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…

Bioprotective effect of non-Saccharomyces yeasts in wines made without SO2

The sulphur dioxide (SO2) is the most widely used additive in the wine industry because of its preservative action. However, in recent years the number of wineries that produce wines without SO2 has increased significantly because its allergenic character.

Terroir and sustainability: an analysis of brazilian vineyards from a territorial perspective

In the concept of sustainable viticulture proposed by the OIV, it can be noted that enhancing terroir is also one measure of sustainability. Thus, the territorial approach may offer an interesting viewpoint from which to consider this issue in a multi-perspective way.

WHAT’S FUTURE FOR SANTORINI’S VITICULTURE IN THE CONTEXT OF CLIMATE CHANGE

The own-rooted vineyard of Santorini is a unique case of vineyard worldwide that is been cultivated for thousands of years. On the island’s volcanic soil, the vines are still cultivated with traditional techniques, which are adapted to the specific and extreme weather conditions that prevail on it. While climate change is a reality in the Mediterranean region, will Santorini vineyard endure its impact? The study of the traditional training systems, techniques and vine density, as well as the application of sustainable solutions (cover crops and use of kaolin etc.) revealed sustainable methods for the adaptation of the local viticulture to new climatic phenomena that tend to be more and more frequent in the region due to climate change.

EFFECTS OF BIODYNAMIC VINEYARD MANAGEMENT ON GRAPE RIPENING MECHANISMS

Biodynamic agriculture, founded in 1924 by Rudolph Steiner, is a form of organic agriculture. Through a holistic approach, biodynamic agriculture seeks to preserve the diversity of agriculture and the existing interactions between the mineral world and the different components of the organic world. Biodynamic grape production involves the use of composts, herbal teas and mineral preparations such as 500, 501 and CBMT.
Several scientific studies have provided evidence on the effects of biodynamic farming on the soil, the plant and the wine. Numerous empirical opinions of wine growers support the existence of differences brought by such a management.

The grapevine single-berry clock, practical tools and outcomes 

The dynamic sequence of physiological events along the three-months of berry development from anthesis to ripe stage has been thoroughly investigated. Most studies were performed on average samples, taking care to crush enough fruits to fairly represent the overall trend of the future harvest. However, phenological stages like 30% caps off (EL25) highlights the asynchronous nature of this population. Consequently, softening, onset of sugar accumulation and coloration were melted by asynchrony in a developmental mumbo jumbo, until their respective timing could be clarified by single berries approaches.