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…

New crossbreed winegrape genotypes cultivated under rainfed conditions in a semi-arid Mediterranean region

Traditional drought tolerant varieties such as Cabernet Sauvignon, Monastrell, and Syrah [1], have been used as parents in the grapevine breeding program initiated by the Instituto Murciano de Investigación y Desarrollo Agrario y Medioambiental (IMIDA) in 1997 [2]. This work presents the results of evaluating three new genotypes obtained from crosses between ‘Monastrell’ and ‘Cabernet Sauvignon’ (MC16 and MC80) and between ‘Monastrell’ and ‘Syrah’ (MS104), comparing their performance under conditions of water scarcity and high temperatures with that of their respective parental varieties. For this purpose, the six genotypes were cultivated under controlled irrigation conditions (60% ETc) and rainfed conditions.

A slight temperature increase modulates changes in physiology and grape quality of two commercial vines of central Chile

Current climate change sceneries represent a menace for grapevine production. Models have estimated than in the middle of the century temperature will increase aprox. 2°C.

Quantification of polysaccharides of variety Pomaces of the D.O.Ca Rioja

Pomace is one of the main residues generated by the wine industry and represents an environmental problem. Currently, there is a growing interest in the revaluation of these products because different bioactive compounds can be obtained from them, such as polyphenols, grape seed oils and polysaccharides. Red grape pomace can be an important source of polysaccharides, but they are currently little studied and even less with viable and environmental extraction processes (green extraction), such as flash extraction. The residual amount of the fraction rich in pectin (residual pulp) and component rich in hemicellulose in the pomace and the strength of association of the pectin with the cellulose-xyloglucan network depend on the degree of extractability of the polysaccharides in red winemaking and on the winemaking conditions.

Functional characterisation of genetic elements regulating bunch morphology in grapevine

Vitis vinifera L., is considered one of the world’s most important cultivated fruit crops. In agriculture, bunch morphology is a grapevine-specific trait, which directly impacts fruit quality and health.
Bunch size, shape, and compactness are major aspects of bunch morphology, with the degree of compactness emerging as an important trait for grapevine genetic enhancement and vineyard management. The importance of this trait stems from its impact on disease susceptibility, berry ripening, and other grape quality properties. However, current knowledge of the genes controlling it remains limited.

Digitising the vineyard: developing new technologies for viticulture in Australia 

New and developing technologies, that provide sensors and the software systems for using and interpreting them, are becoming pervasive through our lives and society. From smart phones to cars to farm machinery, all contain a range of sensors that are monitored automatically with intelligent software, providing us with the information we need, when we need it. This technological revolution has the potential to monitor all aspects of vineyard activity, assisting growers to make the management choices they need to achieve the outcomes they want. For example, a future vineyard may possess automated imaging that generates a three dimensional model of the vine canopy, highlighting differences from the desired structure and how to use canopy management to improve fruit composition, or generates maps with yield estimates and measurements of berry composition throughout the growing season.