Intelligenza artificiale e ortofoto per il censimento e la gestione delle aree pascolabili in ambiente alpino

Francesca Bovolo

Abstract


Mountain areas include precious environments
like pastures that require preservation
strategies by the appointed authorities. Here
we present a system that processes orthophotos
acquired by Agenzia per le Erogazioni in
Agricoltura using Artificial Intelligence to reduce
the time and costs of human inspection
in pasture management activities. The system
is trained to automatically classify multiple
kinds of pasture and no-pasture areas. A user
interface allows to query and refine the pasture
maps. The map can be updated as new
orthophotos come in. The system achieves
good performance in the Provincia Autonoma
di Trento (PAT), but it is suitable for similar
mountain areas as well.


Parole chiave


Intelligenza Artificiale; Sistemi Informativi; Ortofoto; Pascoli; Gestione Montana

Full Text

PDF

Riferimenti bibliografici


He, K., Zhang, X., Ren, S. and Sun, J., 2016.

Deep residual learning for image recognition.

In Proceedings of the IEEE conference on

computer vision and pattern recognition, pp.

-778.

Le Cun, Y. and Bengio, Y., 1995. Convolutional

networks for images, speech, and time

series. The handbook of brain theory and

neural networks, 3361(10), p.1995.

Ruder, S., 2016. An overview of gradient descent

optimization algorithms. arXiv preprint

arXiv:1609.04747.

Kingma, D.P. and Ba, J., 2014. Adam: A

method for stochastic optimization. arXiv

preprint arXiv:1412.6980.

QGIS.org, 2021. QGIS Geographic Information

System. QGIS Association. http://www.

qgis.org




DOI: https://doi.org/10.48258/geo.v25i2.1788

Refback

  • Non ci sono refbacks, per ora.




Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.