Esta tese investiga uma abordagem não supervisionada para o problema da detecção de mudanças em imagens multiespectrais e multitemporais de sensoriamento remoto empregando Support Vector Machines (SVM) com o uso dos kernels polinomial e RBF e de uma nova métrica de pertinência de pixels. A proposta metodológica está baseada na diferença das imagens-fração produzidas para cada data. Em imagens de cenas naturais essa diferença nas frações de solo e vegetação tendem a apresentar uma distribuição simétrica próxima à origem. Essa caracteristica pode ser usada para modelar as distribuições normais multivariadas das classes mudança e não-mudança. O algoritmo Expectation-Maximization (EM) é implementado com a finalidade de estimar os parâmetros (vetor de médias, matriz de covariância e probabilidade a priori) associados a essas duas distribuições. A seguir, amostras aleatórias e normalmente distribuidas são extraídas dessas distribuições e rotuladas segundo sua pertinência em uma das classes. Essas amostras são então usadas no treinamento do classificador SVM. A partir desta classificação é estimada uma nova métrica de pertinência de pixels. A metodologia proposta realiza testes com o uso de conjuntos de dados multitemporais de imagens multiespectrais Landsat-TM que cobrem a mesma cena em duas datas diferentes. A métrica de pertinência proposta é validada através de amostras de teste controladas obtidas a partir da técnica Change Vetor Analysis, além disso, os resultados de pertinência obtidos para a imagem original com essa nova métrica são comparados aos resultados de pertinência obtidos para a mesma imagem pela métrica proposta em (Zanotta, 2010). Baseado nos resultados apresentados neste trabalho que mostram que a métrica para determinação de pertinência é válida e também apresenta resultados compatíveis com outra técnica de pertinência publicada na literatura e considerando que para obter esses resultados utilizou-se poucas amostras de treinamento, espera-se que essa métrica deva apresentar melhores resultados que os que seriam apresentados com classificadores paramétricos quando aplicado a imagens multitemporais e hiperespectrais. / This thesis investigates a unsupervised approach to the problem of change detection in multispectral and multitemporal remote sensing images using Support Vector Machines (SVM) with the use of polynomial and RBF kernels and a new metric of pertinence of pixels. The methodology is based on the difference-fraction images produced for each date. In images of natural scenes. This difference in the fractions of bare soil and vegetation tend to have a symmetrical distribution close to the origin. This feature can be used to model the multivariate normal distributions of the classes change and no-change. The Expectation- Maximization algorithm (EM) is implemented in order to estimate the parameters (mean vector, covariance matrix and a priori probability) associated with these two distributions. Then random and normally distributed samples are extracted from these distributions and labeled according to their pertinence to the classes. These samples are then used in the training of SVM classifier. From this classification is estimated a new metric of pertinence of pixel. The proposed methodology performs tests using multitemporal data sets of multispectral Landsat-TM images that cover the same scene at two different dates. The proposed metric of pertinence is validated via controlled test samples obtained from Change Vector Analysis technique. In addition, the results obtained at the original image with the new metric are compared to the results obtained at the same image applying the pertinence metric proposed in (Zanotta, 2010). Based on the results presented here showing that the metric of pertinence is valid, and also provides results consistent with other published in the relevant technical literature, and considering that to obtain these results was used a few training samples, it is expected that the metric proposed should present better results than those that would be presented with parametric classifiers when applied to multitemporal and hyperspectral images.

Chilling events are infrequent but important disturbances in subtropical Florida. When temperatures drop to near freezing, significant mortality often accrues in mangrove forests. Chilling events play a role in maintaining structural diversity in mangrove forests, and in limiting mangrove poleward distribution. I examined the spatio-temporal distribution of chilling events in mangrove forests of southern Biscayne Bay by using Landsat TM5 images since 1989. Damage was usually confined to dwarf mangrove forest, especially when chilling temperatures were moderate and short in duration. However, damage from extended and severe freezes such as in January 2010 impacted larger trees as well. Recovery is gradual, often extending over multiple years, depending on disturbance severity. Plant communities respond to repeated chilling with increase in the dominance of black mangrove. In the absence of chilling events, patch level dynamics might lead to prevalence of a more homogenous tall red mangrove canopy in these wetlands. Such a trajectory may result with increasing temperatures expected under current global climate change scenarios

abstract: While discrete emotions like joy, anger, disgust etc. are quite popular, continuous emotion dimensions like arousal and valence are gaining popularity within the research community due to an increase in the availability of datasets annotated with these emotions. Unlike the discrete emotions, continuous emotions allow modeling of subtle and complex affect dimensions but are difficult to predict. Dimension reduction techniques form the core of emotion recognition systems and help create a new feature space that is more helpful in predicting emotions. But these techniques do not necessarily guarantee a better predictive capability as most of them are unsupervised, especially in regression learning. In emotion recognition literature, supervised dimension reduction techniques have not been explored much and in this work a solution is provided through probabilistic topic models. Topic models provide a strong probabilistic framework to embed new learning paradigms and modalities. In this thesis, the graphical structure of Latent Dirichlet Allocation has been explored and new models tuned to emotion recognition and change detection have been built. In this work, it has been shown that the double mixture structure of topic models helps 1) to visualize feature patterns, and 2) to project features onto a topic simplex that is more predictive of human emotions, when compared to popular techniques like PCA and KernelPCA. Traditionally, topic models have been used on quantized features but in this work, a continuous topic model called the Dirichlet Gaussian Mixture model has been proposed. Evaluation of DGMM has shown that while modeling videos, performance of LDA models can be replicated even without quantizing the features. Until now, topic models have not been explored in a supervised context of video analysis and thus a Regularized supervised topic model (RSLDA) that models video and audio features is introduced. RSLDA learning algorithm performs both dimension reduction and regularized linear regression simultaneously, and has outperformed supervised dimension reduction techniques like SPCA and Correlation based feature selection algorithms. In a first of its kind, two new topic models, Adaptive temporal topic model (ATTM) and SLDA for change detection (SLDACD) have been developed for predicting concept drift in time series data. These models do not assume independence of consecutive frames and outperform traditional topic models in detecting local and global changes respectively. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2015

abstract: Transfer learning refers to statistical machine learning methods that integrate the knowledge of one domain (source domain) and the data of another domain (target domain) in an appropriate way, in order to develop a model for the target domain that is better than a model using the data of the target domain alone. Transfer learning emerged because classic machine learning, when used to model different domains, has to take on one of two mechanical approaches. That is, it will either assume the data distributions of the different domains to be the same and thereby developing one model that fits all, or develop one model for each domain independently. Transfer learning, on the other hand, aims to mitigate the limitations of the two approaches by accounting for both the similarity and specificity of related domains. The objective of my dissertation research is to develop new transfer learning methods and demonstrate the utility of the methods in real-world applications. Specifically, in my methodological development, I focus on two different transfer learning scenarios: spatial transfer learning across different domains and temporal transfer learning along time in the same domain. Furthermore, I apply the proposed spatial transfer learning approach to modeling of degenerate biological systems.Degeneracy is a well-known characteristic, widely-existing in many biological systems, and contributes to the heterogeneity, complexity, and robustness of biological systems. In particular, I study the application of one degenerate biological system which is to use transcription factor (TF) binding sites to predict gene expression across multiple cell lines. Also, I apply the proposed temporal transfer learning approach to change detection of dynamic network data. Change detection is a classic research area in Statistical Process Control (SPC), but change detection in network data has been limited studied. I integrate the temporal transfer learning method called the Network State Space Model (NSSM) and SPC and formulate the problem of change detection from dynamic networks into a covariance monitoring problem. I demonstrate the performance of the NSSM in change detection of dynamic social networks. / Dissertation/Thesis / Doctoral Dissertation Industrial Engineering 2015

abstract: Multi-sensor fusion is a fundamental problem in Robot Perception. For a robot to operate in a real world environment, multiple sensors are often needed. Thus, fusing data from various sensors accurately is vital for robot perception. In the first part of this thesis, the problem of fusing information from a LIDAR, a color camera and a thermal camera to build RGB-Depth-Thermal (RGBDT) maps is investigated. An algorithm that solves a non-linear optimization problem to compute the relative pose between the cameras and the LIDAR is presented. The relative pose estimate is then used to find the color and thermal texture of each LIDAR point. Next, the various sources of error that can cause the mis-coloring of a LIDAR point after the cross- calibration are identified. Theoretical analyses of these errors reveal that the coloring errors due to noisy LIDAR points, errors in the estimation of the camera matrix, and errors in the estimation of translation between the sensors disappear with distance. But errors in the estimation of the rotation between the sensors causes the coloring error to increase with distance. On a robot (vehicle) with multiple sensors, sensor fusion algorithms allow us to represent the data in the vehicle frame. But data acquired temporally in the vehicle frame needs to be registered in a global frame to obtain a map of the environment. Mapping techniques involving the Iterative Closest Point (ICP) algorithm and the Normal Distributions Transform (NDT) assume that a good initial estimate of the transformation between the 3D scans is available. This restricts the ability to stitch maps that were acquired at different times. Mapping can become flexible if maps that were acquired temporally can be merged later. To this end, the second part of this thesis focuses on developing an automated algorithm that fuses two maps by finding a congruent set of five points forming a pyramid. Mapping has various application domains beyond Robot Navigation. The third part of this thesis considers a unique application domain where the surface displace- ments caused by an earthquake are to be recovered using pre- and post-earthquake LIDAR data. A technique to recover the 3D surface displacements is developed and the results are presented on real earthquake datasets: El Mayur Cucupa earthquake, Mexico, 2010 and Fukushima earthquake, Japan, 2011. / Dissertation/Thesis / Doctoral Dissertation Engineering Science 2016

Este trabalho examina as características evolutivas de manguezais (Sistema Estuarino de Santos, estado de São Paulo) através da oportunidade de acessar os impactos cumulativos de mudanças ambientais e suas consequências na vegetação. Para atingir este objetivo foi testado uma metodologia de detecção de mudança baseado no processamento de 9 imagens Landsat. Fora estabelecido uma rotina de trabalho o qual proporcionou a extração de bosques de mangue através de uma classificação orientada a objetos. Análises subseqüentes de índices de vegetação foram efetuadas para caracterizar a evolução de aspectos espectrais relativos aos manguezais. Também foram aplicados a extração de medidas de métricas relativas a estrutura da paisagem. Dados auxiliares, como um Modelo Digital de Elevação e imagens de alta resolução espacial propiciaram um melhor entendimento das análises efetuadas. Todos os dados gerados foram integrados em Sistema de Informação Geográfica (SIG). Os resultados apontaram que a área como um todo apresentou tendências de recobrimento de manguezais em termos de área e vigor entre 1985 e 1999, quando se tronou relativamente estável, mostrando variações locais de regeneração e degradação. A avaliação geral das formas e padrões dos bosques de manguezais baseados na delimitação de áreas e medidas da estrutura da paisagem mostraram melhores resultados quando comparados com análises de índices de vegetação, que parecem ser sensíveis a flutuações ambientais ocorridas quando da aquisição das imagens. / This work examines the evaluative characteristics of an impacted mangrove system (Santos/São Vicente region, São Paulo State) providing opportunities to assess the cumulative impact of environmental changes and their consequences on the vegetation. To achieve this objective it was tested a methodology of Time Change Detection techniques (TCD) based on the processing of series of 9 Landsat images. It was established a detailed study framework based on the individual mangroves extraction from object oriented classification. Subsequently analysis of vegetation indices values was performed in order to characterize the evolution of the spectral aspects of the mangroves. This work also assessed models of landscape patterns and structure. Other types of data such as High Resolution Satellite images, Aerial photographs and Satellite altimetry were also used to better understand the whole estuarine system. Thus it was also proposed the implementation of a geographically referenced database in a GIS in order to analyze variables which could affect mangrove dynamics. The results of the analysis demonstrated that the area as a whole confirms a tendency of recovering in terms of area and vigor since 1985 until 1999 when it became quite stable showing local variations in terms of recovering and degradation. The overall evaluation of form and shape of the mangrove forests, based in the delimitation of areas and landscape metrics, showed better results when comparing with the Vegetation Indices analysis, which seems quite influenced by the environmental conditions at the time satellite images were taken.

Made available in DSpace on 2014-06-11T19:22:25Z (GMT). No. of bitstreams: 0 Previous issue date: 2009-06-19Bitstream added on 2014-06-13T18:49:02Z : No. of bitstreams: 1 souza_ggb_me_prud.pdf: 3569562 bytes, checksum: 1967b82d0ff7aaed4984bec889309e19 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / A atualização cadastral de área urbana é uma das questões mais importantes a ser considerada no planejamento municipal. Por esta área tratar de uma riqueza de detalhes acentuada, quando comparada as área rurais e de expansão urbana, torna-se difícil traçar uma metodologia de atualização de dados cadastrais que possa ser generalizada às áreas urbanas dos municípios. Isso não apenas em metodologia, mas para atender as necessidades e realidades que se deseja atualizar no Cadastro. Neste trabalho é apresentada uma proposta de atualização cadastral de área urbana a partir da utilização de imagens de satélite de alta resolução espacial (Quick Bird). São empregados, para isso, alguns métodos e técnicas nos processos de utilização das imagens adotadas. As imagens utilizadas abrangem a área teste, definida no município de Presidente Prudente. Para a detecção das alterações a serem atualizadas no banco de dados cadastrais foram utilizadas imagens pancromáticas e multiespectrais de épocas diferentes e empregaram-se técnicas de classificação de imagens para identificar e descrever visualmente os tipos de alvos alterados. De acordo com um limiar adotado, a partir das imagens e processos descritos, as alterações identificadas foram atualizadas no banco de dados cadastrais. As implicações para a seqüência adotada são apresentadas e discutidas nos capítulos desta pesquisa. / The urban cadastre updating is one of the most important questions about urban planning. In this area there are many details when compared to the rural area and urban expansion area that hinds the introduction cadastral updating approach could be generalized to urban areas. The demand of public administration and the reality of the cities must be considered in all process including Cadastre. In this work there is presented a urban area cadastral updating approach with the use of high resolution imagery (Quick Bird satellite). The methods and techniques are employed in the processes of use of the adopted images. The used images are of the city of Presidente Prudente. Images of different times were used for the change detection to be updated in the cadastral database. Image Classifications were used to identify and to describe visually the changes. In accordance with an adopted threshold, from the images and described processes, the identified changes were updated in the cadastral database. The implications for the adopted sequence are presented and discussed in the chapters of this report.

Submitted by Carlos Rodrigo Tanajura Caldeira null (caldeiracrt@gmail.com) on 2016-10-27T11:38:12Z No. of bitstreams: 1 Dissertação_Carlos_Caldeira_2016.pdf: 5274728 bytes, checksum: d84e1b35b90b970f07821893e3a468c9 (MD5) / Approved for entry into archive by Juliano Benedito Ferreira (julianoferreira@reitoria.unesp.br) on 2016-11-01T15:48:15Z (GMT) No. of bitstreams: 1 caldeira_crt_me_prud.pdf: 5274728 bytes, checksum: d84e1b35b90b970f07821893e3a468c9 (MD5) / Made available in DSpace on 2016-11-01T15:48:15Z (GMT). No. of bitstreams: 1 caldeira_crt_me_prud.pdf: 5274728 bytes, checksum: d84e1b35b90b970f07821893e3a468c9 (MD5) Previous issue date: 2016-02-15 / Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) / Realizar detecções de mudanças de características da superfície da Terra é importante para a compreensão tanto da dinâmica dos fenômenos quanto para a previsão dos impactos, bem como para o apoio na tomada de decisões. Durante as últimas décadas foram desenvolvidas várias técnicas de detecção de mudanças a partir de imagens, dentre elas as baseadas em imagens de Sensoriamento Remoto. Em geral, a detecção de mudança envolve a utilização de um conjunto de dados multi-temporais, que permite a análise quantitativa do fenômeno de interesse. Uma aplicação de grande interesse destas técnicas é a detecção automática de mudanças no entorno de reservatórios, que podem ser utilizados como dados auxiliares em um sistema de monitoramento das áreas de interesse. Em um sistema desta natureza espera-se que as mudanças decorrentes da ação humana sejam detectadas, mesmo na presença de diferenças entre as cenas provenientes de mudanças nas condições atmosféricas, iluminação da cena, ângulos de visada do sensor, umidade do solo, dentre outros fatores. Considerando este contexto, este trabalho apresenta resultados da avaliação de uma abordagem de detecção de alterações baseada numa modificação aplicada à técnica RCEN (Radiometric Rotation Controlled by Nonchange axis). O método foi implementado e aplicado em um conjunto de imagens ortorretificadas obtidas pelo sistema orbital SPOT-6, tomadas em duas épocas distintas, sobre o reservatório de Canoas I, sob concessão da Duke Energy. Os resultados mostraram que o algoritmo baseado na técnica RCEN modificada mostrou-se eficiente para a detecção de mudanças de forma automática. / Perform change detection of Earth's surface features is important to understanding both the dynamics of the phenomena and for the prediction of impacts and to support decision-making. During the last decades were developed several change detection techniques from images, among them those based on remote sensing images. In general, the change detection involves the use of a set of multi-temporal data, which allows quantitative analysis of the phenomenon of interest. An application of great interest of these techniques is the automatic detection of changes in the vicinity of reservoirs, which can be used as auxiliary data in a monitoring system of the areas of interest. In such a system it is expected that the changes resulting from human activity are detected even if there are factors that cause differences between scenes, such as atmospheric conditions, scene lighting, sensor view point, soil moisture, among other factors. Considering this context, this paper presents the evaluation results of a change detection approach based on a modification applied to the RCEN technique (Radiometric Rotation Controlled by Nonchange axis). The method was implemented and applied to a set of orthorectified images obtained by orbital system SPOT-6, taken at two different times on the Canoas I reservoir, under concession from Duke Energy. The results showed that the algorithm based on modified RCEN technique was efficient to detect automatically changes.

Orientador: Amilton Amorim / Banca: Maria de Lourdes Bueno Trindade Galo / Banca: Alzir Felippe Buffara Antunes / Resumo: A atualização cadastral de área urbana é uma das questões mais importantes a ser considerada no planejamento municipal. Por esta área tratar de uma riqueza de detalhes acentuada, quando comparada as área rurais e de expansão urbana, torna-se difícil traçar uma metodologia de atualização de dados cadastrais que possa ser generalizada às áreas urbanas dos municípios. Isso não apenas em metodologia, mas para atender as necessidades e realidades que se deseja atualizar no Cadastro. Neste trabalho é apresentada uma proposta de atualização cadastral de área urbana a partir da utilização de imagens de satélite de alta resolução espacial (Quick Bird). São empregados, para isso, alguns métodos e técnicas nos processos de utilização das imagens adotadas. As imagens utilizadas abrangem a área teste, definida no município de Presidente Prudente. Para a detecção das alterações a serem atualizadas no banco de dados cadastrais foram utilizadas imagens pancromáticas e multiespectrais de épocas diferentes e empregaram-se técnicas de classificação de imagens para identificar e descrever visualmente os tipos de alvos alterados. De acordo com um limiar adotado, a partir das imagens e processos descritos, as alterações identificadas foram atualizadas no banco de dados cadastrais. As implicações para a seqüência adotada são apresentadas e discutidas nos capítulos desta pesquisa. / Abstract: The urban cadastre updating is one of the most important questions about urban planning. In this area there are many details when compared to the rural area and urban expansion area that hinds the introduction cadastral updating approach could be generalized to urban areas. The demand of public administration and the reality of the cities must be considered in all process including Cadastre. In this work there is presented a urban area cadastral updating approach with the use of high resolution imagery (Quick Bird satellite). The methods and techniques are employed in the processes of use of the adopted images. The used images are of the city of Presidente Prudente. Images of different times were used for the change detection to be updated in the cadastral database. Image Classifications were used to identify and to describe visually the changes. In accordance with an adopted threshold, from the images and described processes, the identified changes were updated in the cadastral database. The implications for the adopted sequence are presented and discussed in the chapters of this report. / Mestre

Esta tese investiga uma abordagem supervisionada para o problema da detecção de mudanças em imagens multitemporais de sensoriamento remoto empregando Support Vector Machines (SVM) com o uso dos kernels polinomial e gaussiano (RBF). A proposta metodológica está baseada na diferença das imagens-fração produzidas para cada data. Em imagens de cenas naturais a diferença nas frações de solo e vegetação tendem a apresentar uma distribuição simétrica em torno da origem. Esse fato pode ser usado para modelar duas distribuições normais multivariadas: mudança e não-mudança. O algoritmo Expectation-Maximization (EM) é implementado para estimar os parâmetros (vetor de médias, matriz de covariância e probabilidade a priori) associados a essas duas distribuições. Amostras aleatórias são extraídas dessas distribuições e usadas para treinar o classificador SVM nesta abordagem supervisionada. A metodologia proposta realiza testes com o uso de conjuntos de dados multitemporais de imagens multiespectrais TM-Landsat, que cobrem a mesma cena em duas datas diferentes. Os resultados são comparados com outros procedimentos, incluindo trabalhos anteriores, um conjunto de dados sintéticos e o classificador SVM One-Class. / In this thesis, we investigate a supervised approach to change detection in remote sensing multi-temporal image data by applying Support Vector Machines (SVM) technique using polynomial kernel and Gaussian kernel (RBF). The methodology is based on the difference-fraction images produced for two dates. In natural scenes, the difference in the fractions such as vegetation and bare soil occurring in two different dates tend to present a distribution symmetric around the origin of the coordinate system. This fact can be used to model two normal multivariate distributions: class change and no-change. The Expectation-Maximization algorithm (EM) is implemented to estimate the parameters (mean vector, covariance matrix and a priori probability) associated with these two distributions. Random samples are drawn from these distributions and used to train the SVM classifier in this supervised approach.The proposed methodology performs tests using multi-temporal TMLandsat multispectral image data covering the same scene in two different dates. The results are compared to other procedures including previous work, a synthetic data set and SVM One-Class.