[pt] A partir da disponibilização comercial de imagens de alta resolução, modelos 3D de superfícies geradas a partir de imagens aéreas e de satélite tornaram-se uma alternativa mais atraente para aplicações como planejamento de telecomunicações, monitoramento de desastres e planejamento urbano. A exatidão dos modelos 3D da superfície terrestre baseados em pares de imagens estereoscópicas depende da exatidão com que pontos homólogos são localizados em ambas as imagens. Os métodos automáticos de localização de pontos homólogos em imagens digitais baseados em área, combinados com técnicas de crescimento de região, são capazes de produzir uma nuvem densa e exata de pontos homólogos. Entretanto, o processo de crescimento de região pode ser interrompido em regiões da imagem cujo efeito de uma variação abrupta da paralaxe no eixo x aparece de maneira importante. Neste caso, novas sementes devem ser introduzidas, normalmente por um operador humano. A partir dessas novas sementes, o processo será reiniciado. Dependendo do tipo da imagem utilizada e da estrutura 3D da região mapeada, a intervenção humana pode ser considerável. Propõe-se então uma alternativa completamente automatizada no qual se combinam as técnicas do SIFT (Scale Invariant Feature Transform), mínimos quadrados e crescimento de região. Experimentos realizados em pares de imagens aéreas e de satélite cobrindo diversos tipos de terrenos mostraram a eficácia do método proposto, especialmente em regiões com mudanças abruptas de elevação, como fachadas de prédios altos. / [en] After the high resolution images became commercially available, 3D surface models generated from space-born stereo images turned into an attractive alternative for applications such as telecommunication planning, disaster monitoring and urban planning. The accuracy of the 3D models of the earth surface depends on the accuracy of corresponding points located in both images. Area-based automatic image matching combined with a region-growing technique are able to provide a dense and accurate grid of corresponding points. However the region-growing process may stop at image patches where the effect of a sudden change in the x-parallax is important. In such a case new seed points must be provided, usually by human operator. From the additional seed points the region-growing procedure may continue. Depending upon the type of image and the 3D-structure of the mapped area, the human intervention may be considerable. A fully automatic alternative that combines the SIFT (Scale Invariant Feature Transform), least square matching and region-growing technique is proposed in this work. Experiments conducted on stereo pairs of Ikonos and aerial images covering different terrain types have shown the effectiveness of the proposed method especially in locations with abrupt height changes, such as façades of high buildings.

[pt] A classificação e segmentação não-supervisionadas de imagens de sensoriamento remoto são examinadas neste trabalho. A classificação é realizada tomando-se como base o critério de Bayes, que busca minimizar o valor esperado do erro de classificação. Os algoritmos desenvolvidos foram propostos pressupondo-se que a estrutura das classes presentes na imagem podem ser bem modeladas por vetores aleatórios guassianos. Os classificadores convencionais, que só levam em conta a informação dos pixels de forma isolada, forma tratados sob a ótica da quantização vetorial. Em particular, foi proposto um algoritmo de classificação com base na quantização vetorial com restrição de entropia. O desempenho das técnicas de classificação é analisado obsevando-se a discrepância entre classificações, comparando-se as imagens classificadas com imagens referencia e classificando-se imagens sintéticas. A taxa de acerto, entre 80% e 95%. Este bom desempenho dos classificadores é limitado pelo fato de, em suas estruturas, levarem em conta a informação dos pixels de forma isolada. Buscamos, através da classificação de segmentos, incorporar informações de contexto em nossos classificadores. A classificação de segmentos levou a taxas de erros inferiores àquelas alcançadas por classificadores baseados em pixels isolados. Um algoritmo de segmentação, que incorpora ao modelo de classificação por pixels a influencia de sua vizinhança através de uma abordagem markoviana, é apresentado. / [en] Unsupervised classification and segmentation of satellite images are examined in this work. The classification is based on Bayes` criterion, which tries to minimize the expected value of the classification error. The algorthms developed were proposed postulating that the classes in the image are well modeled by gaussian random vectors. Conventional classifiers, which take into account only pixelwise information, were treated as vector quantizers. Specifically, it was proposed a classification algorithm based on entropy constrained vector. The behaviour of the classifiers is examined observing the discrepancy between classifications, comparing classified images with reference-images and classifyng sinthetic images. The percentage of pixels whitch are assigned to the same class as in the reference-images ranged from 80,0% to 95,0%. This good behaviour of the classidiers is limited by the fact that, in theirs structures, are taken into account only isolated pixel information. We have sought, by classifying segments, to introduce contextual information into the classifiers structure. The segments classidiers. A segmentation algorithm, which introduces contextual information into pixelwise classifier by a markovian approach, is presented.

Made available in DSpace on 2014-06-11T19:24:43Z (GMT). No. of bitstreams: 0 Previous issue date: 2008-12-03Bitstream added on 2014-06-13T20:12:53Z : No. of bitstreams: 1 gambarato_rl_me_botfca.pdf: 2023614 bytes, checksum: 79b7ed04822d3f14eaf0d40f43fd3022 (MD5) / Entre as diversas áreas de estudo reunidas sob o denominador comum de processamento digital de imagens, encontra-se a área conhecida como análise de imagens. Este campo de estudos visa ao desenvolvimento de técnicas que permitam extrair informações das imagens, possibilitando às pessoas e aos equipamentos maior poder de análise, resultando em maior suporte às decisões. Neste processo, uma etapa importante é a de segmentação que se refere à divisão da imagem em diversas partes elementares, permitindo a análise destas isoladamente. Este é um processo complexo porque tenta traduzir para o computador um processo cognitivo extremamente sofisticado realizado através da visão humana que realiza agrupamentos baseados na proximidade, similaridade e continuidade das imagens captadas. Tais agrupamentos são utilizados na classificação e análise semântica dos objetos percebidos. Atualmente, o processamento de imagens de satélite é uma ferramenta importante e eficaz no planejamento agrícola e no monitoramento ambiental. Fazendo uso de imagens de satélite e de técnicas de processamento de imagens, o profissional pode analizar a área de interesse e realizar um planejamento prévio sem a necessidade de uma visita ao local. As técnicas de segmentação dividem a imagem em partes homogêneas, identificando, assim, as áreas de cultivo, as áreas de mata, rios e lagos, facilitando o processo de identificação de áreas de interesse do profissional. Diante deste contexto, o presente trabalho visou facilitar a detecção de áreas de cultivo de eucalipto através do desenvolvimento do programa SmartClass, que realiza a composição de imagens, a partir das bandas espectrais isoladas coletadas pelos satélites imageadores, e o processamento para este fim, sendo que as etapas do processamento são realizadas de forma automática. A detecção das áreas de cultivo de eucalipto foi... / Among the various fields of study grouped under the common denominator of digital image processing, is the area known as analysis of images. This field of study aims to develop techniques that allow extracting information from images, enabling the people and equipment increased power of analysis, resulting in greater support for the decisions. In the process, an important step is to target regard to the division of the image in various parts elementary, allowing the analysis of isolation. This is a complex process because the computer tries to translate to an extremely sophisticated cognitive process through the vision that conducts human groupings based on proximity, similarity and continuity of images. Such groupings are used in the classification and semantic analysis of the objects perceived. Currently, the processing of satellite imagery is an important and effective tool in agricultural planning and environmental monitoring. Making use of satellite imagery and techniques of image processing, the operator can analyze the area of interest and conduct a preliminary planning without the need for a site visit. The techniques of image segmentation divided into parts homogeneous, identifying thus the areas under cultivation, the areas of forest, rivers and lakes, facilitating the process of identifying areas of interest to the profession. In this context, the present study to facilitate the detection of areas of cultivation of eucalyptus by developing the SmartClass program, which makes the composition of images, from the individual spectral bands collected by satellite images, and processing for this purpose, with the processing stages are performed automatically. The detection of areas of cultivation of eucalyptus has been successful and the program proved to be easy to use.

Orientador: Célia Regina Lopes Zimback / Banca: Zacarias Xavier de Barros / Banca: Osmar Delmanto Junior / Resumo: Entre as diversas áreas de estudo reunidas sob o denominador comum de processamento digital de imagens, encontra-se a área conhecida como análise de imagens. Este campo de estudos visa ao desenvolvimento de técnicas que permitam extrair informações das imagens, possibilitando às pessoas e aos equipamentos maior poder de análise, resultando em maior suporte às decisões. Neste processo, uma etapa importante é a de segmentação que se refere à divisão da imagem em diversas partes elementares, permitindo a análise destas isoladamente. Este é um processo complexo porque tenta traduzir para o computador um processo cognitivo extremamente sofisticado realizado através da visão humana que realiza agrupamentos baseados na proximidade, similaridade e continuidade das imagens captadas. Tais agrupamentos são utilizados na classificação e análise semântica dos objetos percebidos. Atualmente, o processamento de imagens de satélite é uma ferramenta importante e eficaz no planejamento agrícola e no monitoramento ambiental. Fazendo uso de imagens de satélite e de técnicas de processamento de imagens, o profissional pode analizar a área de interesse e realizar um planejamento prévio sem a necessidade de uma visita ao local. As técnicas de segmentação dividem a imagem em partes homogêneas, identificando, assim, as áreas de cultivo, as áreas de mata, rios e lagos, facilitando o processo de identificação de áreas de interesse do profissional. Diante deste contexto, o presente trabalho visou facilitar a detecção de áreas de cultivo de eucalipto através do desenvolvimento do programa SmartClass, que realiza a composição de imagens, a partir das bandas espectrais isoladas coletadas pelos satélites imageadores, e o processamento para este fim, sendo que as etapas do processamento são realizadas de forma automática. A detecção das áreas de cultivo de eucalipto foi... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Among the various fields of study grouped under the common denominator of digital image processing, is the area known as analysis of images. This field of study aims to develop techniques that allow extracting information from images, enabling the people and equipment increased power of analysis, resulting in greater support for the decisions. In the process, an important step is to target regard to the division of the image in various parts elementary, allowing the analysis of isolation. This is a complex process because the computer tries to translate to an extremely sophisticated cognitive process through the vision that conducts human groupings based on proximity, similarity and continuity of images. Such groupings are used in the classification and semantic analysis of the objects perceived. Currently, the processing of satellite imagery is an important and effective tool in agricultural planning and environmental monitoring. Making use of satellite imagery and techniques of image processing, the operator can analyze the area of interest and conduct a preliminary planning without the need for a site visit. The techniques of image segmentation divided into parts homogeneous, identifying thus the areas under cultivation, the areas of forest, rivers and lakes, facilitating the process of identifying areas of interest to the profession. In this context, the present study to facilitate the detection of areas of cultivation of eucalyptus by developing the SmartClass program, which makes the composition of images, from the individual spectral bands collected by satellite images, and processing for this purpose, with the processing stages are performed automatically. The detection of areas of cultivation of eucalyptus has been successful and the program proved to be easy to use. / Mestre

Conselho Nacional de Desenvolvimento CientÃfico e TecnolÃgico / In order to manage adequately natural resources inside a fragile environment, just like Caatinga, one should know its properties and spatial distribution. This work proposes an approach to classify LANDSAT-5 satellite images. These images, corresponding to a semiarid environment located in Iguatu country, Ceara, Brazil, were classified aiming at detecting the Caatinga biome by two type of classifiers based on machinery learning: Multi Layer Perceptron (MLP) and Support Vector Machine (SVM). The static classifier of Maximum Likelihood was also used as comparison to the other two methods. Agriculture, water, anthropical, herbaceous shrub Caatinga (CHA) and dense high Caatinga (CAD) are the five classes defined for classifying. MLP method tests were carried out changing neurons quantity in the intermediate layer. SVM method tests were carried out changing σ, from Gauss function, and penalization parameter (C). Performance of the tests was analyzed by Global Accuracy, Specific Accuracy and Kappa coefficient. The last one calculated by confusion matrix, which has been generated by comparison of classification data and ground control points GPS georreferenced (true points). MLP method presented best performance for tests in which 12 neurons have been attributed to the intermediate layer resulting in Global Accuracy and Kappa values of 82.14% and 0.76, respectively. On the other hand, SVM method presented best performance for tests carried out with C=1000 and σ=2, resulting in Global Accuracy and Kappa values of 86.03% and 0.77, respectively. The Maximum Likelihood classifier presented 81.2% of its pixels correctly classified (Global Accuracy) and K coefficient value of 0.73. The values of Specific Accuracy, which makes it possible to analyze the performance of each individual class, were above 70% in each class. A total 576 km2 area was classified. Between the two types of Caatinga biome considered, herbaceous shrub Caatinga (CHA) comes to be the most common. Therefore, taking into account experimental results, it is possible to conclude that both SVM and MLP methods, which are based on machine learning, show satisfactory performance for classifying Caatinga biome. / O manejo adequado dos recursos naturais em ambientes frÃgeis, como o da Caatinga, requer o conhecimento de suas propriedades e distribuiÃÃo espacial. Desta forma, o presente trabalho propÃe uma abordagem para a classificaÃÃo de imagens do satÃlite LANDSAT-5, correspondente a uma regiÃo semiÃrida localizada no municÃpio de Iguatu no Estado do CearÃ, objetivando detectar o bioma da Caatinga por meio de dois tipos de classificadores baseados em aprendizado de mÃquina: o mÃtodo baseado em Perceptrons de MÃltiplas Camadas-MLP (do inglÃs Multi Layer Perceptron) e o mÃtodo MÃquinas de Vetores de Suporte-SVM (do inglÃs Support Vector Machine). O classificador estatÃstico da mÃxima verossimilhanÃa, por ser amplamente utilizado na literatura, tambÃm foi aplicado à Ãrea em estudo para que o desempenho dos mÃtodos propostos fosse comparado aos destes. Cinco classes foram definidas para a classificaÃÃo, a saber: agricultura, antropizada, Ãgua, caatinga herbÃcea arbustiva (CHA) e caatinga arbÃrea densa (CAD). Para o mÃtodo MLP, foram realizados testes variando a quantidade de neurÃnios na camada intermediÃria. Jà os testes para o mÃtodo SVM consistiram em variar o parÃmetro σ da funÃÃo gaussiana e o parÃmetro de penalizaÃÃo (C). A eficiÃncia dos mÃtodos foi analisada por meio dos coeficientes de ExatidÃo Global, ExatidÃo EspecÃfica e de Kappa calculados por meio dos dados da matriz de confusÃo. Esta, por sua vez, foi gerada para cada mÃtodo a partir da comparaÃÃo entre a classificaÃÃo e os pontos georreferenciados com aparelho GPS (correspondentes à verdade terrestre). O mÃtodo MLP apresentou melhor desempenho para o teste em que 12 neurÃnios foram atribuÃdos à camada intermediÃria, com valores de ExatidÃo Global e de Kappa de 82,14% e 0,76, respectivamente. Jà o mÃtodo SVM apresentou melhor performance para o teste com C=1000 e σ=2 no qual se obteve valores de 86,03% e 0,77 para os coeficientes de ExatidÃo Global e Kappa, respectivamente. O valor de ExatidÃo Global para o classificador estatÃstico da mÃxima verossimilhanÃa permitiu concluir que 81,2% dos pixels foram classificados corretamente e o coeficiente de Kappa para este mÃtodo foi de 0,73. Os valores dos coeficientes de ExatidÃo EspecÃfica, que proporcionam analisar o desempenho dos mÃtodos em cada classe, foram superiores a 70%. A Ãrea total classificada foi de 576 km2 e, dentre as duas classes consideradas para o bioma Caatinga, a predominante à a do tipo caatinga herbÃcea arbustiva (CHA). Assim, por meio dos resultados experimentais obtidos, pode-se afirmar que os mÃtodos SVM e MLP, baseados em aprendizado de mÃquina, apresentaram desempenho satisfatÃrio para a classificaÃÃo do bioma Caatinga.

No description available.

Please read the abstract in the section 00front of this document / Dissertation (MSc (Botany))--University of Pretoria, 2007. / Plant Science / MSc / unrestricted

No description available.

Background:The background of this research lies in detecting the images from satellites. The recognition of images from satellites has become increasingly importantdue to the vast amount of data that can be obtained from satellites. This thesisaims to develop a method for the recognition of images from satellites using machinelearning techniques. Objective:The main objective of this thesis is a unique approach to recognizingthe data with a CRNN algorithm that involves image recognition in satellite imagesusing machine learning, specifically the CRNN (Convolutional Recurrent Neural Network) architecture. The main task is classifying the images accurately, and this isachieved by utilizing object classification algorithms. The CRNN architecture ischosen because it can effectively extract features from satellite images using Convolutional Blocks and leverage the great memory power of the Long Short-TermMemory (LSTM) networks to connect the extracted features efficiently. The connected features improve the accuracy of our model significantly. Method:The proposed method involves doing a literature review to find currentimage recognition models and then experimentation by training a CRNN, CNN andRNN and then comparing their performance using metrics mentioned in the thesis work. Results:The performance of the proposed method is evaluated using various metrics, including precision, recall, F1 score and inference speed, on a large dataset oflabeled images. The results indicate that high accuracy is achieved in detecting andclassifying objects in satellite images through our approach. The potential utilization of our proposed method can span various applications such as environmentalmonitoring, urban planning, and disaster management. Conclusion:The classification on the satellite images is performed using the 2 datasetsfor ships and cars. The proposed architectures are CRNN, CNN, and RNN. These3 models are compared in order to find the best performing algorithm. The resultsindicate that CRNN has the best accuracy and precision and F1 score and inferencespeed, indicating a strong performance by the CRNN. Keywords: Comparison of CRNN, CNN, and RNN, Image recognition, MachineLearning, Algorithms,You Only Look Once. Version3, Satellite images, Aerial Images, Deep Learning

The human vision system is generally recognized as being superior to all known artificial vision systems. Visual attention, among many processes that are related to human vision, is responsible for identifying relevant regions in a scene for further processing. In most cases, analyzing an entire scene is unnecessary and inevitably time consuming. Hence considering visual attention might be advantageous. A subfield of computer vision where this particular functionality is computationally emulated has been shown to retain high potential in solving real world vision problems effectively. In this monograph, elements of visual attention are explored and algorithms are proposed that exploit such elements in order to enhance image understanding capabilities. Satellite images are given special attention due to their practical relevance, inherent complexity in terms of image contents, and their resolution. Processing such large-size images using visual attention can be very helpful since one can first identify relevant regions and deploy further detailed analysis in those regions only. Bottom-up features, which are directly derived from the scene contents, are at the core of visual attention and help identify salient image regions. In the literature, the use of intensity, orientation and color as dominant features to compute bottom-up attention is ubiquitous. The effects of incorporating an entropy feature on top of the above mentioned ones are also studied. This investigation demonstrates that such integration makes visual attention more sensitive to fine details and hence retains the potential to be exploited in a suitable context. One interesting application of bottom-up attention, which is also examined in this work, is that of image segmentation. Since low salient regions generally correspond to homogenously textured regions in the input image; a model can therefore be learned from a homogenous region and used to group similar textures existing in other image regions. Experimentation demonstrates that the proposed method produces realistic segmentation on satellite images. Top-down attention, on the other hand, is influenced by the observer’s current states such as knowledge, goal, and expectation. It can be exploited to locate target objects depending on various features, and increases search or recognition efficiency by concentrating on the relevant image regions only. This technique is very helpful in processing large images such as satellite images. A novel algorithm for computing top-down attention is proposed which is able to learn and quantify important bottom-up features from a set of training images and enhances such features in a test image in order to localize objects having similar features. An object recognition technique is then deployed that extracts potential target objects from the computed top-down attention map and attempts to recognize them. An object descriptor is formed based on physical appearance and uses both texture and shape information. This combination is shown to be especially useful in the object recognition phase. The proposed texture descriptor is based on Legendre moments computed on local binary patterns, while shape is described using Hu moment invariants. Several tools and techniques such as different types of moments of functions, and combinations of different measures have been applied for the purpose of experimentations. The developed algorithms are generalized, efficient and effective, and have the potential to be deployed for real world problems. A dedicated software testing platform has been designed to facilitate the manipulation of satellite images and support a modular and flexible implementation of computational methods, including various components of visual attention models.