996 resultados para Processamento de imagens - Técnicas digitais


Relevância:

40.00% 40.00%

Publicador:

Resumo:

Com o advento dos sensores hiperespectrais se tornou possível em sensoriamento remoto, uma serie de diferentes aplicações. Uma delas, é a possibilidade de se discriminar classes com comportamentos espectrais quase idênticas. Porém um dos principais problemas encontrados quando se trabalha com dados de alta dimensionalidade, é a dificuldade em estimar os inúmeros parâmetros que se fazem necessários. Em situações reais é comum não se ter disponibilidade de tamanho de amostra suficiente, por exemplo, para se estimar a matriz de covariâncias de forma confiável. O sensor AVIRIS fornece uma riqueza de informações sobre os alvos, são 224 bandas cobrindo o espectro eletromagnético, o que permite a observação do comportamento espectral dos alvos de forma muito detalhada. No entanto surge a dificuldade de se contar com uma amostra suficiente para se estimar a matriz de covariâncias de uma determinada classe quando trabalhamos com dados do sensor AVIRIS, para se ter uma idéia é preciso estimar 25.200 parâmetros somente na matriz de covariâncias, o que necessitaria de uma amostra praticamente impraticável na realidade. Surge então a necessidade de se buscar formas de redução da dimensionalidade, sem que haja perda significativa de informação. Esse tipo de problema vem sendo alvo de inúmeros estudos na comunidade acadêmica internacional. Em nosso trabalho pretendemos sugerir a redução da dimensionalidade através do uso de uma ferramenta da geoestatística denominada semivariograma. Investigaremos se os parâmetros calculados para determinadas partições do transecto de bandas do sensor AVIRIS são capazes de gerar valores médios distintos para classes com comportamentos espectrais muito semelhantes, o que por sua vez, facilitaria a classificação/discriminação destas classes.

Relevância:

40.00% 40.00%

Publicador:

Resumo:

o monitoramento da expansão das áreas urbanas e a análise da sua interação com o meio físico têm sido um grande desafio para os técnicos de planejamento urbano. No Brasil, em especial, dada a velocidade com que o fenômeno se processa e graças a um crescimento desordenado das cidades nas últimas décadas, esses estudos, que envolvem um elevado número de informações, tem exigido decisões e diagnósticos urbanos cada vez mais rápidos. Esta dissertação propõe uma metodologia para o planejamento racional do uso do solo urbano através do emprego integrado de tecnologias recentes como Sistema de Informações Geográficas (SIG), Modelagem Numérica do Terreno (MNT) e Sensoriamento Remoto através de imagens orbitais. Para isso, são implementados no SIG desenvolvido pelo INPE dados provenientes de cartas topográficas, de mapas temáticos do meio físico e de imagens orbitais LANSAT/TM da região estudada. A partir desses dados iniciais são geradas, também num SIG, outras informações com objetivo de estudar a evolução da área urbana, identificar áreas com suscetibilidade preliminar à erosão laminar, áreas com restrição ao uso urbano e áreas de eventos perigosos e riscos. o trabalho apresenta inicialmente uma revisão bibliográfica sobre a aplicação de Sensoriamento Remoto, Modelagem Numérica do Terreno (MNT) e Sistema de Informações Geográficas (SIG) em estudos urbanos. Segue-se a conceituação e aspectos teóricos dessas três ferramentas básicas utilizadas. A metodologia propriamente dita traz os planos de informações originais e as suas respectivas fontes de informações, os processos de classificação de imagens digitais empregados e os modelos de cruzamentos desenvolvidos para um SIG. A área teste escolhida é a sub-bacia do Arroio Feijó, localizada na região metropolitana de Porto Alegre, na porção centro-leste do Estado do Rio Grande do Sul. A região é caracterizada por uma elevada densidade populacional, pela presença de áreas inundáveis e pela ocorrência de processos eroslVOS. Os resultados mostram que a metodologia proposta é adequada e eficiente para agilizar as atividades de planejamento urbano, subsidiando a elaboração de Planos Diretores de Desenvolvimento Integrado e orientando o crescimento das cidades para regiões mais favoráveis. Além disso, contribui para a prevenção de parcela dos riscos e problemas geotécnicos relacionados ao meio físico nas áreas urbanas.

Relevância:

40.00% 40.00%

Publicador:

Resumo:

O exame de sangue é um dos procedimentos de análises clínicos mais utilizados pelo largo espectro de anomalias que consegue detectar. A contagem de células de sangue, objeto deste trabalho, é um destes exames. A contagem manual é feita por um operador que examina ao microscópio, com ampliação adequada, uma amostra eventualmente tratada ou colorida. Ainda hoje há casos em que contagem manual é necessária mas é cada vez mais freqüente a utilização da contagem automática, feita através de citômetro de fluxo. Esta dissertação aborda um sistema de contagem de células do sangue por processamento digital de imagens e pode ser automático ou semi-automático. O projeto é fruto de uma parceria entre o LaPSIDELET e o HCPA. Deste projeto surgiu o SAIMO (Sistema de Aquisição de Imagens para uso em Microscopia Óptica). No estágio atual o SAIMO possui algumas limitações no controle de posicionamento e no campo de visão limitado. O controle de posicionamento atual fica a cargo do operador: não há informação sobre as imagens já adquiridas, podendo ocorrer sobreposição. Devido à limitação do campo de visão, várias aquisições devem ser feitas para se obter o número mínimo de células recomendado. Além disso, há um possível aumento de erro de contagem associado às imagens parciais de célula presentes nas bordas das imagens. Este trabalho tem como proposta solucionar o problema de controle de posicionamento das aquisições, com a localização da cena durante a captura da imagem. Além disso, é proposta uma técnica de composição de mosaico com as imagens adquiridas, reduzindo os problemas causados pelo campo de visão limitado. Também são propostos métodos de préprocessamento apropriados às imagens adquiridas, que proporcionam a redução do tempo das tarefas subseqüentes. O método de validação das localizações verifica se as coordenadas encontradas por este processo são consistentes. Os resultados obtidos mostraram que o método é rápido na localização e eficiente na composição do mosaico, podendo ser utilizado como parte de um sistema de contagem de células por processamento digital de imagens.

Relevância:

40.00% 40.00%

Publicador:

Resumo:

This work aims to develop a methodology for analysis of images using overlapping, which assists in identification of microstructural features in areas of titanium, which may be associated with its biological response. That way, surfaces of titanium heat treated for 08 (eight) different ways have been subjected to a test culture of cells. It was a relationship between the grain, texture and shape of grains of surface of titanium (attacked) trying to relate to the process of proliferation and adhesion. We used an open source software for cell counting adhered to the surface of titanium. The juxtaposition of images before and after cell culture was obtained with the aid of micro-hardness of impressions made on the surface of samples. From this image where there is overlap, it is possible to study a possible relationship between cell growth with microstructural characteristics of the surface of titanium. This methodology was efficient to describe a set of procedures that are useful in the analysis of surfaces of titanium subjected to a culture of cells

Relevância:

40.00% 40.00%

Publicador:

Resumo:

The skin cancer is the most common of all cancers and the increase of its incidence must, in part, caused by the behavior of the people in relation to the exposition to the sun. In Brazil, the non-melanoma skin cancer is the most incident in the majority of the regions. The dermatoscopy and videodermatoscopy are the main types of examinations for the diagnosis of dermatological illnesses of the skin. The field that involves the use of computational tools to help or follow medical diagnosis in dermatological injuries is seen as very recent. Some methods had been proposed for automatic classification of pathology of the skin using images. The present work has the objective to present a new intelligent methodology for analysis and classification of skin cancer images, based on the techniques of digital processing of images for extraction of color characteristics, forms and texture, using Wavelet Packet Transform (WPT) and learning techniques called Support Vector Machine (SVM). The Wavelet Packet Transform is applied for extraction of texture characteristics in the images. The WPT consists of a set of base functions that represents the image in different bands of frequency, each one with distinct resolutions corresponding to each scale. Moreover, the characteristics of color of the injury are also computed that are dependants of a visual context, influenced for the existing colors in its surround, and the attributes of form through the Fourier describers. The Support Vector Machine is used for the classification task, which is based on the minimization principles of the structural risk, coming from the statistical learning theory. The SVM has the objective to construct optimum hyperplanes that represent the separation between classes. The generated hyperplane is determined by a subset of the classes, called support vectors. For the used database in this work, the results had revealed a good performance getting a global rightness of 92,73% for melanoma, and 86% for non-melanoma and benign injuries. The extracted describers and the SVM classifier became a method capable to recognize and to classify the analyzed skin injuries

Relevância:

40.00% 40.00%

Publicador:

Resumo:

Visual Odometry is the process that estimates camera position and orientation based solely on images and in features (projections of visual landmarks present in the scene) extraced from them. With the increasing advance of Computer Vision algorithms and computer processing power, the subarea known as Structure from Motion (SFM) started to supply mathematical tools composing localization systems for robotics and Augmented Reality applications, in contrast with its initial purpose of being used in inherently offline solutions aiming 3D reconstruction and image based modelling. In that way, this work proposes a pipeline to obtain relative position featuring a previously calibrated camera as positional sensor and based entirely on models and algorithms from SFM. Techniques usually applied in camera localization systems such as Kalman filters and particle filters are not used, making unnecessary additional information like probabilistic models for camera state transition. Experiments assessing both 3D reconstruction quality and camera position estimated by the system were performed, in which image sequences captured in reallistic scenarios were processed and compared to localization data gathered from a mobile robotic platform

Relevância:

40.00% 40.00%

Publicador:

Resumo:

In Simultaneous Localization and Mapping (SLAM - Simultaneous Localization and Mapping), a robot placed in an unknown location in any environment must be able to create a perspective of this environment (a map) and is situated in the same simultaneously, using only information captured by the robot s sensors and control signals known. Recently, driven by the advance of computing power, work in this area have proposed to use video camera as a sensor and it came so Visual SLAM. This has several approaches and the vast majority of them work basically extracting features of the environment, calculating the necessary correspondence and through these estimate the required parameters. This work presented a monocular visual SLAM system that uses direct image registration to calculate the image reprojection error and optimization methods that minimize this error and thus obtain the parameters for the robot pose and map of the environment directly from the pixels of the images. Thus the steps of extracting and matching features are not needed, enabling our system works well in environments where traditional approaches have difficulty. Moreover, when addressing the problem of SLAM as proposed in this work we avoid a very common problem in traditional approaches, known as error propagation. Worrying about the high computational cost of this approach have been tested several types of optimization methods in order to find a good balance between good estimates and processing time. The results presented in this work show the success of this system in different environments

Relevância:

40.00% 40.00%

Publicador:

Resumo:

Several methods of mobile robot navigation request the mensuration of robot position and orientation in its workspace. In the wheeled mobile robot case, techniques based on odometry allow to determine the robot localization by the integration of incremental displacements of its wheels. However, this technique is subject to errors that accumulate with the distance traveled by the robot, making unfeasible its exclusive use. Other methods are based on the detection of natural or artificial landmarks present in the environment and whose location is known. This technique doesnt generate cumulative errors, but it can request a larger processing time than the methods based on odometry. Thus, many methods make use of both techniques, in such a way that the odometry errors are periodically corrected through mensurations obtained from landmarks. Accordding to this approach, this work proposes a hybrid localization system for wheeled mobile robots in indoor environments based on odometry and natural landmarks. The landmarks are straight lines de.ned by the junctions in environments floor, forming a bi-dimensional grid. The landmark detection from digital images is perfomed through the Hough transform. Heuristics are associated with that transform to allow its application in real time. To reduce the search time of landmarks, we propose to map odometry errors in an area of the captured image that possesses high probability of containing the sought mark

Relevância:

40.00% 40.00%

Publicador:

Resumo:

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

Relevância:

40.00% 40.00%

Publicador:

Resumo:

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Relevância:

40.00% 40.00%

Publicador:

Resumo:

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

Relevância:

40.00% 40.00%

Publicador:

Resumo:

This research presents a methodology for prediction of building shadows cast on urban roads existing on high-resolution aerial imagery. Shadow elements can be used in the modeling of contextual information, whose use has become more and more common in image analysis complex processes. The proposed methodology consists in three sequential steps. First, the building roof contours are manually extracted from an intensity image generated by the transformation of a digital elevation model (DEM) obtained from airborne laser scanning data. In similarly, the roadside contours are extracted, now from the radiometric information of the laser scanning data. Second, the roof contour polygons are projected onto the adjacent roads by using the parallel projection straight lines, whose directions are computed from the solar ephemeris, which depends on the aerial image acquisition time. Finally, parts of shadow polygons that are free from building perspective obstructions are determined, given rise to new shadow polygons. The results obtained in the experimental evaluation of the methodology showed that the method works properly, since it allowed the prediction of shadow in high-resolution imagery with high accuracy and reliability.

Relevância:

40.00% 40.00%

Publicador:

Resumo:

In this work, we propose a multi agent system for digital image steganalysis, based on the poliginic bees model. Such approach aims to solve the problem of automatic steganalysis for digital media, with a case study on digital images. The system architecture was designed not only to detect if a file is suspicious of covering a hidden message, as well to extract the hidden message or information regarding it. Several experiments were performed whose results confirm a substantial enhancement (from 67% to 82% success rate) by using the multi-agent approach, fact not observed in traditional systems. An ongoing application using the technique is the detection of anomalies in digital data produced by sensors that capture brain emissions in little animals. The detection of such anomalies can be used to prove theories and evidences of imagery completion during sleep provided by the brain in visual cortex areas