Comparative analysis of methods applied in vegetation cover delimitation using Landsat 8 images
PDF-en

Keywords

Image classification
NDVI
Principal Component Analysis
Similarity
Bands composition

How to Cite

DUTRA, D. J.; ELMIRO, M. A. T.; GARCIA, R. A. . Comparative analysis of methods applied in vegetation cover delimitation using Landsat 8 images. Sociedade & Natureza, [S. l.], v. 32, p. 699–710, 2020. DOI: 10.14393/SN-v32-2020-56139. Disponível em: https://seer.ufu.br/index.php/sociedadenatureza/article/view/56139. Acesso em: 30 nov. 2022.

Abstract

There is a wide availability of methods and techniques for classification of data from remote sensing images. However, one of the biggest challenges is to identify whether the applied method is really effective for the thematic mapping the terrain features. Thus, the aim of this work was to provide a comparative analysis involving data classification methods for mapping forest cover using orbital images from the Landsat 8 satellite. The applied method consisted of pre-processing the images, calculating the NDVI image, performing the infrared image composition and principal component analysis (PCA). The maximum likelihood classification method (MAXVER) was used to delimit the vegetation cover applied to the three types of databases. To validate the classification results, field data, Kappa analysis and pixel-by-pixel analysis were applied. The results pointed out that the NDVI method showed the least general similarity regarding to the reference data used for validation from the MAPBIOMAS project. It was possible to identify similar results in relation to the delimitation of forest cover. The results allowed identifying that the several methodologies available for classification of vegetation are of great value for the thematic mapping of forest resources. In addition, we conclude that the PCA showed the best capacity for delimiting the vegetation cover in the study region, closely followed by infrared composition, and the NDVI was the least accurate.

https://doi.org/10.14393/SN-v32-2020-56139
PDF-en

References

ABDU, H. A. Classification accuracy and trend assessments of land cover- land use changes from principal components of land satellite images. International Journal of Remote Sensing, v. 40, n. 4, p. 1275–1300, 2019. https://doi.org/10.1080/01431161.2018.1524587

BAN, Y.; GONG, P.; GIRI, C. Global land cover mapping using Earth observation satellite data: Recent progresses and challenges. ISPRS Journal of Photogrammetry and Remote Sensing, v. 103, p. 1–6, 2015. https://doi.org/10.1016/j.isprsjprs.2015.01.001

BARBOSA, S. G. et al. Geotechnology in the analysis of forest fragments in northern Mato Grosso, Brazil. Scientific Reports, v. 8, n. 1, p. 1–7, 2018. https://doi.org/10.1038/s41598-018-22311-y

BRAGA, T. G. M. et al. A dinâmica de alterações ambientais com base nas transições, permanências e vulnerabilidades: o caso da bacia hidrográfica do rio Moju, Amazônia. Interciencia, v. 44, n. 3, p. 178–186, 2019.

CAMARA, G. et al. Spring : Integrating Remote Sensing and Gis By Data Modelling. Science, v. 20, n. 3, p. 395–403, 1996. https://doi.org/10.1016/0097-8493(96)00008-8.

CHANDER, G.; COAN, M. J.; SCARAMUZZA, P. L. Evaluation and comparison of the IRS-P6 and the landsat sensors. IEEE Transactions on Geoscience and Remote Sensing, v. 46, n. 1, p. 209–221, 2008. https://doi.org/10.1109/TGRS.2007.907426

CHIANG, J. L. Knowledge-based principal component analysis for image fusion. Applied Mathematics and Information Sciences, v. 8, n. 1 L, p. 223–230, 2014. http://dx.doi.org/10.12785/amis/081L28

CHUTIA, D. et al. Hyperspectral Remote Sensing Classifications: A Perspective Survey. Transactions in GIS, v. 20, n. 4, p. 463–490, 2016. https://doi.org/10.1111/tgis.12164

CONGALTON, R. G.; GREEN, K. Assessing the Accuracy of remote sensed data: principle and pratices. New York: Lewis Publishers, 1999.

CONGEDO, L. Semi-Automatic Classification Plugin Documentation Release 4.8.0.1. QGIS, 2016. v. 1.

CŔOSTA, A. P. et al. Targeting key alteration minerals in epithermal deposits in Patagonia, Argentina, using ASTER imagery and principal component analysis. International Journal of Remote Sensing, v. 24, n. 21, p. 4233–4240, 2003. https://doi.org/10.1080/0143116031000152291

CRUZ, A. P. et al. Inter-relação entre paisagem, organização florístico-estrutural edemografia. Ciência Florestal, v. 28, n. 1, p. 67–79, 2018.

FERREIRA JÚNIOR, J. I. Análise comparativa dos métodos de classificação da vegetação NDVI e análise por componentes principais em uma imagem rapideye. Cadernos do leste, v. 15, n. 15, p. 66–85, 2015.

FOODY, G. M. Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy. Photogrammetric Engineering and Remote Sensing, v. 70, n. 5, p. 627–633, 2004. https://doi.org/10.14358/PERS.70.5.627

FORMAGGIO, A. R., SANCHES, I. D. Sensoriamento remoto em agricultura. 1o ed. São José dos Campos: Oficina de Textos, 2017.

HAGEN, A. Fuzzy set approach to assessing similarity of categorical maps. International Journal of Geographical Information. n. June, p. 37–41, 2003. http://dx.doi.org/10.1080/13658810210157822

HAYES, D. J.; SADER, S. A. Comparison of change-detection techniques for monitoring tropical forest clearing and vegetation regrowth in a time series. Photogrammetric Engineering and Remote Sensing, v. 67, n. 9, p. 1067–1075, 2001.

HERCULANO, R. N. Aplicação dos métodos de classificação de imagem ndvi e acp para o mapeamento de floresta nativa da apa do benfica no município de Itaúna/MG: uma análise comparativa. Cadernos do leste, v. 16, n. 16, p. 98–113, 2016.

JOLLIFFE, I. Principal component analysis. Berlin. Springer Berlin Heidelberg, 2011.

MAPBIOMAS. Coleção MAPBIOMAS. Available in: <https://mapbiomas.org/download>. Acessed: June 15, 2019.

LEROUX, L. et al. Land cover mapping using sentinel-2 images and the semi-automatic classification plugin: a northern burkina faso case study. QGIS and Applications in Agriculture and Forest, v. 2, p. 119–151, 2018. https://doi.org/10.1002/9781119457107.ch4

LYONS, M. B. et al. A comparison of resampling methods for remote sensing classification and accuracy assessment. Remote Sensing of Environment, v. 208, n. September 2017, p. 145–153, 2018. https://doi.org/10.1016/j.rse.2018.02.026

QGIS. QGIS Development. QGIS Geographic Information System. Open Source Geoespatial Fundation Project, 2019

MATASCI, G. et al. Semisupervised transfer component analysis for domain adaptation in remote sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, v. 53, n. 7, p. 3550–3564, 2015. https://doi.org/10.1109/TGRS.2014.2377785

MELO, E. T.; SALES, M. C. L.; OLIVEIRA, J. G. B. Aplicação do índice de vegetação por diferença normalizada (NDVI) para análise da degradação ambiental da microbacia hidrográfica do Riacho dosCavalos, Crateús-CE. Ra´E Ga, v. 23, p. 520–533, 2011.

MISRA, G. et al. Mapping specific crop: A multi sensor temporal approach. International Geoscience and Remote Sensing Symposium (IGARSS), n. July, p. 3034–3037, 2012. https://doi.org/10.1109/IGARSS.2012.6350786

NOBLE, B.; DANIEL, J. W. Álgebra linear aplicada. Rio de Janeiro: Prentice-Hall do Brasil, 1986.

NOVO, E. M. L. M. Sensoriamento remoto: Princípios e aplicações. 4. ed. São Paulo: Blucher, 2010.

PONZONI, F. J.; SHIMABUKURO, Y. E.; KUPLICH, T. M. Sensoriamento remoto da vegetação. São José dos Campos: Oficina de Textos, 2015.

PONZONI, F. J.; SHIMABUKURO, Y. E. Sensoriamento Remoto no Estudo da Vegetação. São José dos Campos: Ed. Parêntese, 2010.

ROUSE, J. W. et al. Monitoring vegetation systems in the great plains with ERTS. Third Earth Resources Technology Satellite (ERTS) symposium, v. 1, p. 309–317, 1973.

ROUSE, J. W. et al. Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation. Type II Report for the period (Sptember 1973 - March 1973). College Station, Texas: 1974.

SABINS JR, F. F. Remote sensing--principles and interpretation. 1987.

SHARMA, V.; CHAUDHRY, S. Vegetation composition and plant diversity in mining disturbed tropical thorn forest of Asola-Bhatti wildlife sanctuary, northern India. Taiwania, v. 63, n. 3, p. 267–280, 2018. https://doi.org/10.6165/tai.2018.63.267

SILVA, C. V. J.; COSTA, O. B.; MATRICARDI, E. A. T. Detecção de cicatrizes de fogo na vegetação cerrado do Distrito Federal entre 1999 a 2011. Revista Brasileira de Cartografia, v. 69/4, p. 687–699, 2017.

TSAI, F.; LIN, E. K.; YOSHINO, K. Spectrally segmented principal component analysis of hyperspectral imagery for mapping invasive plant species. International Journal of Remote Sensing, v. 28, n. 5, p. 1023–1039, 2007. https://doi.org/10.1080/01431160600887706

VURAL, A.; CORUMLUOGLU, O.; ASRI, I. Exploring gördes zeolite sites by feature oriented principle component analysis of Landsat images. Caspian Journal of Environmental Sciences, v. 14, n. 4, p. 285–298, 2016.

WEI, W. et al. Study on remote sensing image vegetation classification method based on decision tree classifier. Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018, p. 2292–2297, 2019. https://doi.org/10.1109/SSCI.2018.8628721

WHITE, R; ENGELEN, G. High-resolution integrated modelling of the spatial dynamics of urban and regional system. Computers, environment and urban system, v. 24, p. 383–400, 2000.

XUE, J.; SU, B. Significant remote sensing vegetation indices: A review of developments and applications. Journal of Sensors, v. 2017, 2017. https://doi.org/10.1155/2017/1353691

Authors hold the Copyright for articles published in this journal, and the journal holds the right for first publication. Because they appear in a public access journal, articles are licensed under Creative Commons Attribution (BY), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...