Made available in DSpace on 2015-03-13T17:08:24Z (GMT). No. of bitstreams: 1 RenataCLA.pdf: 1406363 bytes, checksum: c23d0993b7ed86a192397c6e7f6d9580 (MD5) Previous issue date: 2004-10-14 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / Objective to establish a methodology for the oil spill monitoring on the sea surface, located at the Submerged Exploration Area of the Polo Region of Guamar?, in the State of Rio Grande do Norte, using orbital images of Synthetic Aperture Radar (SAR integrated with meteoceanographycs products. This methodology was applied in the following stages: (1) the creation of a base map of the Exploration Area; (2) the processing of NOAA/AVHRR and ERS-2 images for generation of meteoceanographycs products; (3) the processing of RADARSAT-1 images for monitoring of oil spills; (4) the integration of RADARSAT-1 images with NOAA/AVHRR and ERS-2 image products; and (5) the structuring of a data base. The Integration of RADARSAT-1 image of the Potiguar Basin of day 21.05.99 with the base map of the Exploration Area of the Polo Region of Guamar? for the identification of the probable sources of the oil spots, was used successfully in the detention of the probable spot of oil detected next to the exit to the submarine emissary in the Exploration Area of the Polo Region of Guamar?. To support the integration of RADARSAT-1 images with NOAA/AVHRR and ERS-2 image products, a methodology was developed for the classification of oil spills identified by RADARSAT-1 images. For this, the following algorithms of classification not supervised were tested: K-means, Fuzzy k-means and Isodata. These algorithms are part of the PCI Geomatics software, which was used for the filtering of RADARSAT-1 images. For validation of the results, the oil spills submitted to the unsupervised classification were compared to the results of the Semivariogram Textural Classifier (STC). The mentioned classifier was developed especially for oil spill classification purposes and requires PCI software for the whole processing of RADARSAT-1 images. After all, the results of the classifications were analyzed through Visual Analysis; Calculation of Proportionality of Largeness and Analysis Statistics. Amongst the three algorithms of classifications tested, it was noted that there were no significant alterations in relation to the spills classified with the STC, in all of the analyses taken into consideration. Therefore, considering all the procedures, it has been shown that the described methodology can be successfully applied using the unsupervised classifiers tested, resulting in a decrease of time in the identification and classification processing of oil spills, if compared with the utilization of the STC classifier / Objetiva o estabelecimento de uma metodologia para monitoramento de derramamento de ?leo no mar, na ?rea de Explora??o Submersa do P?lo de Guamar?, no Estado do Rio Grande do Norte, utilizando imagens orbitais de radares de abertura sint?tica (SAR) integradas aos produtos meteoceanogr?ficos. A aplica??o do modelo metodol?gico foi composto pelas seguintes etapas: (1) a cria??o de um mapa base da ?rea de Explora??o; (2) o processamento de imagens NOAA/AVHRR e ERS-2 para gera??o de produtos meteoceanogr?ficos; (3) o processamento de imagens RADARSAT-1 para monitoramento das manchas de ?leo; (4) a integra??o da imagem RADARSAT-1 com os produtos de imagens NOAA/AVHRR e ERS-2; e (5) a estrutura??o de um banco de dados. A Integra??o da imagem RADARSAT-1 da Bacia Potiguar do dia 21.05.99 com o mapa base da ?rea de Explora??o do P?lo de Guamar? para a identifica??o das prov?veis fontes das manchas de ?leo, foi utilizada com sucesso na detec??o da prov?vel mancha de ?leo detectada pr?xima ? sa?da do emiss?rio submarino na ?rea de Explora??o do P?lo de Guamar?. Para subsidiar a integra??o da imagem RADARSAT-1 com os produtos de imagens NOAA/AVHRR e ERS-2, desenvolveu-se uma metodologia para a classifica??o das manchas de ?leo identificadas em imagens RADARSAT-1. Nesta metodologia, testou-se os seguintes algor?tmos de classifica??o n?o-supervisionada: K-means, Fuzzy k-means e Isodata, que s?o parte integrante do software PCI Geomatics, o qual foi utilizado para a filtragem das imagens RADARSAT-1. Para a avalia??o dos resultados, as manchas de ?leo submetidas ? classifica??o n?o-supervisionada foram comparadas aos resultados do Classificador Textural por Semivariograma (STC), o qual foi desenvolvido especificamente para esta finalidade e requer a utiliza??o do software PCI Geomatics para efetuar parte do processamento das imagens RADARSAT-1. Por fim, os resultados das classifica??es foram analisados atrav?s de An?lise Visual; C?lculo de Proporcionalidade de Grandezas e An?lise Estat?stica. Dentre os tr?s algoritmos de classifica??o testados n?o houve significantes altera??es em rela??o as manchas classificadas pelo STC, em nenhuma das an?lises efetuadas. Os procedimentos adotados demonstraram que a metodologia descrita aqui poder? ser aplicada com sucesso, utilizando os classificadores n?o supervisionados testados, o que acarretaria em diminui??o de tempo no processo de identifica??o e classifica??o de manchas de ?leo, em compara??o ? utiliza??o do classificador STC

Made available in DSpace on 2014-12-17T14:56:21Z (GMT). No. of bitstreams: 1 DaniloLS.pdf: 2499617 bytes, checksum: 328b5ce6d56f5a92a61ad220565411c7 (MD5) Previous issue date: 2006-07-24 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / Oil spill on the sea, accidental or not, generates enormous negative consequences for the affected area. The damages are ambient and economic, mainly with the proximity of these spots of preservation areas and/or coastal zones. The development of automatic techniques for identification of oil spots on the sea surface, captured through Radar images, assist in a complete monitoring of the oceans and seas. However spots of different origins can be visualized in this type of imaging, which is a very difficult task. The system proposed in this work, based on techniques of digital image processing and artificial neural network, has the objective to identify the analyzed spot and to discern between oil and other generating phenomena of spot. Tests in functional blocks that compose the proposed system allow the implementation of different algorithms, as well as its detailed and prompt analysis. The algorithms of digital image processing (speckle filtering and gradient), as well as classifier algorithms (Multilayer Perceptron, Radial Basis Function, Support Vector Machine and Committe Machine) are presented and commented.The final performance of the system, with different kind of classifiers, is presented by ROC curve. The true positive rates are considered agreed with the literature about oil slick detection through SAR images presents / Derramamentos de ?leo sobre o mar, mesmo que acidentais, geram enormes conseq??ncias negativas para a ?rea afetada. Os preju?zos s?o ambientais e econ?micos, principalmente com a proximidade dessas manchas de ?reas de preserva??o e/ou zonas costeiras. O desenvolvimento de t?cnicas autom?ticas para a identifica??o de manchas de ?leo sobre a superf?cie marinha, capturadas atrav?s de imagens de Radar, auxiliam num completo monitoramento dos oceanos e mares. Contudo, manchas de diferentes origens podem ser visualizadas nesse tipo de produ??o de imagem, tornando o monitoramento dif?cil. O sistema proposto neste trabalho, baseado em t?cnicas de processamento digital de imagens e redes neurais artificiais, tem o objetivo de identificar a mancha analisada e discernir entre ?leo e os demais fen?menos geradores de mancha. Testes nos blocos funcionais que comp?em o sistema proposto permitem a implementa??o de diferentes algoritmos, assim como sua an?lise detalhada e pontual. Os algoritmos que tratam do processamento digital de imagem (filtragem do ru?do speckle e gradiente), assim como o de classifica??o (Perceptron de M?ltiplas Camadas, rede de fun??o de Base Radial, M?quina de Vetor de Suporte e M?quina de comit?) s?o apresentados e comentados.O desempenho final do sistema, com diferentes tipos de classificadores, ? apresentado atrav?s da curva ROC. As taxas de acertos s?o consideradas condizentes com o que a literatura de detec??o de manchas de ?leo na superf?cie oce?nica atrav?s de imagens de SAR apresenta