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.

Download the abstract

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…

Impact of defoliation on leaf and berry compounds of Vitis vinifera L. Cv. Riesling investigated using non-destructive methods)

Climate change has a strong impact on the earlier onset of important phenological stages and plant development in viticulture.

Read More

The adaptation and resilience of scions and rootstocks to water constraint

The ability of grapevine cultivars and rootstocks to cope with and adapt to recurring water constraints is the focus of this study. The contribution of intrinsic (epigenetic) and extrinsic (rootzone microbial community) factors to water stress resilience will be discussed. The study was conducted in a validated model vineyard where three scion cultivars (Pinotage, Shiraz, and Cabernet Sauvignon) on two rootstocks (Richter 110 and USVIT8-7) grow under recurring seasonal water constraint (and control) scenarios since planting (in 2020). Comprehensive profiling of the site, soil, atmospheric conditions, plants, and their physiological responses provide contextual data for the analyses conducted.

Read More

The colour pattern of flower arrangements influence wine tasters’ sensory description

The arrangements of flowers and wine counterparts are inextricably linked. Whether a fundamental aspect of tablescaping or acolytes to broader entertainment rituals, they have an entangled history since ancient times. The aim of this contribution is to verify the influence of visually delicate and robust flower arrangements on individual description of wines. Changes in the sensory description of wines were investigated during subjects’ (thirty-two participants) exposure to three different conditions: the presence of delicate, robust, or totally absent flower arrangements. In each condition, the same two wines were blind tasted: a wine previously defined as delicate – a Pinot Noir from Australia, and a wine known for its robust character – a Tannat from Uruguay.

Read More

Closing the carbon loop: evaluating the potential of grapevine-derived biochar as a soil conditioner in warm climate vineyards

Significant increases in anthropogenic carbon dioxide (CO2) emissions due to combustion of fossil fuels and intensive land management practices that release CO2 into the atmosphere have resulted in higher air temperatures due to the greenhouse effect.

Read More

Fine-scale projections of future climate in the vineyards of southern Uruguay

In viticulture, climate change significantly impacts the plant’s development and the quality and characteristics of wines. These variations are often observed over short distances in a wine-growing region and are linked to local features (slope, soil, seasonal climate, etc.). The high spatial variability of climate caused by local factors is often of the same order or even higher than the temperature increase simulated by the different IPCC scenarios.

Read More