Obálka

Enhancing visual autonomous navigation in row-based crops with effective synthetic data generation

Uloženo v:
Vydáno v:Precision Agriculture vol. 25, no. 6 (Dec 2024), p. 2881
Hlavní autor: Martini, Mauro
Další autoři: Ambrosio, Marco, Navone, Alessandro, Tuberga, Brenno, Chiaberge, Marcello
Vydáno:
Springer Nature B.V.
Témata:
Robotics
Datasets
Visual perception
Crops
Robust control
Image segmentation
Visual fields
Image processing
Autonomous navigation
Semantic segmentation
Virtual networks
Image quality
Visual perception driven algorithms
Visual control
Robot control
Synthetic data
Deep learning
Food
Robots
Localization
Agriculture
Simulation
3-D graphics
Farming
Artificial intelligence
Algorithms
Semantics
Precision agriculture
Environmental
On-line přístup:Citation/Abstract
Full Text - PDF
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstrakt:IntroductionService robotics is recently enhancing precision agriculture enabling many automated processes based on efficient autonomous navigation solutions. However, data generation and in-field validation campaigns hinder the progress of large-scale autonomous platforms. Simulated environments and deep visual perception are spreading as successful tools to speed up the development of robust navigation with low-cost RGB-D cameras.Materials and methodsIn this context, the contribution of this work resides in a complete framework to fully exploit synthetic data for a robust visual control of mobile robots. A wide realistic multi-crops dataset is accurately generated to train deep semantic segmentation networks and enabling robust performance in challenging real-world conditions. An automatic parametric approach enables an easy customization of virtual field geometry and features for a fast reliable evaluation of navigation algorithms.Results and conclusionThe high quality of the generated synthetic dataset is demonstrated by an extensive experimentation with real crops images and benchmarking the resulting robot navigation both in virtual and real fields with relevant metrics.
ISSN:1385-2256
1573-1618
DOI:10.1007/s11119-024-10157-6
Zdroj:ABI/INFORM Global