Acacia dealbata classification from aerial imagery acquired using unmanned aerial vehicles
Authors: 
Jorge Pinto, António Sousa, Joaquim J. Sousa, Emanuel Peres, Luís PáduaAuthors Info & Claims
Jorge Pinto, António Sousa, Joaquim J. Sousa, Emanuel Peres, Luís PáduaAuthors Info & ClaimsPages 626 - 633
Abstract
Non-native plant species can have a negative impact in the ecosystems and in local economies when they spread uncontrollably. Monitoring tools can support their management and spread. In this paper, an exploratory approach is presented for pixelwise detection of Acacia dealbata from UAV-based imagery acquired from RGB and multispectral sensors. Four machine learning algorithms - k-nearest neighbors (KNN), random forest (RF), adaptive boosting (AdaBoost) and a linear kernel SVM (LSVM) - are trained using four datasets (hue, saturation and value - HSV, multispectral - MSP, RGB and a combination of all features) and their classification performance is evaluated. RF classifier obtained the overall best performance, with an accuracy above 86% in all data combinations, with LSVM showing the poorer results. Obtained results are encouraging for monitoring invasive species and can serve as a base for future improvements to detect invasive species.
References
[1]
D.M. Richardson, P. Pyšek, M. Rejmánek, M.G. Barbour, F.D. Panetta, C.J. West, Naturalization and invasion of alien plants: concepts and definitions, Divers. Distrib. 6 (2000) 93–107,.
[2]
L.J.R. Nunes, M.A.M. Raposo, C.I.R. Meireles, C.J.P. Gomes, N.M.C.A. Ribeiro, The Impact of Rural Fires on the Development of Invasive Species: Analysis of a Case Study with Acacia dealbata Link. in Casal do Rei (Seia, Portugal), Environments 8 (2021) 44,.
[3]
C.A. Kull, C.M. Shackleton, P.J. Cunningham, C. Ducatillon, J.-M. Dufour-Dror, K.J. Esler, J.B. Friday, A.C. Gouveia, A.R. Griffin, E. Marchante, S. Midgley, A. Pauchard, H. Rangan, D.M. Richardson, T. Rinaudo, J. Tassin, L.S. Urgenson, G.P. Von Maltitz, R.D. Zenni, M.J. Zylstra, Adoption, use and perception of Australian acacias around the world, Divers. Distrib. (2011) https://agritrop.cirad.fr/560863/(accessed June 12, 2022.
[4]
Decreto-Lei n.o 92/2019 | DRE, (2019). https://dre.pt/dre/detalhe/decreto-lei/92-2019-123025739 (accessed June 12, 2022).
[5]
H. Viana, J. Aranha, Mapping invasive species (Acacia dealbata Link) using ASTER/TERRA and LANDSAT 7 ETM+ imagery, in: 2010.
[6]
F. Martins, C. Alegria, G. Artur, Mapping invasive alien Acacia dealbata Link using ASTER multispectral imagery: a case study in central-eastern of Portugal, For. Syst. 25 (2016) e078,. e078.
[7]
M.A.M. Raposo, C.J. Pinto Gomes, L.J.R. Nunes, Evaluation of Species Invasiveness: A Case Study with Acacia dealbata Link. on the Slopes of Cabeça (Seia-Portugal), Sustainability 13 (2021) 11233,.
[8]
C. Masemola, M.A. Cho, A. Ramoelo, Sentinel-2 time series based optimal features and time window for mapping invasive Australian native Acacia species in KwaZulu Natal, South Africa, Int. J. Appl. Earth Obs. Geoinformation. 93 (2020),.
[9]
B. Spracklen, D.V. Spracklen, Synergistic Use of Sentinel-1 and Sentinel-2 to Map Natural Forest and Acacia Plantation and Stand Ages in North-Central Vietnam, Remote Sens 13 (2021) 185,.
[10]
L. Pádua, J. Vanko, J. Hruška, T. Adão, J.J. Sousa, E. Peres, R. Morais, UAS, sensors, and data processing in agroforestry: a review towards practical applications, Int. J. Remote Sens. 38 (2017) 2349–2391,.
[11]
J. Martínez-Sánchez, L.M. González-de Santos, A. Novo, H. González-Jorge, UAV and satellite imagery applied to alien species mapping in NW Spain, Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 42 (2019) 455–459.
[12]
T. Kattenborn, J. Lopatin, M. Förster, A.C. Braun, F.E. Fassnacht, UAV data as alternative to field sampling to map woody invasive species based on combined Sentinel-1 and Sentinel-2 data, Remote Sens. Environ. 227 (2019) 61–73,.
[13]
J.R.K. Lehmann, T. Prinz, S.R. Ziller, J. Thiele, G. Heringer, J.A.A. Meira-Neto, T.K. Buttschardt, Open-Source Processing and Analysis of Aerial Imagery Acquired with a Low-Cost Unmanned Aerial System to Support Invasive Plant Management, Front, Environ. Sci. (2017) 5. https://www.frontiersin.org/article/10.3389/fenvs.2017.00044 accessed April 212022.
[14]
B. Melville, A. Lucieer, J. Aryal, Classification of Lowland Native Grassland Communities Using Hyperspectral Unmanned Aircraft System (UAS) Imagery in the Tasmanian Midlands, Drones 3 (2019) 5,.
[15]
J. Guerra-Hernández, R.A. Díaz-Varela, J.G. Ávarez-González, P.M. Rodríguez-González, Assessing a novel modelling approach with high resolution UAV imagery for monitoring health status in priority riparian forests, For. Ecosyst. 8 (2021) 61,.
[16]
Jr. J.W. Rouse, R.H. Haas, J.A. Schell, D.W. Deering, Monitoring Vegetation Systems in The Great Plains with ERTS, Goddard Space Flight Cent. 3d ERTS-1 Symp, NASA, 1974, pp. 309–317. https://ntrs.nasa.gov/archive/nasa/casi.ntrs.nasa.gov/19740022614.pdf.
[17]
F. Marzialetti, L. Frate, W. De Simone, A.R. Frattaroli, A.T.R. Acosta, M.L. Carranza, Unmanned Aerial Vehicle (UAV)-Based Mapping of Acacia saligna Invasion in the Mediterranean Coast, Remote Sens 13 (2021) 3361,.
[18]
C. Gonçalves, P. Santana, T. Brandão, M. Guedes, Automatic detection of Acacia longifolia invasive species based on UAV-acquired aerial imagery, Inf. Process. Agric. 9 (2022) 276–287,.
[19]
N.C. de Sá, P. Castro, S. Carvalho, E. Marchante, F.A. López-Núñez, H. Marchante, Mapping the Flowering of an Invasive Plant Using Unmanned Aerial Vehicles: Is There Potential for Biocontrol Monitoring?, Front. Plant Sci. 9 (2018) 293,.
[20]
M.R. Fernandes, F.C. Aguiar, M.J. Martins, N. Rico, M.T. Ferreira, A.C. Correia, Carbon Stock Estimations in a Mediterranean Riparian Forest: A Case Study Combining Field Data and UAV Imagery, Forests. 11 (2020) 376. https://doi.org/10.3390/f11040376.
[21]
Geographic Resources Analysis Support System (GRASS) Software, Version 7.2., Open Source Geospatial Found, GRASS Development Team, 2017, http://grass.osgeo.org.
[22]
J. Inglada, E. Christophe, The Orfeo Toolbox remote sensing image processing software, in: 2009 IEEE Int. Geosci. Remote Sens. Symp., 2009,. IV-733-IV–736.
[23]
J. Lopatin, K. Dolos, T. Kattenborn, F.E. Fassnacht, How canopy shadow affects invasive plant species classification in high spatial resolution remote sensing, Remote Sens. Ecol. Conserv. 5 (2019) 302–317,.
[24]
L. Pádua, A. Matese, S.F. Di Gennaro, R. Morais, E. Peres, J.J. Sousa, Vineyard classification using OBIA on UAV-based RGB and multispectral data: A case study in different wine regions, Comput. Electron. Agric. 196 (2022),.
[25]
L. Pádua, A.M. Antão-Geraldes, J.J. Sousa, M.Â. Rodrigues, V. Oliveira, D. Santos, M.F.P. Miguens, J.P. Castro, Water Hyacinth (Eichhornia crassipes) Detection Using Coarse and High Resolution Multispectral Data, Drones 6 (2022) 47,.
Index Terms
- Acacia dealbata classification from aerial imagery acquired using unmanned aerial vehicles
Index terms have been assigned to the content through auto-classification.
Recommendations
Juvenile tree classification based on hyperspectral image acquired from an unmanned aerial vehicle
Unmanned aerial vehicles for environmental applicationsThe technique of unmanned aerial vehicle UAV offers great advantages in vegetation classification because of its high spatiotemporal resolutions and low cost and risk in field measurements. This study explores the potential of using hyperspectral images ...
Juvenile tree classification based on hyperspectral image acquired from an unmanned aerial vehicle
Unmanned aerial vehicles for environmental applicationsThe technique of unmanned aerial vehicle UAV offers great advantages in vegetation classification because of its high spatiotemporal resolutions and low cost and risk in field measurements. This study explores the potential of using hyperspectral images ...
Juvenile tree classification based on hyperspectral image acquired from an unmanned aerial vehicle
Unmanned aerial vehicles for environmental applicationsThe technique of unmanned aerial vehicle UAV offers great advantages in vegetation classification because of its high spatiotemporal resolutions and low cost and risk in field measurements. This study explores the potential of using hyperspectral images ...
Comments
Information & Contributors
Information
Published In
Copyright © 2023.
Publisher
Elsevier Science Publishers B. V.
Netherlands
Publication History
Published: 01 January 2023
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 28 Jan 2025