Land-use and vegetation-cover mapping of an indigenous land area in the state of Mato Grosso (Brazil) based on spectral linear mixing model,segmentation and region classification |
| |
Authors: | Fernando Shinji Kawakubo Rubia Gomes Morato Carmen Lucia Midaglia Maria Lucia Cereda Gomide Ailton Luchiari |
| |
Institution: | 1. Department of Geography , Universidade de S?o Paulo, Cidade Universit?ria , S?o Paulo, Brazil fsk@usp.br;3. Department of Geography , Universidade de S?o Paulo, Cidade Universit?ria , S?o Paulo, Brazil |
| |
Abstract: | A spectral linear-mixing model using Landsat ETM+ imagery was undertaken to estimate fraction images of green vegetation, soil and shade in an indigenous land area in the state of Mato Grosso in the central-western region of Brazil. The fraction images were used to classify different types of land use and vegetation cover. The fraction images were classified by the following two methods: (a) application of a segmentation based on the region-growing technique; and (b) grouping of the regions segmented using the per-region unsupervised classifier named ISOSEG. Adopting a 75% threshold, ISOSEG generated 44 clusters that were grouped into eight land-use and vegetation-cover classes. The mapping achieved an average accuracy of 83%, showing that the methodology is efficient in mapping areas of great land-use and vegetation-cover diversity, such as that found in the Brazilian cerrado (savanna). |
| |
Keywords: | vegetation cerrado Landsat ETM+ fraction images segmentation classification by region |
|
|