Abstract | ||
---|---|---|
Develop ground robots for crop monitoring and harvesting in steep slope vineyards is a complex challenge due to two main reasons: harsh condition of the terrain and unstable localization accuracy got from Global Positioning Systems (GPS). For this context, a reliable localization system requires a high density of natural/artificial features and an accurate detector. This paper presents a novel visual detector for Vineyards Trunks and Masts (ViTruDe). The ViTruDe detector was developed considering the constrains of a cost-effective robot to carry-out crop monitoring tasks in steep slope vineyard environment. The obtained results with real data shows an accuracy higher than 95% for all tested configurations. The training and test data are made public for future research work. This approach is a contribution for an accurate and reliable localization system that is GPS-free. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/ICARSC.2016.68 | 2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC) |
Keywords | Field | DocType |
vine trunk detector,reliable robot localization system,crop monitoring,global positioning systems,GPS,vineyard trunk and mast,ViTruDe detector,cost-effective robot,steep slope vineyard environment,crop harvesting | Terrain,Remote sensing,Support vector machine,Feature extraction,Real-time computing,Global Positioning System,Test data,Engineering,Simultaneous localization and mapping,Robot,Detector | Conference |
ISSN | ISBN | Citations |
2573-9360 | 978-1-5090-2256-4 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jorge Mendes | 1 | 0 | 0.68 |
Filipe Neves dos Santos | 2 | 23 | 12.24 |
Nuno Ferraz | 3 | 0 | 1.01 |
Pedro Couto | 4 | 119 | 9.41 |
Raul Morais | 5 | 56 | 13.00 |