Please use this identifier to cite or link to this item: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1132498
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPEREIRA, P. R. M.
dc.contributor.authorCOSTA, F. W. D.
dc.contributor.authorBOLFE, E. L.
dc.contributor.authorMACARRINGE, L.
dc.contributor.authorBOTELHO, A. C.
dc.date.accessioned2021-06-23T02:20:46Z-
dc.date.available2021-06-23T02:20:46Z-
dc.date.created2021-06-22
dc.date.issued2021
dc.identifier.citationISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V. V-3-2021, p. 167-173, 2021.
dc.identifier.urihttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1132498-
dc.descriptionAbstract. One of the main applications of satellite images is the characterization of terrestrial coverage, that from the use of classification techniques, allows the monitoring of spatial transformations of the terrestrial surface, this process being directly associated with the potential of classifiers to differentiate the most diverse data present in the images, a fundamental aspect for the use of remote sensing data. This article evaluates the performance of different classification algorithms in the mapping classes of land use and land cover in medium resolution images from the Landsat 8 program, the test area of this test corresponds to the Municipality of Tasso Fragoso (State Maranhão - Brazil), stands out for a typical vegetation cover of the Cerrado Biome, presents similar spectral patterns that induce high difficulty of class differentiation automatically. In this paper, were analyzed the machine learning algorithms C5.0 and Random Forest in comparison to traditional classification algorithms being the Minimum Distance and the Spectral Angle Mapper. The best results were generated by Random Forest with 90% accuracy and Kappa of 0.861, followed by the C5.0 algorithm. Traditional algorithms, on the other hand, presented a lower precision rate with global accuracy, not exceeding 75% of accuracy and Kappa varying between 0.507 and 0.627. The accuracy of the producer showed that all the algorithms, in major or minor tendency presented difficulties in to differentiate the areas, with rates of mistakes varying between 25 and 75%, being the main, the confusion with pastoral areas.
dc.language.isoeng
dc.rightsopenAccesseng
dc.subjectCobertura da terra
dc.subjectClassificação digital
dc.subjectBioma cerrado
dc.subjectLandsat 8
dc.subjectAlgoritmos de aprendizado de máquina
dc.subjectRandom Forest
dc.subjectDigital Classification
dc.subjectPerformance Indexes
dc.subjectCerrado Biome
dc.subjectMaranhão State
dc.subjectMachine learning algorithms
dc.subjectClassification algorithms
dc.titleComparison of classification algorithms of images for the mapping of the land covering in Tasso Fragoso municipality, Brazil.
dc.typeArtigo de periódico
dc.subject.thesagroUso da Terra
dc.subject.nalthesaurusLand cover
dc.subject.nalthesaurusLand use
dc.description.notesThis research is funded by the São Paulo Research Foundation (FAPESP), grant number 2019/26222-6.eng
riaa.ainfo.id1132498
riaa.ainfo.lastupdate2021-06-22
dc.identifier.doihttps://doi.org/10.5194/isprs-annals-V-3-2021-167-2021
dc.contributor.institutionUnicamp; Unesp; EDSON LUIS BOLFE, Unicamp, CNPTIA; Unicamp; Unicamp.
Appears in Collections:Artigo em periódico indexado (CNPTIA)

Files in This Item:
File Description SizeFormat 
PL-Comparison-classification-algorithm-ISPRS-2021.pdf1,53 MBAdobe PDFThumbnail
View/Open

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace