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…

Polyphenolic profile and dietary fiber content of skins and seeds from unfermented and fermented grape pomace

The valorization of winemaking byproducts is subordinated to the knowledge of their chemical characteristics. This work concerned the determination of the polyphenolic profile and the dietary fiber content of skins and seeds from unfermented and fermented pomace of different cultivars (Moscato bianco, Cortese, Arneis, Pinot Noir, Barbera, Grignolino, Nebbiolo), sampled from some wineries in the Piedmont area (Italy) during the 2020 harvest.

Read More

Enhancing plant defense: carbon dots for efficient spray-induced gene silencing 

Ectopic RNA application for plant defense faces challenges in tree crops, including size, diffusion, and stability of active compounds such as ribonucleoproteins and nucleic acids. While existing strategies involve expressing dsRNA in transgenic plants targeting pathogens, our research strives to develop a transient RNAi system based on Spray-Induced Gene Silencing (SIGS). This approach aims to circumvent legal barriers and public concerns associated with genetically modified organisms (GMOs). Our strategy integrates SIGS with branched polyethyleneimine-functionalized Carbon Dots (bPEI-CDs) as nanocarriers, effectively addressing unique delivery challenges in plant defense as RNA stability and uptake enhancement

Read More

Use of cyclodextrins to improve grape must fermentability thanks to their sequestering effect on medium-chain fatty acids

Cyclodextrins are complex cyclic oligosaccharides of glucose units. They are produced from the breakdown of starch by the enzymatic reaction of glucosyltransferase. The result is a ring-shaped molecule with a cavity with a hydrophilic outer part and a hydrophobic inner part. As a consequence of this cavity, cyclodextrin is able to form complexes with non-polar organic molecules [1,2].

Read More

Vineyard innovative tools based on the integration of earth observation services and in-field sensors (VitiGEOSS project)

Climate change is having an unprecedented impact on the wine industry, which is one of the major agricultural sectors around the world. Global warming, combined with the variation in rainfall patterns and the increase in frequency of extreme weather events, is significantly influencing vine physiology and exposing, more frequently, plants to severe biotic and abiotic stresses. This represents a challenge for viticulturists who need to take complex decisions to adjust vineyard management and achieve oenological goals.

Read More

CropManage online decision support tool for irrigation scheduling of vineyards

CropManage (CM) is an online decision support service (DSS) developed by the University of California, Division of Agriculture and Natural Resources for assisting farmers with efficiently managing water and nitrogen fertilizer to match the site-specific needs of their crops.

Read More