EVALUATION OF EFFICIENCY FOR REMOTE SENSING IMAGE CLASSIFIERS WITH VARIATION IN THE SPATIAL RESOLUTION

Authors

DOI:

https://doi.org/10.18764/2446-6549.e202204

Keywords:

Kappa Index, Image Classification, Thematic Quality, Comparison of Indices

Abstract

Understanding the characteristics of terrestrial features in order to conduct decision-making that causes the least negative impact on the environment is an initial and fundamental step. This
research aimed to evaluate the performance of five image classification algorithms for the mapping of land use and land cover classes in two regions with different characteristics from Belo Horizonte
- MG. For the classification process, 2 images from orthophoto images with an original spatial resolution of 0.20 m were used, and based on these, 12 new images were generated through the pixel resampling process. To test the statistical significance of the classifications, the Global Accuracy, Kappa Index, and Pearson's Correlation Coefficient (r) were used. The results obtained pointed to the need to approach the interpretation of several authors, as well as other thematic quality indexes, in addition to the need to create a methodology in the future that considers the positional quality and the theme together in the final evaluation of the maps. 

Downloads

Download data is not yet available.

Author Biographies

Warlen Librelon de Oliveira, Universidade Federal de Minas Gerais

Mestre em Engenharia Mecânica pela Universidade Federal de Minas Gerais – UFMG. Graduado em Engenharia Ambiental pelo Centro Universitário Newton Paiva.

Bárbara Roberta Morais, Universidade Federal de Minas Gerais

Mestra em Análise e Modelagem de Sistemas Ambientais – UFMG. Graduada em Agronomia pelo Instituto Federal de Educação, Ciência e Tecnologia de Minas Gerais – IFMG/Campus Bambuí.

Marcelo Antônio Nero, Universidade Federal de Minas Gerais

Pós-Doutor pela Escola Politécnica da Universidade de São Paulo – USP. Doutor em Engenharia de Transportes pela Universidade de São Paulo – USP. Mestre em Engenharia de Transporte pela Universidade de São Paulo – USP. Graduado em Cartografia pela Universidade Estadual Paulista Júlio de Mesquita Filho – UNESP. Professor do Departamento de Cartografia do Instituto de Geociências – UFMG.

Published

2022-10-28

How to Cite

OLIVEIRA, Warlen Librelon de; MORAIS, Bárbara Roberta; NERO, Marcelo Antônio.
EVALUATION OF EFFICIENCY FOR REMOTE SENSING IMAGE CLASSIFIERS WITH VARIATION IN THE SPATIAL RESOLUTION
. InterEspaço: Revista de Geografia e Interdisciplinaridade, p. e202204, 28 Oct. 2022 Disponível em: https://cajapio.ufma.br/index.php/interespaco/article/view/20208. Acesso em: 28 sep. 2024.

Issue

Section

Artigos