177 resultados para classificação supervisionada

em Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho"


Relevância:

100.00% 100.00%

Publicador:

Resumo:

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Relevância:

70.00% 70.00%

Publicador:

Resumo:

The aim of this work is to discriminate vegetation classes throught remote sensing images from the satellite CBERS-2, related to winter and summer seasons in the Campos Gerais region Paraná State, Brazil. The vegetation cover of the region presents different kinds of vegetations: summer and winter cultures, reforestation areas, natural areas and pasture. Supervised classification techniques like Maximum Likelihood Classifier (MLC) and Decision Tree were evaluated, considering a set of attributes from images, composed by bands of the CCD sensor (1, 2, 3, 4), vegetation indices (CTVI, DVI, GEMI, NDVI, SR, SAVI, TVI), mixture models (soil, shadow, vegetation) and the two first main components. The evaluation of the classifications accuracy was made using the classification error matrix and the kappa coefficient. It was defined a high discriminatory level during the classes definition, in order to allow separation of different kinds of winter and summer crops. The classification accuracy by decision tree was 94.5% and the kappa coefficient was 0.9389 for the scene 157/128. For the scene 158/127, the values were 88% and 0.8667, respectively. The classification accuracy by MLC was 84.86% and the kappa coefficient was 0.8099 for the scene 157/128. For the scene 158/127, the values were 77.90% and 0.7476, respectively. The results showed a better performance of the Decision Tree classifier than MLC, especially to the classes related to cultivated crops, indicating the use of the Decision Tree classifier to the vegetation cover mapping including different kinds of crops.

Relevância:

70.00% 70.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

60.00% 60.00%

Publicador:

Resumo:

Este trabalho teve o objetivo de avaliar a evolução do uso da terra no município de Botucatu - SP, no período de três anos, considerando-se seis tipos de cobertura vegetal (cana-de-açúcar, reflorestamento, floresta nativa, pastagem, cítrus e outros), tendo como base as imagens de satélite Landsat 5, bandas 3; 4 e 5, órbita 220, ponto 76, quadrante A, passagem de 8 de junho de 1999. O Sistema de Informações Geográficas - IDRISI for Windows 3.2, foi utilizado para as análises. Os resultados mostraram que esse programa foi eficiente para auxiliar na identificação e mapeamento das áreas com uso da terra, facilitando o processamento dos dados. As imagens de satélite TM/LANDSAT 5 forneceram um excelente banco de dados para a classificação supervisionada. O município não vem sendo preservado ambientalmente, pois apresenta-se coberto com menos de 20% de florestas nativas, mínimo exigido por lei. As áreas de pastagem, principal componente da paisagem do município, confirmam a vocação da região para a pecuária.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

60.00% 60.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

60.00% 60.00%

Publicador:

Resumo:

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Relevância:

60.00% 60.00%

Publicador:

Resumo:

The objective of this research was to conduct an analysis of multitemporal landscape Ipanema National Forest, located in the municipalities of Iperó, Capela do Alto and Araçoiaba da Serra – São Paulo estate, Brazil, considering the scenarios of 1965, 2007 and 2011. The multitemporal analysis, using aerial photographs and satellite images, contributed to the contextualization and spatialization of the evolution of the landscape area. Through analysis interpretation of the images, performed by means of supervised classification were obtained thematic maps of the area, equivalent to approximately 53 km2. Through geoprocessing techniques, especially Geographic Information Systems, it was possible the integration and manipulation of data, both spatial and statistical, allowing integrated analysis of data from the entire area of the National Forest of Ipanema. As the main result, we found that the Ipanema National Forest is in landscape evolution positive, with those 46 years examined the increase of native heavy foliage areas. Increasing from 7.1 km2 of the total area of dense vegetation in 1965 to 35.9 km2 in 2011. Overall, it was possible to realize a scenario landscape quite optimistic about the evolution of forest conservation area

Relevância:

60.00% 60.00%

Publicador:

Resumo:

The main objective of this study was to perform a temporal analysis of land use and cover of Itirapina – São Paulo estate, Brazil, for 1962, 2000 and 2008 scenarios, indicating the rate of change in native vegetation and contextualizing its modifications. Based on photointerpretation performed by supervised classification using the method of Bhattacharya, the thematic classes were mapped and characterized in an area equivalent to 56400 hectares. Using remote sensing technologies and geographic information systems, was structured and implemented a georeferenced and relational database, allowing the analysis of the size of the area occupied. The results showed that the expansion of cultivation of cane sugar and reforestation in the past 45 years has been conditioned the fragmentation of natural vegetation cover in the city, which fell by 34793 ha (61,7%) in 1962 to 9765,2 ha (17,3%) in 2008, with the loss of 25027,8 hectares.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Relevância:

60.00% 60.00%

Publicador:

Resumo:

This study aimed to recognize the significant temporal changes in land use between 1984 and 2008 in Barra Bonita City/ SP and to analyze the conflicts of land use in permanent preservation areas (PPA) with reference to the Forest Code and Resolution N. 303/2002 of CONAMA. The GIS Idrisi Andes 5.0 – geographic information system was used and the images were processed by LANDSAT TM5. Maps of land use were obtained by Maxver supervised classification and showed that in 1984 the area occupied by sugar cane crop was about 10.50 ha (70%) in 1984 and 10.90 ha in 2008. In analysis of conflicts about land use in permanent preservation areas showed that in 24 years the sugar-cane crops increased 3.6% on PPA. The occupation was represented by adequate forest of 279.25 ha (31.5% of total) in 1984. In 2008, the sugar-cane crop was the biggest conflict in PPA occupying 357.9 ha and 11.4% corresponds to areas in preparation for use. This year, 59.5% of total PPA is at odds with environmental legislation.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

O grande desafio da população mundial é a conservação ambiental, pois as Áreas de Preservação Permanentes, que têm papel vital dentro de uma microbacia, por serem responsáveis pela manutenção, preservação e conservação dos ecossistemas ali existentes. O presente trabalho visou analisar os conflitos de uso do solo em áreas de preservação permanentes (APPs) da microbacia do Alto Capivara - Botucatu (SP) através do uso de Sistema de Informações Geográficas e de imagem de satélite digital. A área com 4551,19ha, situa-se entre as coordenadas geográficas: 22o 51’ 57” a 22o 57’ 55” de latitude S e 48o 21’ 58” a 48o 26’ 38” de longitude WGR. O mapa de uso do solo de 2006 foi obtido a partir da classificação supervisionada em imagem de satélite digital de 23/10/2006. Na identificação digital dos alvos foram utilizadas as chaves de interpretação para imagens e as áreas foram determinadas através do software SIG – IDRISI. Os conflitos de uso nas áreas de preservação permanente foram analisados ao longo da rede de drenagem e das nascentes, conforme itens dos artigos 2º e 3º da Resolução nº 303 do CONAMA. A área de APP discriminada ao longo da rede de drenagem foi de 416,5ha (9,15%) . No entanto, 201,15ha da área de APP está ocupada com pastagem (48,3%), reflorestamento (1,23%) e 0,48% por área urbana de forma inadequada (conflito). Portanto, quase 50% de área de APP vem sendo parcialmente utilizada adequadamente.