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…

Formation And Evolution Of Minty Terpenoids During Model Ageing Of Cabernet Franc And Merlot Wines

In recent years, a pool of terpenoids possibly implicated in minty odours and in the appreciable refreshing sensation, has been identified in long aged red Bordeaux wines (Lisanti et al., 2021, Picard et al., 2016; Picard et al., 2017). These compounds were found to play a key role in the so-called “ageing bouquet”, that can be defined as “the homogeneous, harmonious flavour resulting from the complex transformation process in wine during bottle storage” (Picard et al., 2015). Moreover the minty-fresh sensory dimension in fine aged red wines plays an important role in typicity judgement by wine professionals (Picard et al., 2015).

Read More

Chemical affinity and binding capacity between pre-purified Cabernet-Sauvignon/Merlot anthocyanins and salivary proteins monitored by UHPLC Q-ToF MS analysis

Apart from pro(antho)cyanidins and tannins, other phenolic compounds in wine or grapes have been shown to interact with salivary proteins and may contribute to overall sensory in-mouth sensations [1, 2]. Anthocyanins are the dominant phenolics in red wine and grape skin [3] , so it is expected that they come into contact and interact with salivary proteins after ingestion.

Read More

Determination of metallic elements in Chilean wines by atomic absorption spectroscopy and inductively coupled plasma–mass spectrometry

The chemical composition of wines depends on series of variables such as the type of grape, edaphoclimatic conditions, and viticulture and winemaking practices employed during production. Metallic elements play a significant role during winemaking (e.g. as catalysts of oxidation reactions) and have been previously employed for the classification of wines according to provenance. In this work, we focused on the analysis of metallic elements (K, Na, Ca, Zn, Cu, Fe, Mg, Mn, Ni, Cr, Al, Pb, Cd, Hg, Se, Co, Sn and As) in 145 Chilean wine samples (102 reds and 43 white wines), of seven grape varieties, and five of the major wine producing regions in Chile.

Read More

Crop load management of newly planted Pinot gris grown in warm climate of California

San Joaquin Valley accounts for 68% of Pinot gris acreage and produces 83% of Pinot gris wine in California. Strong demand for Pinot gris has prompted growers to restrict the nonbearing period

Read More

Mapping intra-plot topsoil diversity of Burgundy vineyards (Aloxe-Corton, France) from very high spatial resolution (VHSR) images

In this work, we present a method based on very high spatial resolution (VHSR) aerial images acquired in the visible domain and that map soil surface diversity at the hillslope

Read More