphere continuum, reserve storage, short and long distance signaling mechanisms and plasticity for some of these traits.

Implications of the respect of pruning principles on grapevine development

After some decades sunk into oblivion, pruning has recently recovered the focus of grape growers and viticulturists worldwide. Attention is now being paid to the respect the sap flow continuity and to pruning wounds, as they may affect the general performance and longevity of the plant. The longevity and profitability are strongly affected by the increasing incidence of grapevine wood diseases (GWD), intensified by the omission of good pruning practices and leading to an increasingly aggressive pruning. The purpose of this study is to provide an objective evaluation of the short- and mid-term implications of different pruning practices that differ in the degree of observation several of pruning principles.