EVALUATION OF EFFICIENCY FOR REMOTE SENSING IMAGE CLASSIFIERS WITH VARIATION IN THE SPATIAL RESOLUTION
DOI:
https://doi.org/10.18764/2446-6549.e202204Keywords:
Kappa Index, Image Classification, Thematic Quality, Comparison of IndicesAbstract
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
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Direitos autorais InterEspaço: Revista de Geografia e InterdisciplinaridadeEste obra está licenciado com uma Licença Creative Commons Atribuição-NãoComercial-SemDerivações 4.0 Internacional.
Os conteúdos publicados são de inteira e exclusiva responsabilidade de seus autores, ainda que reservado aos editores o direito de proceder a ajustes textuais e de adequação às normas da publicação.