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…

DNA-Free genome editing confers disease resistance in grapevine

Grapevine (Vitis Vinifera L.), one of the most important cultivated fruit crops, is facing significant challenges due to climate change. Specifically, increasing temperatures negatively impact the physiological traits and disrupt plant phenology. Additionally, increased virulence in pathogen attacks and pests leads to significant yield loss, requiring widespread application of plant protection products. Traditional agronomic practices offer only partial mitigation, requiring the development of precise and effective intervention strategies. The economic worth of viticulture has prompted continuous efforts in grapevine genetic improvement programs, traditionally involving conventional breeding and clonal selection that, however, are complex and time-consuming approaches.

Bioprospecting of native Metschnikowia pulcherrima strains for biocontrol and aroma enhancement in the wine production chain

Metschnikowia pulcherrima is a well-studied non-conventional oenological yeast due to its positive contributions to winemaking as a bioprotective agent and as an aroma-enhancing starter in sequential fermentations with Saccharomyces cerevisiae (Binati et al., 2023; Canonico et al., 2023).

Investigation on the effects of terrain slope and elevation on chemical features of wine within the PDO Prosecco area in Veneto region (Italy)

The terroir can be considered as a well-defined area where natural conditions such as geomorphology of location, climate, ventilation, sun exposure, rainfall quantity and distribution, and humidity contribute to the production of a wine that is specific to that area and identifiable through the characteristics of the territory of origin (Bonfante and Brillante, 2022).

Homozygosity of the berry color locus on chr 2 in Vitis vinifera cv. Dornfelder, Domina and Probus

Achieving intense berry coloration and high phenolic ripeness represents a major challenge in cool climate viticulture, where lower temperatures often limit anthocyanin accumulation and the production of full-bodied red wines.

Sensory and colorimetric profiling of Armenian brandy: influence of aging on aroma, taste, and visual characteristics

Armenian brandy is a culturally and economically significant distilled spirit, characterized by a complex sensory profile shaped by autochthonous grapevine varieties, distillation, and barrel aging and blending.