Classificador neural híbrido para imagens obtidas por sensoriamento remoto

Remote sensing is one technology of extreme importance, allowing capture of data from the Earth's surface that are used with various purposes, including, environmental monitoring, tracking usage of natural resources, geological prospecting and monitoring of disasters. One of the main applications of remote sensing is the generation of thematic maps and subsequent survey of areas from images generated by orbital or sub-orbital sensors. Pattern classification methods are used in the implementation of computational routines to automate this activity. Artificial neural networks present themselves as viable alternatives to traditional statistical classifiers, mainly for applications whose data show high dimensionality as those from hyperspectral sensors. This work main goal is to develop a classiffier based on neural networks radial basis function and Growing Neural Gas, which presents some advantages over using individual neural networks. The main idea is to use Growing Neural Gas's incremental characteristics to determine the radial basis function network's quantity and choice of centers in order to obtain a highly effective classiffier. To demonstrate the performance of the classiffier three studies case are presented along with the results.

Segmentação fuzzy de imagens coloridas com características texturais: uma aplicação a rochas sedimentares

Image segmentation is the process of labeling pixels on di erent objects, an important step in many image processing systems. This work proposes a clustering method for the segmentation of color digital images with textural features. This is done by reducing the dimensionality of histograms of color images and using the Skew Divergence to calculate the fuzzy a nity functions. This approach is appropriate for segmenting images that have colorful textural features such as geological, dermoscopic and other natural images, as images containing mountains, grass or forests. Furthermore, experimental results of colored texture clustering using images of aquifers' sedimentary porous rocks are presented and analyzed in terms of precision to verify its e ectiveness.

Cartografia temporal e análise geoambiental da dinâmica da foz do Rio Piranhas-Açu, regiao de Macau-RN, com base em imagens Landast 5-MT

This work embraces the application of Landsat 5-TM digital images, comprising August 2 1989 and September 22 1998, for temporal mapping and geoenvironmental analysis of the dynamic of Piranhas-Açu river mouth, situated in the Macau (RN) region. After treatment using several digital processing techniques (e.g. colour composition in RGB, ratio of bands, principal component analysis, index methods, among others), it was possible to generate several image products and multitemporal maps of the coastal morphodynamics of the studied area. Using the image products it was possible the identification and characterization of the principal elements of interest (vegetation, soil, geology and water) in the surface of the studied area, associating the spectral characteristics of these elements to that presented by the image products resulting of the digital processing. Thus, it was possible to define different types of soils: Amd, AQd6, SK1 and LVe4; vegetation grouping: open arboreal-shrubby caatinga, closed arborealshrubby caatinga, closed arboreal caatinga, mangrove vegetation, dune vegetation and areas predominately constituted by juremas; geological units: quaternary units beach sediments, sand banks, dune flats, barrier island, mobile dunes, fixed dunes, alluvium, tidal and inundation flats, and sandy facies of the Potengi Formation; tertiary-quaternary units Barreiras Formation grouped to the clayey facies of the Potengi Formation, Macau Formation grouped to the sediments of the Tibau Formation; Cretaceous units Jandaíra Formation; moreover it was to identify the sea/land limit, shallow submersed areas and suspended sediments. The multitemporal maps of the coastal morphodynamics allowed the identification and a semi-quantitative evoluation of regions which were submitted to erosive and constructive processes in the last decade. This semi-quantitative evoluation in association with an geoenvironmental characterization of the studied area are important data to the elaboration of actions that may minimize the possible/probable impacts caused by the implantation of the Polo Gas/Sal and to the monitoring of areas explorated by the petroleum and salt industries

Caracterização macro, meso e microscópica das estruturas frágeis do corpo arenítico conglomerático da região de Santana do Acaraú (CE) e seu embasamento circundante

The structural framework of the sedimentary basins usually plays an important role in oil prospects and reservoirs. Geometry, interconectivity and density of the brittle features developed during basin evolution could change the permo-porous character of the rocks involved in generation, migration and entrapment of fluid flow. Once the structural characterization of the reservois using only sub-surface data is not an easy task, many studies are focused in analogous outcrops trying to understand the main processes by which brittle tectonic is archieved. In the Santana do Acaraú region (Ceará state, NE Brazil) a pack of conglomeratic sandstone (here named CAC) has its geometry controlled mainly by NE trending faults, interpreted as related to reactivation of a precambrian Sobral Pedro II Lineament (LSP-II). Geological mapping of the CAC showed a major NE-SW trending synform developed before its complete lithification during a dextral transpression. This region was then selected to be studied in details in order of constrain the cretaceous deformation and so help the understanding the deformation of the basins along the brazilian equatorial margin. In order to characterize the brittle deformation in different scales, I study some attributes of the fractures and faults such as orientation, density, kinematic, opening, etc., through scanlines in satellite images, outcrops and thin sections. The study of the satellite images showed three main directions of the macrostructures, N-S, NE-SW and E-W. Two of theses features (N-S and E-W) are in aggreement with previous geophysical data. A bimodal pattern of the lineaments in the CAC´s basement rocks has been evidenciated by the NE and NW sets of structures obtained in the meso and microscale data. Besides the main dextral transpression two others later events, developed when the sediments were complety lithified, were recognized in the area. The interplay among theses events is responsible for the compartimentation of the CAC in several blocks along within some structural elements display diferents orientations. Based on the variation in the S0 orientation, the CAC can be subdivided in several domains. Dispite of the variations in orientations of the fractures/faults in the diferents domains, theses features, in the meso and microscopic scale, are concentrated in two sets (based on their trend) in all domains which show similar orientation of the S0 surface. Thus the S0 orientation was used to group the domains in three major sets: i) The first one is that where S0 is E-W oriented: the fractures are oriented mainly NE with the development of a secondary NW trending; ii) S0 trending NE: the fractures are concentrated mainly along the trend NW with a secondary concentration along the NE trend; iii) The third set, where S0 is NS the main fractures are NE and the secondary concentration is NW. Another analized parameter was the fault/fracture length. This attribute was studied in diferent scales trying to detect the upscale relationship. A terrain digital model (TDM) was built with the brittlel elements supperposed. This model enhanced a 3D visualization of the area as well as the spatial distribution of the fault/fractures. Finally, I believe that a better undertanding of the brittle tectonic affecting both CAC and its nearby basement will help the future interpretations of the tectonic envolved in the development of the sedimentary basins of the brazilian equatorial margin and their oil reservoirs and prospects, as for instance the Xaréu field in the Ceará basin, which subsurface data could be correlated with the surface ones