Dans cette thèse, nous nous intéressons aux méthodes de la fusion d'images multi focales. Cette technique consiste à fusionner plusieurs images capturées avec différentes distances focales de la même scène. Cela permet d'obtenir une image de meilleure qualité à partir des deux images sources. Nous proposons une méthode de fusion d'images s'appuyant sur les techniques des pyramides Laplaciennes en utilisant comme règle de sélection les transformées d'ondelettes discretes(DWT: Discrete Wavelet Transform). Nous développons, par la suite, deux méthodes de fusion d'images multi focales basée sur la variabilité locale de chaque pixel. Elle tient en compte les informations dans la région environnante des pixels. La première consiste à utiliser la variabilité locale comme information dans la méthode de Dempster-Shafer. La seconde utilise une métrique basée sur la variabilité locale. En effet, la fusion proposée effectue une pondération de chaque pixel par une exponentielle de sa variabilité locale. Une étude comparative entre les méthodes proposées et celles existantes a été réalisée. Les résultats expérimentaux démontrent que nos méthodes proposées donnent des meilleurs fusions, tant dans la perception visuelle que dans l'analyse quantitative. / In this thesis, we are interested in the multi-focus image fusion method. This technique consists of fusing several captured images with different focal lengths of the same scene to obtain an image with better quality than the two source images. We propose an image fusion method based on Laplacian pyramid technique using Discrete Wavelet Transform (DWT) as a selection rule. We then develop two multi-focus image fusion methods based on the local variability of each pixel. It takes into account the information in the surrounding pixel area. The first method is to use local variability as an information in the Dempster-Shafer theory. The second method uses a metric based on local variability. Indeed, the proposed fusion method weighs each pixel by an exponential of its local variability. A comparative study between the proposed methods and the existing methods was carried out. The experimental results show that our proposed methods give better fusions, both in visual perception and in quantitative analysis.

Made available in DSpace on 2016-06-02T19:06:02Z (GMT). No. of bitstreams: 1 4859.pdf: 3995047 bytes, checksum: d6fe8fefac57632109ba02702cb2a16a (MD5) Previous issue date: 2012-06-11 / Financiadora de Estudos e Projetos / The digital image processing has been used to solve a significant number of problems in the agricultural sector, especially with the evolution of remote sensing systems. This work presents a computational model based on digital image processing and remote sensing to infer about the risk in the agricultural environment. To validate the method, a experimental study was conducted about the risk of fungal disease in banana plantations. Temporal series of meteorological and monitoring data of the disease, organized in classes for the definition of probability distribution models, based on polynomial functions were used to validate results as well as satellite images integrated by fusion techniques, geometric corrections and re-sampling with interpolators based on kriging techniques. Fusion methods by IHS (Intensity, Hue, and Saturation) and PCA (Principal Component Analysis) and the Gaussian models, exponential and cylindrical for the ordinary kriging were tested. The IHS fusion technique demonstrated to be more interesting in relation the PCA technique, with correlation coefficients between bands 2, 3 and 4 originals and hybrids, of 0.2318, 0.0304 and 0.1800, respectively. The method of ordinary kriging for re-sampling of the images showed better results when adjusted by the Gaussian model. The proposed method is feasible to the development of risk maps of disease occurrence, since confer spatial and temporal variability in relation to the model existing on the literature for the region. / O processamento de imagens digitais tem auxiliado na solução de um expressivo número de problemas do setor agrícola, sobretudo com a evolução dos sistemas de sensoriamento remoto. Este trabalho tem por objetivo apresentar um modelo computacional baseado em processamento digital de imagens e sensoriamento remoto para inferência de risco em ambiente agrícola. Para validação do método, foi realizado estudo experimental sobre o risco de ocorrência da doença fúngica em bananais. Foram utilizadas séries temporais de dados meteorológicos e de monitoramento da doença, organizados em classes para a definição de modelos de distribuição de probabilidades, baseados em funções polinomiais, bem como imagens de satélites, organizadas com técnicas de fusão, correções geométricas e re-amostragem, com interpoladores baseados em técnicas de krigagem. Foram testados os métodos de fusão por IHS (Intensity, Hue, Saturation) e PCA (Principal Component Analysis), bem como os modelos gaussiano, exponencial e cilíndrico para a krigagem ordinária. A técnica de fusão por IHS demonstrou-se mais interessante em relação à técnica por PCA, apresentando coeficientes de correlação entre as bandas 2, 3 e 4 originais e híbridas, de 0,2318, 0,0304 e 0,1800, respectivamente. O método de krigagem ordinária para reamostragem das imagens apresentou melhores resultados quando ajustado pelo modelo gaussiano. A metodologia proposta se apresentou viável e adequada para a elaboração de mapas de risco de ocorrência da doença, uma vez que conferece variabilidade espacial e temporal ao modelo já existente na literatura para aquela região.

Geospatial analysis involves application of statistical methods, algorithms and information retrieval techniques to geospatial data. It incorporates time into spatial databases and facilitates investigation of land cover (LC) dynamics through data, model, and analytics. LC dynamics induced by human and natural processes play a major role in global as well as regional scale patterns, which in turn influence weather and climate. Hence, understanding LC dynamics at the local / regional as well as at global levels is essential to evolve appropriate management strategies to mitigate the impacts of LC changes. This can be captured through the multi-resolution remote sensing (RS) data. However, with the advancements in sensor technologies, suitable algorithms and techniques are required for optimal integration of information from multi-resolution sensors which are cost effective while overcoming the possible data and methodological constraints. In this work, several per-pixel traditional and advanced classification techniques have been evaluated with the multi-resolution data along with the role of ancillary geographical data on the performance of classifiers. Techniques for linear and non-linear un-mixing, endmember variability and determination of spatial distribution of class components within a pixel have been applied and validated on multi-resolution data. Endmember estimation method is proposed and its performance is compared with manual, semi-automatic and fully automatic methods of endmember extraction. A novel technique - Hybrid Bayesian Classifier is developed for per pixel classification where the class prior probabilities are determined by un-mixing a low spatial-high spectral resolution multi-spectral data while posterior probabilities are determined from the training data obtained from ground, that are assigned to every pixel in a high spatial-low spectral resolution multi-spectral data in Bayesian classification. These techniques have been validated with multi-resolution data for various landscapes with varying altitudes. As a case study, spatial metrics and cellular automata based models applied for rapidly urbanising landscape with moderate altitude has been carried out.

L’imagerie hyperspectrale (HS) consiste à acquérir une même scène dans plusieurs centaines de bandes spectrales contiguës (dimensions d'un cube de données), ce qui a conduit à trois types d'applications pertinentes, telles que la détection de cibles, la classification et le démélange spectral. Cependant, tandis que les capteurs hyperspectraux fournissent une information spectrale abondante, leur résolution spatiale est généralement plus limitée. Ainsi, la fusion d’une image HS avec d'autres images à haute résolution de la même scène, telles que les images multispectrales (MS) ou panchromatiques (PAN) est un problème intéressant. Le problème de fusionner une image HS de haute résolution spectrale mais de résolution spatiale limitée avec une image auxiliaire de haute résolution spatiale mais de résolution spectrale plus limitée (parfois qualifiée de fusion multi-résolution) a été exploré depuis de nombreuses années. D'un point de vue applicatif, ce problème est également important et est motivé par ceratins projets, comme par exemple le project Japonais HISIU, qui vise à fusionner des images MS et HS recalées acquises pour la même scène avec les mêmes conditions. Les techniques de fusion bayésienne permettent une interprétation intuitive du processus de fusion via la définition de la loi a posteriori de l’image à estimer (qui est de hautes résolutions spatiale et spectrale). Puisque le problème de fusion est généralement mal posé, l’inférence bayésienne offre un moyen pratique pour régulariser le problème en définissant une loi a priori adaptée à la scène d'intérêt. Les différents chapitres de cette thèse sont résumés ci-dessous. Le introduction présente le modèle général de fusion et les hypothèses statistiques utilisées pour les images multi-bandes observées, c’est-à-dire les images HS, MS ou PAN. Les images observées sont des versions dégradées de l'image de référence (à hautes résolutions spatiale et spectrale) qui résultent par exemple d’un flou spatial et spectral et/ou d’un sous-échantillonnage liés aux caractéristiques des capteurs. Les propriétés statistiques des mesures sont alors obtenues directement à partir d’un modèle linéaire traduisant ces dégradations et des propriétés statistiques du bruit. Le chapitre 1 s’intéresse à une technique de fusion bayésienne pour les images multi-bandes de télédétection, à savoir pour les images HS, MS et PAN. Tout d'abord, le problème de fusion est formulé dans un cadre d'estimation bayésienne. Une loi a priori Gaussienne exploitant la géométrie du problème est définie et un algorithme d’estimation Bayésienne permettant d’estimer l’image de référence est étudié. Pour obtenir des estimateurs Bayésiens liés à la distribution postérieure résultant, deux algorithmes basés sur échantillonnage de Monte Carlo et l'optimisation stratégie ont été développés. Le chapitre 2 propose une approche variationnelle pour la fusion d’images HS et MS. Le problème de fusion est formulé comme un problème inverse dont la solution est l'image d’intérêt qui est supposée vivre dans un espace de dimension résuite. Un terme de régularisation imposant des contraintes de parcimonie est défini avec soin. Ce terme traduit le fait que les patches de l'image cible sont bien représentés par une combinaison linéaire d’atomes appartenant à un dictionnaire approprié. Les atomes de ce dictionnaire et le support des coefficients des décompositions des patches sur ces atomes sont appris à l’aide de l’image de haute résolution spatiale. Puis, conditionnellement à ces dictionnaires et à ces supports, le problème de fusion est résolu à l’aide d’un algorithme d’optimisation alternée (utilisant l’algorithme ADMM) qui estime de manière itérative l’image d’intérêt et les coefficients de décomposition. / Hyperspectral (HS) imaging, which consists of acquiring a same scene in several hundreds of contiguous spectral bands (a three dimensional data cube), has opened a new range of relevant applications, such as target detection [MS02], classification [C.-03] and spectral unmixing [BDPD+12]. However, while HS sensors provide abundant spectral information, their spatial resolution is generally more limited. Thus, fusing the HS image with other highly resolved images of the same scene, such as multispectral (MS) or panchromatic (PAN) images is an interesting problem. The problem of fusing a high spectral and low spatial resolution image with an auxiliary image of higher spatial but lower spectral resolution, also known as multi-resolution image fusion, has been explored for many years [AMV+11]. From an application point of view, this problem is also important as motivated by recent national programs, e.g., the Japanese next-generation space-borne hyperspectral image suite (HISUI), which fuses co-registered MS and HS images acquired over the same scene under the same conditions [YI13]. Bayesian fusion allows for an intuitive interpretation of the fusion process via the posterior distribution. Since the fusion problem is usually ill-posed, the Bayesian methodology offers a convenient way to regularize the problem by defining appropriate prior distribution for the scene of interest. The aim of this thesis is to study new multi-band image fusion algorithms to enhance the resolution of hyperspectral image. In the first chapter, a hierarchical Bayesian framework is proposed for multi-band image fusion by incorporating forward model, statistical assumptions and Gaussian prior for the target image to be restored. To derive Bayesian estimators associated with the resulting posterior distribution, two algorithms based on Monte Carlo sampling and optimization strategy have been developed. In the second chapter, a sparse regularization using dictionaries learned from the observed images is introduced as an alternative of the naive Gaussian prior proposed in Chapter 1. instead of Gaussian prior is introduced to regularize the ill-posed problem. Identifying the supports jointly with the dictionaries circumvented the difficulty inherent to sparse coding. To minimize the target function, an alternate optimization algorithm has been designed, which accelerates the fusion process magnificently comparing with the simulation-based method. In the third chapter, by exploiting intrinsic properties of the blurring and downsampling matrices, a much more efficient fusion method is proposed thanks to a closed-form solution for the Sylvester matrix equation associated with maximizing the likelihood. The proposed solution can be embedded into an alternating direction method of multipliers or a block coordinate descent method to incorporate different priors or hyper-priors for the fusion problem, allowing for Bayesian estimators. In the last chapter, a joint multi-band image fusion and unmixing scheme is proposed by combining the well admitted linear spectral mixture model and the forward model. The joint fusion and unmixing problem is solved in an alternating optimization framework, mainly consisting of solving a Sylvester equation and projecting onto a simplex resulting from the non-negativity and sum-to-one constraints. The simulation results conducted on synthetic and semi-synthetic images illustrate the advantages of the developed Bayesian estimators, both qualitatively and quantitatively.

Made available in DSpace on 2016-06-02T19:03:57Z (GMT). No. of bitstreams: 1 5415.pdf: 8638421 bytes, checksum: 0e5c5abf95c786434202fdae3e69dc1e (MD5) Previous issue date: 2013-06-24 / Financiadora de Estudos e Projetos / The resolution enhancement of an image is always desirable, independently of its objective, but mainly if the image has the purpose of visual analysis. The hardware development for increasing the image resolution still has a higher cost than the algorithmic solutions for super-resolution. Like image restoration, super-resolution is also an ill-conditioned inverse problem, and has an infinite number of solutions. This work analyzes the iterative restoration methods (Van Cittert, Tikhonov-Miller and Conjugate Gradiente) which propose solutions for the ill-conditioning problem and compares them with the IBP method (Iterative Back Projection). The analysis of the found similarities is the basis of a generalization, such that other iterative restoration methods can have their properties adapted, as regularization of the ill-conditioning, noise reduction and other degradations and the increase of the convergence rate can be incorporated to the techniques of super-resolution. Two new methods were created as case studies of the proposed generalization: the first one is a super-resolution method for dynamic magnetic resonance imaging (MRI) of the swallowing process, that uses an adaptiveWiener filtering as regularization and a non-rigid registration; and the second one is a pan sharpening method of SPOT satellite bands, that uses sampling based on sensor s characteristics and non-adaptive Wiener filtering. / A melhora da resolução de uma imagem é sempre desejada, independentemente de seu objetivo, mas principalmente se destinada a análise visual. O desenvolvimento de hardware para o aumento de resolução de uma imagem em sua captura ainda possui o custo mais elevado do que as soluções algorítmicas de super resolução (SR). Assim como a restauração de imagens, a super resolução também é um problema inverso mal-condicionado e possui infinitas soluções. Este trabalho analisa métodos de restauração iterativos (Van Cittert, Tikhonov-Miller e Gradiente Conjugado) que proponham soluções para o problema do malcondicionamento e os compara com o método IBP (Iterative Back-Projection). A análise das semelhanças encontradas é base para uma generalização de modo que outros métodos iterativos de restauração possam ter suas propriedades adaptadas, tais como regularização do mal-condicionamento, redução do ruído e outras degradações e aumento na taxa de convergência, para que possam ser incorporadas à técnicas de super resolução. Dois novos métodos foram criados como estudo de caso da generalização proposta: o primeiro é um método de super-resolução para imageamento por ressonância magnética (MRI) dinâmico do processo de deglutição, que utiliza uma filtragem de Wiener adaptativa como regularização e registro não-rígido; o segundo é um método de pansharpening das bandas do satélite SPOT, que utiliza amostragem baseada nas características do sensor e filtragem de Wiener não-adaptativa.