In precision agriculture, the scarcity of labeled data and significant covariate shifts pose unique challenges for training machine learning models. This scarcity is particularly problematic due to the dynamic nature of the environment and the evolving appearance of agricultural subjects as living things. We propose a novel system for generating realistic synthetic data to address these challenges. Utilizing a vineyard simulator based on the Unity engine, our system employs a cut-and-paste technique with geometrical consistency considerations to produce accurate photo-realistic images and labels from synthetic environments to train detection algorithms. This approach generates diverse data samples across various viewpoints and lighting conditions. We demonstrate considerable performance improvements in training a state-of-the-art detector by applying our method to table grapes cultivation. The combination of techniques can be easily automated, an increasingly important consideration for adoption in agricultural practice.

Self-Supervised Data Generation for Precision Agriculture: Blending Simulated Environments with Real Imagery / Saraceni, Leonardo; Motoi, IONUT MARIAN; Nardi, Daniele; Ciarfuglia, THOMAS ALESSANDRO. - (2024), pp. 71-77. (Intervento presentato al convegno 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE) tenutosi a Bari; Italy) [10.1109/CASE59546.2024.10711594].

Self-Supervised Data Generation for Precision Agriculture: Blending Simulated Environments with Real Imagery

Leonardo Saraceni
;
Ionut Marian Motoi;Daniele Nardi;Thomas Alessandro Ciarfuglia
2024

Abstract

In precision agriculture, the scarcity of labeled data and significant covariate shifts pose unique challenges for training machine learning models. This scarcity is particularly problematic due to the dynamic nature of the environment and the evolving appearance of agricultural subjects as living things. We propose a novel system for generating realistic synthetic data to address these challenges. Utilizing a vineyard simulator based on the Unity engine, our system employs a cut-and-paste technique with geometrical consistency considerations to produce accurate photo-realistic images and labels from synthetic environments to train detection algorithms. This approach generates diverse data samples across various viewpoints and lighting conditions. We demonstrate considerable performance improvements in training a state-of-the-art detector by applying our method to table grapes cultivation. The combination of techniques can be easily automated, an increasingly important consideration for adoption in agricultural practice.
2024
2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)
Compute Vision; Object Detection; Synthetic Data Generation; Data Augmentation
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Self-Supervised Data Generation for Precision Agriculture: Blending Simulated Environments with Real Imagery / Saraceni, Leonardo; Motoi, IONUT MARIAN; Nardi, Daniele; Ciarfuglia, THOMAS ALESSANDRO. - (2024), pp. 71-77. (Intervento presentato al convegno 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE) tenutosi a Bari; Italy) [10.1109/CASE59546.2024.10711594].
File allegati a questo prodotto
File Dimensione Formato  
Saraceni_Self-Supervised_2024.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.92 MB
Formato Adobe PDF
1.92 MB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1726259
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact