Land use image classification through optimum-path forest clustering

Land use classification has been paramount in the last years, since we can identify illegal land use and also to monitor deforesting areas. Although one can find several research works in the literature that address this problem, we propose here the land use recognition by means of Optimum-Path Forest Clustering (OPF), which has never been applied to this context up to date. Experiments among Optimum-Path Forest, Mean Shift and K-Means demonstrated the robustness of OPF for automatic land use classification of images obtained by CBERS-2B and Ikonos-2 satellites. © 2011 IEEE.

Fototriangulação em bloco de imagens orbitais com modelos rigorosos baseados em pontos e retas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Diagnóstico de ambiência na sub-bacia do Rio das Pedras, Municipio de Itatinga – SP, visando o planejamento sócio conservacionista

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Geoprocessamento aplicado no diagnóstico físico-ambiental do Ribeirão Descalvado, Botucatu-SP

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Ação de forças gravitacionais e não gravitacionais sobre o movimento orbital de satélites artificiais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Caracterização do meio físico em bacias hidrográficas com suportes de sensoriamento remoto e geoprocessamento

Pós-graduação em Geografia - IGCE

Orientação exterior de imagens orbitais usando modelos rigorosos com feições retas

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Diagnóstico integrado de síntese de Bacia do Rio Capivara, Botucatu (SP)

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Classificação de cobertura do solo utilizando árvores de decisão e sensoriamento remoto

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Seleção de áreas potenciais para implantação da zona de processamento e exportação de Fernandópolis - SP utilizando geotecnologia

The implementation of an Export and Processing Zone (ZEPs) brings several benefits to the local, state and federal economy, but often, only socioeconomic factors are considered, apart from several other factors that should be analyzed, such as the environment. In this context of industrialization and the struggle for sustainable development, this work propose to incorporate the environmental variable in the decision process for establishing industrial areas, in particular, the ZPE in the city of Fernandópolis, São Paulo state, Brazil, by examining several physical and environmental factors such as slope intervals, geological features, pedological factors and land use. Developed using a multicriteria analysis, a model has been elaborated, where these factors have received a proportional value according with their importance, supported by a GIS tool (Geographical Information System) and remote sensing products, such as images from CBERS satellite and SRTM radar, showing the suited areas for industrial activities, considering environmental conditions. This model may assist to take better decision about the ZPE implementation area and to reduce the negative environmental impacts that would result of poorly planned locations

Caracterização e mapeamento da cultura da cana-de-açúcar no município de Rio Claro (SP) por meio de técnicas de sensoriamento remoto e sistemas de informações geográficas

This paper discusses about the use of remote sensing image and processing digital images tools for mapping and assessing the effect on the biomass of the culture of sugar cane in the city of Rio Claro. We used satellite images from CBERS in the passages of 19/04/2009 and 23/09/08, which correspond respectively to the stages where the sugar cane appeared in growing and adult pre-harvest stage. In these images, we applied procedures of digital processing, as the application of the procedures for extending linear contrast, radiometric normalization, Normalized Vegetation Index (NDVI) and pixel by pixel classification by ISOSEG through of the software SPRING. As a result we obtained mapping of the distribution and development stages of the culture of sugar cane in the city of Rio Claro and the mapping of the existing biomass of this culture, showing that the method used to assess the relative effect on biomass in culture of sugar cane was efficient, and that images of low-medium resolution are not the most suitable for the mapping of this culture

Diagnóstico de conflitos em áreas de preservação permanente na bacia do Rio Capivara - Botucatu (SP)

The permanent preservation areas (PPA) established by Brazilian law are there to protect the natural environment. With the expansion of space occupied by man and development of economic activities in these areas were engaged in conflicts characterized PPA, where the use is other than the natural vegetation. According to these paradigms work aims to raise these conflict areas in the River Basin Capivara, Botucatu (SP) with the help of GIS Ilwis 3.4, topographic maps of IBGE and satellite images CBERS 2B. The map was generated from PPA in the GIS by distance calculation in relation to drainage, springs and break line on Cuesta de Botucatu. The classes of land use and natural vegetation were determined by interpretation of satellite images and field visits to check their veracity. With the cutting of the map of land use and natural vegetation in relation to PPA unit it was determined that the total 44,63% PPA is in conflict occupied by pasture, forest plantation, orange, annual crops, farms and irrigated rice project in lowland. This diagnostic characterizes the degradation of the environment and highlights the need to harmonize the economic and urban development with the preservation of the environment to ensure sustainability of the region.

Discriminação de classes de cobertura vegetal utilizando técnicas de classificação digital de imagens de sensoriamento remoto

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.

Diagnóstico de potenciliade das unidades ambientais na bacia do Rio Capivara, Botucatu - SP

This work has the objective to elaborate the potentialities of the farming expand diagnosis of the Capivara River Hydrographic basin, in the Botucatu – SP municipal district, to obtain an interpretation of the system actual situation through the historical trajectory and possible evolution with the assistance of the SIG Ilwis 3.4 and orbital images CBERS 2B, in the pancromatics bands, obtained in 12/07/2008. The potentialities of the farming expand diagnosis was obtained through the physical mean modeling, of the farming expand presents in the studied environment and shows possible line actions to minimize the impacts e reach a sustainable development to the region. The Capivara river basin presents more than 70% of your areas occupied by the anthropic expanding, with the extensive farming predominance, forestall planting, orange and sugar cane. In the potentiality diagnostic analyses notes the good quality of the basin to the farming expand, except the region comprehended by the Botucatu Cuesta and the meadows area. The basin until has a good environmental quality and this diagnosis must serve for a start point to the realization of the territorial ordination as quick as possible to the environment conditions finds remains the same, granting the recovery capability.

O REORDENAMENTO DA CALHA DO RIO JEQUITINHONHA NO CONTROLE DE INUNDAÇÃO NA CIDADE DE BELMONTE NA BAHIA, BRASIL

O núcleo urbano de Belmonte localizado no litoral Sul do estado da Bahia se desenvolveu em 1764, a partir do porto fluvial no rio Jequitinhonha. As cheias do rio eram muito comuns entre os meses de dezembro e fevereiro e o risco de inundações sempre foi por muito tempo um problema para os gestores municipais, diante da ameaça à população com perda de residências e de parte da cidade pelas enxurradas. Desta maneira este trabalho teve por objetivo mapear as transformações ocorridas no canal do rio Jequitinhonha após a intervenção na sua calha, com a abertura e desvio do canal, em 1989. Adotou-se para o mapeamento as fotografias aéreas verticais de 1960, 1965 e 1974 na escala de 1: 25.000 e a imagem de satélite CBERS – 2, de 2005 com o trabalho de campo realizado entre 2005 e 2007. O desvio do canal do rio contribuiu para que Belmonte ficasse protegida das cheias dos anos subseqüentes. Por outro lado, alterou a morfologia do canal do rio, com diferentes formas deposicionais, com o adensamento de ilhas fluviais a oeste da cidade e com o assoreamento e estreitamento do antigo leito do rio, transformado em canal secundário, colmatado.