MAPEADO DE LA COBERTURA DEL SUELO DE LOS ALREDEDORES DE UNA PRESA HIDROELÉCTRICA MEDIANTE EL CLASIFICADOR MÁQUINA DE VECTOR DE SOPORTE

Rafael  Walter de Albuquerque; Maurício  George Miguel Jardini; Mariana  Abrantes Giannotti; José Alberto  Quintanilha

doi:10.26512/2236-56562017e40159

Authors

Rafael Walter de Albuquerque Escola Politécnica da Universidade de São Paulo - Departamento de Engenharia de Transportes - Av. Prof. Almeida Prado, Travessa 2, no. 83 - São Paulo - SP - Brasil
Maurício George Miguel Jardini 2FDTE - Fundação para o Desenvolvimento tecnológico da Engenharia, Av. Eusébio Matoso, 1375, 6° Andar, Butantà, São Paulo-SP, CEP: 05423-180
Mariana Abrantes Giannotti Escola Politécnica da Universidade de São Paulo - Geoprocessing Laboratory (LabGeo) - Departamento de Engenharia de Transportes -Av. Prof. Almeida Prado, Travessa 2, no. 83 - São Paulo - SP - Brasil
José Alberto Quintanilha Escola Politécnica da Universidade de São Paulo - Departamento de Engenharia de Transportes - Av. Prof. Almeida Prado, Travessa 2, no. 83 - São Paulo - SP- Brasil

DOI:

https://doi.org/10.26512/2236-56562017e40159

Keywords:

satellite images classification, Support Vector Machine (SVM), Maximum Likelihood (ML), hydroelectric, reservoir, Remote Sensing

Abstract

Las clasificaciones mediante imágenes de satélite son muy útiles para la identificación de la cobertura del suelo y pueden ser utilizadas para evaluar los dominios terrestres. El propósito principal del artículo es mostrar una metodología de mapeado de la cobertura terrestre/uso de suelo - CTUS en las cercanías de una presa hidroeléctrica utilizando imágenes de satélite con alta resolución espacial y dos conocidos algoritmos: la Máquina de Vector de Soporte – MVS y la Máxima Verosimilitud - MV. Ambos clasificadores presentaron una alta precisión y las diferencias no fueron estadísticamente significativas. Los resultados de la clasificación sugieren que el uso del fuego en la zona representa una amenaza para la buena situación ambiental del embalse. Este hallazgo confirma y enfatiza la importancia de las herramientas analizadas en este artículo, lo cual ayuda en la monitorización ambiental.

References

AGRESTI, A. (1996) An Introduction to Categorical Data Analysis. Wiley, New York, N. Y.: 312 p.

BOSSARD, M.; FERANEC, J.; OTAHEL, J. CORINE (2000) Land cover technical guide-Addendum 2000. Technical Report - European Environment Agency, n. 40.

BURGES, C. (1998) A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, v.2, n.2, p. 121-167.

BÜTTNER, G. CORINE (2014) Land Cover and Land Cover Change Products. En; Land Use and Land Cover Mapping in Europe. Springer Netherlands. Pp. 55-74.

CAMPBELL, J. B. (2008) Introduction to Remote Sensing. New York: Guildford Press, 626 p.

CONG, P.; HOWART, P. J. (1990) An assessment of some factors influencing multispectral land-cover classification. Photogrammetric Engineering and Remote Sensing. Bethesda, v. 56, n. 5, p. 597-603.

CONGALTON, R. G., and GREEN, K. (1999) Assessing the Accuracy of Remotely Sensed Data: Principles and Practices. Lewis Publishers, New York: 137p.

CONGALTON, R. G. (2005) Thematic and Positional Accuracy Assessment of Digital Remotely Sensed Data. En: Proceedings of the Seventh Annual Forest Inventory and Analysis Symposium, 2005. USDA Forest Service, 2005, p. 149-154.

DUTTA, S.; SHARMA, S.A.; KHERA, A.P; AJAI, YADAV, M.; HOODA, R.S.; MOTHIKUMAR, K.E.; MANCHANDA, M.L. (1994) Accuracy assessment in cotton acreage estimation using Indian remote sensing satellite data. Journal of Photogrammetry and Remote Sensing, v.49, n.6, p. 21-26.

FOODY, G. M. (2004) Thematic Map Comparison: Evaluating the Statistical Significance of Differences in Classification Accuracy. Photogrammetric Engineering & Remote Sensing, Vol. 70, No. 5, p. 627-633

FOODY, G. M.; MATHUR, A. (2004) Toward Intelligent Training of Supervised Image Classifications: Directing Training Data Aquisition for SVM Classification. Remote Sensing of Environment, v. 93, p. 107-117.

GEOEYE (2010) Geo Eye Product Guide. Dulles - Virginia - United States of America: Printed by GeoEye. Version 2.

GIGANDET, X.; CUADRA, M. B.; POINTET, A.; CAMMOUN, L.; CALOZ, R.; THIRAN, J. (2005) Region-based satellite image classification; method and validation. Image Processing, v. 3. p. 832-835.

GUALTIERI, J. and CROMP, R. (1998) Support vector machines for hyperspectral remote sensing classification. En; AIPR WORKSHOP, 27, 1998, Washington, D. C. Proceedings of SPIE…… Washington D. C.: The International Society for Optical Engineering 3584, October 14 to 16 in 1998, p. 221-232.

HSU, C.W.; CHANG, C.C; LIN, C.J. (2010) A Practical Guide to Support Vector Classification. Department of Computer Science, National Taiwan University, (Technical report).

HUGHES, G. F. (1968) On the mean accuracy of statistical pattern recognizers, IEEE Trans. Inform. Theory, vol. 14, no. 1, pp.55-63.

INSTITUTO BRASILEIRO DE GEOGRAFIA ESTATÍSTICA(2006) Manual Técnico de Uso da Terra. Rio de Janeiro: Manuais Técnicos em Geociências, n.7. 91p.

INSTITUTO BRASILEIRO DE GEOGRAFIA E ESTATÍSTICA - IBGE. (2010). Censo Demográfico - 2010. In: http://ibge.gov.br/cidadesat/painel/economia.php?lang=&codmun=171200&search=tocantins|lajeadolinfograficos:-despesas-e- receitas-orcamentarias-e-pib

IWAI, O. K.; QUINTANILHA, J. A. (2005) Utilização de imagens de satélite como ferramenta de auxilio ao planejamento urbano. Revista de Geografía Norte Grande, v. 34, p. 65-82. JARDINI, M. G. M.;

JARDINI, J.A.; MAGRINI, L. C.; CRISPINO, F.; QUINTANILHA, J. A.; PINFARE, J. C.; SILVA, L. R. (2011) Monitoring system for hydroelectric reservoir using high resolution satellite images. En; IEEE Trondheim Power Tech 2011, Trondheim. Proceedings……. Norway: IEEE Trondheim PowerTech, 2011.

JENSEN, J. R. (1986) Introductory Digital Image Processing. United States of I America:Prentice-Hall,379p.

LILLESAND, T. M.; KEIFER, R. W.; CHIPMAN, J. W. (2008) Remote Sensing and Image Interpretation. Hoboken, NJ John Wiley & Sons, New York, 756 p.

MATHER, P.; KOCH, M. (2011) Computer Processing of Remotely Sensed Images: an Introduction. 4" ed. England: John Wiley & Sons, Chichester, 434p.

MICHALIJOS, M. P.; UBOLDI, J. (2013) Propuesta metodológica para la evaluación de áreas afetadas por incendios mediante el uso de imágenes satelitales (Sierra de la Ventana, Argentina Revista de Geografia Norte Grande, v. 56, p. 223-234.

OOMMEN, T.; MISRA, D.; TWARAKAVI, N. K. C.; PRAKASH, A.; SAHOO, B.; BANDOPADH YAY, S. (2008) An Objective Analysis of Support Vector Machine Based Classification for Remote Sensing. Math Geosci, v. 40, p. 409-424.

PAL, M.; MATHER, P. (2004) Assessment of the effectiveness of support vector machines for hyperspectral data. Future Generation Computer Systems, v. 20, n. 7, p. 1215-1225

PAL, M. & MATHER, P.M. (2005) Support vector machines for classification in remote sensing. International Journal of Remote Sensing, v. 26, n. S, p. 1007-1011.

RICHARDS, J.A.; JIA, X. (1999) Remote Sensing Digital Image Analysis: An Introduction, 3rd ed. Ed. Springer-Verlag, New York: p. 273-274

SCHOWENGERDT, R. A. (2007) Remote Sensing - Models and Methods for Image Processing, 3rd ed. United States of America; Academic Press, 515p.

SKOLE, D.L, CHOMENTOWSKI, W.H., SALAS, W.A., NOBRE, A.D. (1994) Physical and Human Dimensions of Deforestation in Amadzonia. Bioscience, v. 44, n. 5, p. 314-322.

SONG, M.; CIVCO, D. (2004) Road Extraction Using SVM and Image Segmentation. Photogrammetric Engineering & Remote Sensing, v. 70, n. 12, p. 1365-1371

STEIN, A.; VAN DER MEER, F.; GORTE, B. (1999) Spatial Statistics for Remote Sensing. Netherlands: Kluwer Academic Publishers, 284p.

TZOTSOSA.; ARGILAS D.(2008) Support Vector Machine Classification for Object- Based Image Analysis. In: BLASCHKE T., LANG S., HAY G.J. (org.) Object-Based Image Analysis. Lecture Notes in Geoinformation and Cartography. Ed. Springer, Berlin, Heidelberg: p. p63-677. Disponível em: <https://link.springer.com/chapt er/10.1007/978-3-540-77058-9 36> Acesso em 04 de setembro de 2017.

WARNER, T. A.; FOODY, G. M.; NELLIS, M. D. (2009) The SAGE Handbook of Remote Sensin g. London: SAGE Publications Ltd, 504p.