De Olho na Mata: monitoring Atlantic Forests with drones and few-shot learning

The expansion of invasive species is a global challenge that leads to the loss of biodiversity habitat, and there are few tools to control it. In São Paulo, identification of invasive species is done through field inspections, in parts of Conservation Units and parks, making it difficult...

Full description

Saved in:
Bibliographic Details
Main Authors: A. A. Pedro, F. Dadrass Javan, S. Georgievska, E. H. P. Barreto, O. Ku, F. de Oliveira, P. D. P. Oliveira, C. Gevaert
Format: Article
Language:English
Published: Copernicus Publications 2024-11-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/387/2024/isprs-archives-XLVIII-3-2024-387-2024.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850198713145753600
author A. A. Pedro
F. Dadrass Javan
S. Georgievska
E. H. P. Barreto
O. Ku
F. de Oliveira
P. D. P. Oliveira
C. Gevaert
author_facet A. A. Pedro
F. Dadrass Javan
S. Georgievska
E. H. P. Barreto
O. Ku
F. de Oliveira
P. D. P. Oliveira
C. Gevaert
author_sort A. A. Pedro
collection DOAJ
description The expansion of invasive species is a global challenge that leads to the loss of biodiversity habitat, and there are few tools to control it. In S&atilde;o Paulo, identification of invasive species is done through field inspections, in parts of Conservation Units and parks, making it difficult to map all tree individuals for adequate management and coping strategies. This manuscript presents a workflow that combines Unmanned Aerial Vehicles (UAVs), or drones, with Artificial Intelligence (AI) to accurately map invasive species in the Atlantic Forest. It describes best practices on how to conduct drone flights to map the forests, exponentially expanding the range of identification and efficiency in invasive tree species management. It also presents an AI workflow that uses few-shot learning and Explainable AI techniques (to guarantee transparency and understanding of the decisions made by the algorithms). Preliminary results indicate that the method obtains acceptable results in the range of 70 percent accuracy for <em>Archontophoenix cunninghamiana</em> (popular name: Seaf&oacute;rtia), an invasive Australian palm.
format Article
id doaj-art-0081ee3dde9c46f3bf5e1a49ec01d864
institution OA Journals
issn 1682-1750
2194-9034
language English
publishDate 2024-11-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-0081ee3dde9c46f3bf5e1a49ec01d8642025-08-20T02:12:49ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-11-01XLVIII-3-202438739210.5194/isprs-archives-XLVIII-3-2024-387-2024De Olho na Mata: monitoring Atlantic Forests with drones and few-shot learningA. A. Pedro0F. Dadrass Javan1S. Georgievska2E. H. P. Barreto3O. Ku4F. de Oliveira5P. D. P. Oliveira6C. Gevaert7São Paulo Municipal Green and Environment Secretariat, São Paulo, BrazilUniversity of Twente, Faculty ITC, Enschede, the NetherlandsNetherlands eScience Center, Amsterdam, the NetherlandsSão Paulo Municipal Green and Environment Secretariat, São Paulo, BrazilNetherlands eScience Center, Amsterdam, the NetherlandsSão Paulo Municipal Green and Environment Secretariat, São Paulo, BrazilSão Paulo Municipal Green and Environment Secretariat, São Paulo, BrazilUniversity of Twente, Faculty ITC, Enschede, the NetherlandsThe expansion of invasive species is a global challenge that leads to the loss of biodiversity habitat, and there are few tools to control it. In S&atilde;o Paulo, identification of invasive species is done through field inspections, in parts of Conservation Units and parks, making it difficult to map all tree individuals for adequate management and coping strategies. This manuscript presents a workflow that combines Unmanned Aerial Vehicles (UAVs), or drones, with Artificial Intelligence (AI) to accurately map invasive species in the Atlantic Forest. It describes best practices on how to conduct drone flights to map the forests, exponentially expanding the range of identification and efficiency in invasive tree species management. It also presents an AI workflow that uses few-shot learning and Explainable AI techniques (to guarantee transparency and understanding of the decisions made by the algorithms). Preliminary results indicate that the method obtains acceptable results in the range of 70 percent accuracy for <em>Archontophoenix cunninghamiana</em> (popular name: Seaf&oacute;rtia), an invasive Australian palm.https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/387/2024/isprs-archives-XLVIII-3-2024-387-2024.pdf
spellingShingle A. A. Pedro
F. Dadrass Javan
S. Georgievska
E. H. P. Barreto
O. Ku
F. de Oliveira
P. D. P. Oliveira
C. Gevaert
De Olho na Mata: monitoring Atlantic Forests with drones and few-shot learning
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title De Olho na Mata: monitoring Atlantic Forests with drones and few-shot learning
title_full De Olho na Mata: monitoring Atlantic Forests with drones and few-shot learning
title_fullStr De Olho na Mata: monitoring Atlantic Forests with drones and few-shot learning
title_full_unstemmed De Olho na Mata: monitoring Atlantic Forests with drones and few-shot learning
title_short De Olho na Mata: monitoring Atlantic Forests with drones and few-shot learning
title_sort de olho na mata monitoring atlantic forests with drones and few shot learning
url https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/387/2024/isprs-archives-XLVIII-3-2024-387-2024.pdf
work_keys_str_mv AT aapedro deolhonamatamonitoringatlanticforestswithdronesandfewshotlearning
AT fdadrassjavan deolhonamatamonitoringatlanticforestswithdronesandfewshotlearning
AT sgeorgievska deolhonamatamonitoringatlanticforestswithdronesandfewshotlearning
AT ehpbarreto deolhonamatamonitoringatlanticforestswithdronesandfewshotlearning
AT oku deolhonamatamonitoringatlanticforestswithdronesandfewshotlearning
AT fdeoliveira deolhonamatamonitoringatlanticforestswithdronesandfewshotlearning
AT pdpoliveira deolhonamatamonitoringatlanticforestswithdronesandfewshotlearning
AT cgevaert deolhonamatamonitoringatlanticforestswithdronesandfewshotlearning