CLASSIFICATION OF UAV-BASED PHOTOGRAMMETRIC POINT CLOUDS OF RIVERINE SPECIES USING MACHINE LEARNING ALGORITHMS: A CASE STUDY IN THE PALANCIA RIVER, SPAIN

Autor: Carbonell-Rivera, Juan Pedro, Estornell Cremades, Javier, Ruiz Fernández, Luis Ángel, Torralba, J., Crespo-Peremarch, P.
Jazyk: angličtina
Rok vydání: 2020
Předmět:
lcsh:Applied optics. Photonics
Point cloud classification
UAV
Structure from Motion
Random forest
Riverine species

010504 meteorology & atmospheric sciences
UAV
0211 other engineering and technologies
Point cloud
Decision tree
02 engineering and technology
Land cover
Machine learning
computer.software_genre
01 natural sciences
lcsh:Technology
Aleppo Pine
021101 geological & geomatics engineering
0105 earth and related environmental sciences
geography
geography.geographical_feature_category
biology
business.industry
lcsh:T
lcsh:TA1501-1820
15. Life on land
biology.organism_classification
Structure from Motion
Random forest
Photogrammetry
Ridge
lcsh:TA1-2040
Multilayer perceptron
INGENIERIA CARTOGRAFICA
GEODESIA Y FOTOGRAMETRIA

Environmental science
Riverine species
Artificial intelligence
business
lcsh:Engineering (General). Civil engineering (General)
computer
Point cloud classification
Zdroj: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLIII-B2-2020, Pp 659-666 (2020)
ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
ISSN: 2194-9034
1682-1750
Popis: The management of riverine areas is fundamental due to their great environmental importance. The fast changes that occur in these areas due to river mechanics and human pressure makes it necessary to obtain data with high temporal and spatial resolution. This study proposes a workflow to map riverine species using Unmanned Aerial Vehicle (UAV) imagery. Based on RGB point clouds, our work derived simple geometric and spectral metrics to classify an area of the public hydraulic domain of the river Palancia (Spain) in five different classes: Tamarix gallica L. (French tamarisk), Pinus halepensis Miller (Aleppo pine), Arundo donax L. (giant reed), other riverine species and ground. A total of six Machine Learning (ML) methods were evaluated: Decision Trees, Extra Trees, Multilayer Perceptron, K-Nearest Neighbors, Random Forest and Ridge. The method chosen to carry out the classification was Random Forest, which obtained a mean score cross-validation close to 0.8. Subsequently, an object-based reclassification was done to improve this result, obtaining an overall accuracy of 83.6%, and individually a producer’s accuracy of 73.8% for giant reed, 87.7% for Aleppo pine, 82.8% for French tamarisk, 93.5% for ground and 80.1% for other riverine species. Results were promising, proving the feasibility of using this cost-effective method for periodic monitoring of riverine species. In addition, the proposed workflow is easily transferable to other tasks beyond riverine species classification (e.g., green areas detection, land cover classification) opening new opportunities in the use of UAVs equipped with consumer cameras for environmental applications.
Databáze: OpenAIRE
Pro tento záznam nejsou dostupné žádné jednotky.