Feature Extraction from Whole-Sky Ground-Based Images for Cloud-Type Recognition

Several features that can be extracted from digital images of the sky and that can be useful for cloud-type classification of such images are presented. Some features are statistical measurements of image texture, some are based on the Fourier transform of the image and, finally, others are computed from the image where cloudy pixels are distinguished from clear-sky pixels. The use of the most suitable features in an automatic classification algorithm is also shown and discussed. Both the features and the classifier are developed over images taken by two different camera devices, namely, a total sky imager (TSI) and a whole sky imager (WSC), which are placed in two different areas of the world (Toowoomba, Australia; and Girona, Spain, respectively). The performance of the classifier is assessed by comparing its image classification with an a priori classification carried out by visual inspection of more than 200 images from each camera. The index of agreement is 76% when five different sky conditions are considered: clear, low cumuliform clouds, stratiform clouds (overcast), cirriform clouds, and mottled clouds (altocumulus, cirrocumulus). Discussion on the future directions of this research is also presented, regarding both the use of other features and the use of other classification techniques

Crescimento de plantas de cajueiro anão precoce influenciado pela compactação e temperatura do solo

Atribui-se ao uso de práticas culturais inadequadas uma das causas da redução drástica dos níveis de produtividade e produção da cultura do caju no nordeste brasileiro. A eliminação periódica da cobertura vegetal e o tráfego de máquinas e implementos condicionam temperaturas e densidade de solo que podem comprometer o crescimento e desenvolvimento das plantas, o que é mais preocupante ainda, considerando a textura arenosa dos solos cultivados e as condições climáticas da região. A partir destas constatações, desenvolveu-se o presente trabalho, com vistas em fornecer indicativos capazes de permitir uma avaliação dos efeitos das condições de solo e clima, objetivando identificar o comportamento de plantas de cajueiro anão precoce, submetidas a diferentes níveis de compactação e temperatura de solo, como meio de testar a hipótese de que níveis crescentes destes fatores podem reduzir seu crescimento. O presente trabalho foi desenvolvido em condições controladas, utilizando colunas de solo em tubos de PVC, nas quais se adicionou o Argissolo Vermelho-Amarelo eutrófico típico. Submeteram-se estas colunas a dois níveis de temperatura do solo, um com as colunas de solo isoladas com folhas de isopor pintadas na cor alumínio (tratamento isolado-TI), e o outro, com colunas não isoladas, mas com os tubos de PVC pintados na cor preta, para maior absorção de luz (tratamento não isolado-TNI). Os níveis de densidade a que foram ajustadas as camadas compactadas da coluna de solo foram 1,2; 1,3; 1,4; 1,5; 1,6 e 1,7 Mg m-3, sendo o restante da coluna a 1,3 Mg m-3. Os tratamentos foram distribuídos em delineamento inteiramente casualizado, com arranjo fatorial 6 x 2 (seis níveis de compactação e dois níveis de temperatura), com três repetições. Após o período de 12 meses de cultivo das plantas, a parte aérea foi colhida, determinando-se matéria seca da parte aérea, altura da planta, diâmetro do caule e número de ramificações da parte aérea. Os anéis da coluna de solo foram separados e as raízes foram coletadas, determinando-se, por meio do número de pixels, a área radicular, o comprimento de raízes e a densidade radicular. O aumento da temperatura e da densidade do solo reduziu o crescimento, afetando tanto a parte aérea quanto o sistema radicular das plantas de cajueiro.

Time-lapse and probabilistic inversion strategies for plane-wave electromagnetic data.

L'utilisation efficace des systèmes géothermaux, la séquestration du CO2 pour limiter le changement climatique et la prévention de l'intrusion d'eau salée dans les aquifères costaux ne sont que quelques exemples qui démontrent notre besoin en technologies nouvelles pour suivre l'évolution des processus souterrains à partir de la surface. Un défi majeur est d'assurer la caractérisation et l'optimisation des performances de ces technologies à différentes échelles spatiales et temporelles. Les méthodes électromagnétiques (EM) d'ondes planes sont sensibles à la conductivité électrique du sous-sol et, par conséquent, à la conductivité électrique des fluides saturant la roche, à la présence de fractures connectées, à la température et aux matériaux géologiques. Ces méthodes sont régies par des équations valides sur de larges gammes de fréquences, permettant détudier de manières analogues des processus allant de quelques mètres sous la surface jusqu'à plusieurs kilomètres de profondeur. Néanmoins, ces méthodes sont soumises à une perte de résolution avec la profondeur à cause des propriétés diffusives du champ électromagnétique. Pour cette raison, l'estimation des modèles du sous-sol par ces méthodes doit prendre en compte des informations a priori afin de contraindre les modèles autant que possible et de permettre la quantification des incertitudes de ces modèles de façon appropriée. Dans la présente thèse, je développe des approches permettant la caractérisation statique et dynamique du sous-sol à l'aide d'ondes EM planes. Dans une première partie, je présente une approche déterministe permettant de réaliser des inversions répétées dans le temps (time-lapse) de données d'ondes EM planes en deux dimensions. Cette stratégie est basée sur l'incorporation dans l'algorithme d'informations a priori en fonction des changements du modèle de conductivité électrique attendus. Ceci est réalisé en intégrant une régularisation stochastique et des contraintes flexibles par rapport à la gamme des changements attendus en utilisant les multiplicateurs de Lagrange. J'utilise des normes différentes de la norme l2 pour contraindre la structure du modèle et obtenir des transitions abruptes entre les régions du model qui subissent des changements dans le temps et celles qui n'en subissent pas. Aussi, j'incorpore une stratégie afin d'éliminer les erreurs systématiques de données time-lapse. Ce travail a mis en évidence l'amélioration de la caractérisation des changements temporels par rapport aux approches classiques qui réalisent des inversions indépendantes à chaque pas de temps et comparent les modèles. Dans la seconde partie de cette thèse, j'adopte un formalisme bayésien et je teste la possibilité de quantifier les incertitudes sur les paramètres du modèle dans l'inversion d'ondes EM planes. Pour ce faire, je présente une stratégie d'inversion probabiliste basée sur des pixels à deux dimensions pour des inversions de données d'ondes EM planes et de tomographies de résistivité électrique (ERT) séparées et jointes. Je compare les incertitudes des paramètres du modèle en considérant différents types d'information a priori sur la structure du modèle et différentes fonctions de vraisemblance pour décrire les erreurs sur les données. Les résultats indiquent que la régularisation du modèle est nécessaire lorsqu'on a à faire à un large nombre de paramètres car cela permet d'accélérer la convergence des chaînes et d'obtenir des modèles plus réalistes. Cependent, ces contraintes mènent à des incertitudes d'estimations plus faibles, ce qui implique des distributions a posteriori qui ne contiennent pas le vrai modèledans les régions ou` la méthode présente une sensibilité limitée. Cette situation peut être améliorée en combinant des méthodes d'ondes EM planes avec d'autres méthodes complémentaires telles que l'ERT. De plus, je montre que le poids de régularisation des paramètres et l'écart-type des erreurs sur les données peuvent être retrouvés par une inversion probabiliste. Finalement, j'évalue la possibilité de caractériser une distribution tridimensionnelle d'un panache de traceur salin injecté dans le sous-sol en réalisant une inversion probabiliste time-lapse tridimensionnelle d'ondes EM planes. Etant donné que les inversions probabilistes sont très coûteuses en temps de calcul lorsque l'espace des paramètres présente une grande dimension, je propose une stratégie de réduction du modèle ou` les coefficients de décomposition des moments de Legendre du panache de traceur injecté ainsi que sa position sont estimés. Pour ce faire, un modèle de résistivité de base est nécessaire. Il peut être obtenu avant l'expérience time-lapse. Un test synthétique montre que la méthodologie marche bien quand le modèle de résistivité de base est caractérisé correctement. Cette méthodologie est aussi appliquée à un test de trac¸age par injection d'une solution saline et d'acides réalisé dans un système géothermal en Australie, puis comparée à une inversion time-lapse tridimensionnelle réalisée selon une approche déterministe. L'inversion probabiliste permet de mieux contraindre le panache du traceur salin gr^ace à la grande quantité d'informations a priori incluse dans l'algorithme. Néanmoins, les changements de conductivités nécessaires pour expliquer les changements observés dans les données sont plus grands que ce qu'expliquent notre connaissance actuelle des phénomenès physiques. Ce problème peut être lié à la qualité limitée du modèle de résistivité de base utilisé, indiquant ainsi que des efforts plus grands devront être fournis dans le futur pour obtenir des modèles de base de bonne qualité avant de réaliser des expériences dynamiques. Les études décrites dans cette thèse montrent que les méthodes d'ondes EM planes sont très utiles pour caractériser et suivre les variations temporelles du sous-sol sur de larges échelles. Les présentes approches améliorent l'évaluation des modèles obtenus, autant en termes d'incorporation d'informations a priori, qu'en termes de quantification d'incertitudes a posteriori. De plus, les stratégies développées peuvent être appliquées à d'autres méthodes géophysiques, et offrent une grande flexibilité pour l'incorporation d'informations additionnelles lorsqu'elles sont disponibles. -- The efficient use of geothermal systems, the sequestration of CO2 to mitigate climate change, and the prevention of seawater intrusion in coastal aquifers are only some examples that demonstrate the need for novel technologies to monitor subsurface processes from the surface. A main challenge is to assure optimal performance of such technologies at different temporal and spatial scales. Plane-wave electromagnetic (EM) methods are sensitive to subsurface electrical conductivity and consequently to fluid conductivity, fracture connectivity, temperature, and rock mineralogy. These methods have governing equations that are the same over a large range of frequencies, thus allowing to study in an analogous manner processes on scales ranging from few meters close to the surface down to several hundreds of kilometers depth. Unfortunately, they suffer from a significant resolution loss with depth due to the diffusive nature of the electromagnetic fields. Therefore, estimations of subsurface models that use these methods should incorporate a priori information to better constrain the models, and provide appropriate measures of model uncertainty. During my thesis, I have developed approaches to improve the static and dynamic characterization of the subsurface with plane-wave EM methods. In the first part of this thesis, I present a two-dimensional deterministic approach to perform time-lapse inversion of plane-wave EM data. The strategy is based on the incorporation of prior information into the inversion algorithm regarding the expected temporal changes in electrical conductivity. This is done by incorporating a flexible stochastic regularization and constraints regarding the expected ranges of the changes by using Lagrange multipliers. I use non-l2 norms to penalize the model update in order to obtain sharp transitions between regions that experience temporal changes and regions that do not. I also incorporate a time-lapse differencing strategy to remove systematic errors in the time-lapse inversion. This work presents improvements in the characterization of temporal changes with respect to the classical approach of performing separate inversions and computing differences between the models. In the second part of this thesis, I adopt a Bayesian framework and use Markov chain Monte Carlo (MCMC) simulations to quantify model parameter uncertainty in plane-wave EM inversion. For this purpose, I present a two-dimensional pixel-based probabilistic inversion strategy for separate and joint inversions of plane-wave EM and electrical resistivity tomography (ERT) data. I compare the uncertainties of the model parameters when considering different types of prior information on the model structure and different likelihood functions to describe the data errors. The results indicate that model regularization is necessary when dealing with a large number of model parameters because it helps to accelerate the convergence of the chains and leads to more realistic models. These constraints also lead to smaller uncertainty estimates, which imply posterior distributions that do not include the true underlying model in regions where the method has limited sensitivity. This situation can be improved by combining planewave EM methods with complimentary geophysical methods such as ERT. In addition, I show that an appropriate regularization weight and the standard deviation of the data errors can be retrieved by the MCMC inversion. Finally, I evaluate the possibility of characterizing the three-dimensional distribution of an injected water plume by performing three-dimensional time-lapse MCMC inversion of planewave EM data. Since MCMC inversion involves a significant computational burden in high parameter dimensions, I propose a model reduction strategy where the coefficients of a Legendre moment decomposition of the injected water plume and its location are estimated. For this purpose, a base resistivity model is needed which is obtained prior to the time-lapse experiment. A synthetic test shows that the methodology works well when the base resistivity model is correctly characterized. The methodology is also applied to an injection experiment performed in a geothermal system in Australia, and compared to a three-dimensional time-lapse inversion performed within a deterministic framework. The MCMC inversion better constrains the water plumes due to the larger amount of prior information that is included in the algorithm. The conductivity changes needed to explain the time-lapse data are much larger than what is physically possible based on present day understandings. This issue may be related to the base resistivity model used, therefore indicating that more efforts should be given to obtain high-quality base models prior to dynamic experiments. The studies described herein give clear evidence that plane-wave EM methods are useful to characterize and monitor the subsurface at a wide range of scales. The presented approaches contribute to an improved appraisal of the obtained models, both in terms of the incorporation of prior information in the algorithms and the posterior uncertainty quantification. In addition, the developed strategies can be applied to other geophysical methods, and offer great flexibility to incorporate additional information when available.

Domain Adaptation in remote sensing: increasing the portability of land-cover classifiers

Among the types of remote sensing acquisitions, optical images are certainly one of the most widely relied upon data sources for Earth observation. They provide detailed measurements of the electromagnetic radiation reflected or emitted by each pixel in the scene. Through a process termed supervised land-cover classification, this allows to automatically yet accurately distinguish objects at the surface of our planet. In this respect, when producing a land-cover map of the surveyed area, the availability of training examples representative of each thematic class is crucial for the success of the classification procedure. However, in real applications, due to several constraints on the sample collection process, labeled pixels are usually scarce. When analyzing an image for which those key samples are unavailable, a viable solution consists in resorting to the ground truth data of other previously acquired images. This option is attractive but several factors such as atmospheric, ground and acquisition conditions can cause radiometric differences between the images, hindering therefore the transfer of knowledge from one image to another. The goal of this Thesis is to supply remote sensing image analysts with suitable processing techniques to ensure a robust portability of the classification models across different images. The ultimate purpose is to map the land-cover classes over large spatial and temporal extents with minimal ground information. To overcome, or simply quantify, the observed shifts in the statistical distribution of the spectra of the materials, we study four approaches issued from the field of machine learning. First, we propose a strategy to intelligently sample the image of interest to collect the labels only in correspondence of the most useful pixels. This iterative routine is based on a constant evaluation of the pertinence to the new image of the initial training data actually belonging to a different image. Second, an approach to reduce the radiometric differences among the images by projecting the respective pixels in a common new data space is presented. We analyze a kernel-based feature extraction framework suited for such problems, showing that, after this relative normalization, the cross-image generalization abilities of a classifier are highly increased. Third, we test a new data-driven measure of distance between probability distributions to assess the distortions caused by differences in the acquisition geometry affecting series of multi-angle images. Also, we gauge the portability of classification models through the sequences. In both exercises, the efficacy of classic physically- and statistically-based normalization methods is discussed. Finally, we explore a new family of approaches based on sparse representations of the samples to reciprocally convert the data space of two images. The projection function bridging the images allows a synthesis of new pixels with more similar characteristics ultimately facilitating the land-cover mapping across images.

The combined use of reflectance, emissivity and elevation Aster/Terra data for tropical soil studies

Reflectance, emissivity and elevation data of the sensor ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer)/Terra were used to characterize soil composition variations according to the toposequence position. Normalized data of SWIR (shortwave infrared) reflectance and TIR (thermal infrared) emissivity, coupled to a soil-fraction image from a spectral mixture model, were evaluated to separate bare soils from nonphotosynthetic vegetation. Regression relationships of some soil properties with reflectance and emissivity data were then applied on the exposed soil pixels. The resulting estimated values were plotted on the ASTER-derived digital elevation model. Results showed that the SWIR bands 5 and 6 and the TIR bands 10 and 14 measured the clay mineral absorption band and the quartz emissivity feature, respectively. These bands improved also the discrimination between nonphotosynthetic vegetation and soils. Despite the differences in pixel size and field sampling size, some soil properties were correlated with reflectance (R² of 0.65 for Al2O3 in band 6; 0.61 for Fe2O3 in band 3) and emissivity (R² of 0.65 for total sand fraction in the 10/14 band ratio). The combined use of reflectance, emissivity and elevation data revealed variations in soil composition with topography in specific parts of the landscape. From higher to lower slope positions, a general decrease in Al2O3 and increase in total sand fraction was observed, due to the prevalence of Rhodic Acrustox at the top and its gradual transition to Typic Acrustox at the bottom.

Voir le monde à travers les lunettes du métacontraste : un modèle mathématique inspiré de la psychologie sociale

Résumé La théorie de l'autocatégorisation est une théorie de psychologie sociale qui porte sur la relation entre l'individu et le groupe. Elle explique le comportement de groupe par la conception de soi et des autres en tant que membres de catégories sociales, et par l'attribution aux individus des caractéristiques prototypiques de ces catégories. Il s'agit donc d'une théorie de l'individu qui est censée expliquer des phénomènes collectifs. Les situations dans lesquelles un grand nombre d'individus interagissent de manière non triviale génèrent typiquement des comportements collectifs complexes qui sont difficiles à prévoir sur la base des comportements individuels. La simulation informatique de tels systèmes est un moyen fiable d'explorer de manière systématique la dynamique du comportement collectif en fonction des spécifications individuelles. Dans cette thèse, nous présentons un modèle formel d'une partie de la théorie de l'autocatégorisation appelée principe du métacontraste. À partir de la distribution d'un ensemble d'individus sur une ou plusieurs dimensions comparatives, le modèle génère les catégories et les prototypes associés. Nous montrons que le modèle se comporte de manière cohérente par rapport à la théorie et est capable de répliquer des données expérimentales concernant divers phénomènes de groupe, dont par exemple la polarisation. De plus, il permet de décrire systématiquement les prédictions de la théorie dont il dérive, notamment dans des situations nouvelles. Au niveau collectif, plusieurs dynamiques peuvent être observées, dont la convergence vers le consensus, vers une fragmentation ou vers l'émergence d'attitudes extrêmes. Nous étudions également l'effet du réseau social sur la dynamique et montrons qu'à l'exception de la vitesse de convergence, qui augmente lorsque les distances moyennes du réseau diminuent, les types de convergences dépendent peu du réseau choisi. Nous constatons d'autre part que les individus qui se situent à la frontière des groupes (dans le réseau social ou spatialement) ont une influence déterminante sur l'issue de la dynamique. Le modèle peut par ailleurs être utilisé comme un algorithme de classification automatique. Il identifie des prototypes autour desquels sont construits des groupes. Les prototypes sont positionnés de sorte à accentuer les caractéristiques typiques des groupes, et ne sont pas forcément centraux. Enfin, si l'on considère l'ensemble des pixels d'une image comme des individus dans un espace de couleur tridimensionnel, le modèle fournit un filtre qui permet d'atténuer du bruit, d'aider à la détection d'objets et de simuler des biais de perception comme l'induction chromatique. Abstract Self-categorization theory is a social psychology theory dealing with the relation between the individual and the group. It explains group behaviour through self- and others' conception as members of social categories, and through the attribution of the proto-typical categories' characteristics to the individuals. Hence, it is a theory of the individual that intends to explain collective phenomena. Situations involving a large number of non-trivially interacting individuals typically generate complex collective behaviours, which are difficult to anticipate on the basis of individual behaviour. Computer simulation of such systems is a reliable way of systematically exploring the dynamics of the collective behaviour depending on individual specifications. In this thesis, we present a formal model of a part of self-categorization theory named metacontrast principle. Given the distribution of a set of individuals on one or several comparison dimensions, the model generates categories and their associated prototypes. We show that the model behaves coherently with respect to the theory and is able to replicate experimental data concerning various group phenomena, for example polarization. Moreover, it allows to systematically describe the predictions of the theory from which it is derived, specially in unencountered situations. At the collective level, several dynamics can be observed, among which convergence towards consensus, towards frag-mentation or towards the emergence of extreme attitudes. We also study the effect of the social network on the dynamics and show that, except for the convergence speed which raises as the mean distances on the network decrease, the observed convergence types do not depend much on the chosen network. We further note that individuals located at the border of the groups (whether in the social network or spatially) have a decisive influence on the dynamics' issue. In addition, the model can be used as an automatic classification algorithm. It identifies prototypes around which groups are built. Prototypes are positioned such as to accentuate groups' typical characteristics and are not necessarily central. Finally, if we consider the set of pixels of an image as individuals in a three-dimensional color space, the model provides a filter that allows to lessen noise, to help detecting objects and to simulate perception biases such as chromatic induction.

Atributos topográficos na diferenciação de Argissolos

A topografia do terreno controla muitos processos hidrológicos, geomorfológicos e pedológicos, influenciando a radiação solar, precipitação pluvial, escoamento superficial, evaporação, regime de umidade do solo e tipo de vegetação, entre outros. Desta maneira, atributos topográficos derivados de um modelo digital de elevação foram utilizados para explicar a diferenciação de solos com horizonte B textural da região de ''Mar de Morros'', no noroeste do Estado do Rio de Janeiro. Foram estudados oito perfis de solo (quatro Argissolos Vermelhos e quatro Argissolos Vermelho-Amarelos), desenvolvidos de granulitos noríticos nos municípios de São José de Ubá e Itaperuna. Os dados dos atributos topográficos em cada perfil de solo (elevação, declividade, aspecto, plano e perfil de curvatura, radiação solar e índice topográfico combinado) foram extraídos, utilizando-se uma janela de 7 x 7 pixels, com os perfis ocupando o centro dessa janela. Os Argissolos que ocorrem nas encostas noroeste e nordeste recebem maior quantidade de radiação solar (mais quentes e secas) e por isto são vermelhos, eutróficos e não apresentam horizonte B latossólico, enquanto os solos das encostas sudeste (relativamente mais frias e úmidas) são vermelho-amarelados, distróficos e com horizonte B latossólico. A radiação solar, a declividade e o aspecto são os atributos topográficos relacionados com as diferenças entre os perfis de solos estudados. Os atributos topográficos analisados pelas técnicas multivariadas apresentaram-se efetivos para a distinção entre os Argissolos Vermelho-Amarelos distróficos e os Argissolos Vermelhos eutróficos, exceto o P7 (PVe). Estudos relacionando a influência da radiação solar na pedogênese são escassos em condições tropicais e, embora menos atuante em regiões tropicais, foi a radiação solar que determinou diretamente a diferenciação dos solos da área estudada.

Diffraction theory of Fresnel lenses encoded in low-resolution devices

A mathematical model that describes the behavior of low-resolution Fresnel lenses encoded in any low-resolution device (e.g., a spatial light modulator) is developed. The effects of low-resolution codification, such the appearance of new secondary lenses, are studied for a general case. General expressions for the phase of these lenses are developed, showing that each lens behaves as if it were encoded through all pixels of the low-resolution device. Simple expressions for the light distribution in the focal plane and its dependence on the encoded focal length are developed and commented on in detail. For a given codification device an optimum focal length is found for best lens performance. An optimization method for codification of a single lens with a short focal length is proposed.

Multiscaling and information content of natural color images

Naive scale invariance is not a true property of natural images. Natural monochrome images possess a much richer geometrical structure, which is particularly well described in terms of multiscaling relations. This means that the pixels of a given image can be decomposed into sets, the fractal components of the image, with well-defined scaling exponents [Turiel and Parga, Neural Comput. 12, 763 (2000)]. Here it is shown that hyperspectral representations of natural scenes also exhibit multiscaling properties, observing the same kind of behavior. A precise measure of the informational relevance of the fractal components is also given, and it is shown that there are important differences between the intrinsically redundant red-green-blue system and the decorrelated one defined in Ruderman, Cronin, and Chiao [J. Opt. Soc. Am. A 15, 2036 (1998)].

Advanced Kernel Methods For Remote Sensing Image Classification

Résumé Suite aux recentes avancées technologiques, les archives d'images digitales ont connu une croissance qualitative et quantitative sans précédent. Malgré les énormes possibilités qu'elles offrent, ces avancées posent de nouvelles questions quant au traitement des masses de données saisies. Cette question est à la base de cette Thèse: les problèmes de traitement d'information digitale à très haute résolution spatiale et/ou spectrale y sont considérés en recourant à des approches d'apprentissage statistique, les méthodes à noyau. Cette Thèse étudie des problèmes de classification d'images, c'est à dire de catégorisation de pixels en un nombre réduit de classes refletant les propriétés spectrales et contextuelles des objets qu'elles représentent. L'accent est mis sur l'efficience des algorithmes, ainsi que sur leur simplicité, de manière à augmenter leur potentiel d'implementation pour les utilisateurs. De plus, le défi de cette Thèse est de rester proche des problèmes concrets des utilisateurs d'images satellite sans pour autant perdre de vue l'intéret des méthodes proposées pour le milieu du machine learning dont elles sont issues. En ce sens, ce travail joue la carte de la transdisciplinarité en maintenant un lien fort entre les deux sciences dans tous les développements proposés. Quatre modèles sont proposés: le premier répond au problème de la haute dimensionalité et de la redondance des données par un modèle optimisant les performances en classification en s'adaptant aux particularités de l'image. Ceci est rendu possible par un système de ranking des variables (les bandes) qui est optimisé en même temps que le modèle de base: ce faisant, seules les variables importantes pour résoudre le problème sont utilisées par le classifieur. Le manque d'information étiquétée et l'incertitude quant à sa pertinence pour le problème sont à la source des deux modèles suivants, basés respectivement sur l'apprentissage actif et les méthodes semi-supervisées: le premier permet d'améliorer la qualité d'un ensemble d'entraînement par interaction directe entre l'utilisateur et la machine, alors que le deuxième utilise les pixels non étiquetés pour améliorer la description des données disponibles et la robustesse du modèle. Enfin, le dernier modèle proposé considère la question plus théorique de la structure entre les outputs: l'intègration de cette source d'information, jusqu'à présent jamais considérée en télédétection, ouvre des nouveaux défis de recherche. Advanced kernel methods for remote sensing image classification Devis Tuia Institut de Géomatique et d'Analyse du Risque September 2009 Abstract The technical developments in recent years have brought the quantity and quality of digital information to an unprecedented level, as enormous archives of satellite images are available to the users. However, even if these advances open more and more possibilities in the use of digital imagery, they also rise several problems of storage and treatment. The latter is considered in this Thesis: the processing of very high spatial and spectral resolution images is treated with approaches based on data-driven algorithms relying on kernel methods. In particular, the problem of image classification, i.e. the categorization of the image's pixels into a reduced number of classes reflecting spectral and contextual properties, is studied through the different models presented. The accent is put on algorithmic efficiency and the simplicity of the approaches proposed, to avoid too complex models that would not be used by users. The major challenge of the Thesis is to remain close to concrete remote sensing problems, without losing the methodological interest from the machine learning viewpoint: in this sense, this work aims at building a bridge between the machine learning and remote sensing communities and all the models proposed have been developed keeping in mind the need for such a synergy. Four models are proposed: first, an adaptive model learning the relevant image features has been proposed to solve the problem of high dimensionality and collinearity of the image features. This model provides automatically an accurate classifier and a ranking of the relevance of the single features. The scarcity and unreliability of labeled. information were the common root of the second and third models proposed: when confronted to such problems, the user can either construct the labeled set iteratively by direct interaction with the machine or use the unlabeled data to increase robustness and quality of the description of data. Both solutions have been explored resulting into two methodological contributions, based respectively on active learning and semisupervised learning. Finally, the more theoretical issue of structured outputs has been considered in the last model, which, by integrating outputs similarity into a model, opens new challenges and opportunities for remote sensing image processing.

Identification of different heart tissues from MRI C-SENC images using an unsupervised multi-stage fuzzy clustering technique.

PURPOSE: To objectively characterize different heart tissues from functional and viability images provided by composite-strain-encoding (C-SENC) MRI. MATERIALS AND METHODS: C-SENC is a new MRI technique for simultaneously acquiring cardiac functional and viability images. In this work, an unsupervised multi-stage fuzzy clustering method is proposed to identify different heart tissues in the C-SENC images. The method is based on sequential application of the fuzzy c-means (FCM) and iterative self-organizing data (ISODATA) clustering algorithms. The proposed method is tested on simulated heart images and on images from nine patients with and without myocardial infarction (MI). The resulting clustered images are compared with MRI delayed-enhancement (DE) viability images for determining MI. Also, Bland-Altman analysis is conducted between the two methods. RESULTS: Normal myocardium, infarcted myocardium, and blood are correctly identified using the proposed method. The clustered images correctly identified 90 +/- 4% of the pixels defined as infarct in the DE images. In addition, 89 +/- 5% of the pixels defined as infarct in the clustered images were also defined as infarct in DE images. The Bland-Altman results show no bias between the two methods in identifying MI. CONCLUSION: The proposed technique allows for objectively identifying divergent heart tissues, which would be potentially important for clinical decision-making in patients with MI.

Statistical assessment of dataset shift and model portability in multi-angle in-track image acquisitions

In this study we propose an evaluation of the angular effects altering the spectral response of the land-cover over multi-angle remote sensing image acquisitions. The shift in the statistical distribution of the pixels observed in an in-track sequence of WorldView-2 images is analyzed by means of a kernel-based measure of distance between probability distributions. Afterwards, the portability of supervised classifiers across the sequence is investigated by looking at the evolution of the classification accuracy with respect to the changing observation angle. In this context, the efficiency of various physically and statistically based preprocessing methods in obtaining angle-invariant data spaces is compared and possible synergies are discussed.

IMRT credentialing for prospective trials using institutional virtual phantoms: results of a joint European Organization for the Research and Treatment of Cancer and Radiological Physics Center project.

BACKGROUND AND PURPOSE: Intensity-modulated radiotherapy (IMRT) credentialing for a EORTC study was performed using an anthropomorphic head phantom from the Radiological Physics Center (RPC; RPCPH). Institutions were retrospectively requested to irradiate their institutional phantom (INSTPH) using the same treatment plan in the framework of a Virtual Phantom Project (VPP) for IMRT credentialing. MATERIALS AND METHODS: CT data set of the institutional phantom and measured 2D dose matrices were requested from centers and sent to a dedicated secure EORTC uploader. Data from the RPCPH and INSTPH were thereafter centrally analyzed and inter-compared by the QA team using commercially available software (RIT; ver.5.2; Colorado Springs, USA). RESULTS: Eighteen institutions participated to the VPP. The measurements of 6 (33%) institutions could not be analyzed centrally. All other centers passed both the VPP and the RPC ±7%/4 mm credentialing criteria. At the 5%/5 mm gamma criteria (90% of pixels passing), 11(92%) as compared to 12 (100%) centers pass the credentialing process with RPCPH and INSTPH (p = 0.29), respectively. The corresponding pass rate for the 3%/3 mm gamma criteria (90% of pixels passing) was 2 (17%) and 9 (75%; p = 0.01), respectively. CONCLUSIONS: IMRT dosimetry gamma evaluations in a single plane for a H&N prospective trial using the INSTPH measurements showed agreement at the gamma index criteria of ±5%/5 mm (90% of pixels passing) for a small number of VPP measurements. Using more stringent, criteria, the RPCPH and INSTPH comparison showed disagreement. More data is warranted and urgently required within the framework of prospective studies.

Evaluating effects of spectral training data distribution on continuous field mapping performance

Continuous field mapping has to address two conflicting remote sensing requirements when collecting training data. On one hand, continuous field mapping trains fractional land cover and thus favours mixed training pixels. On the other hand, the spectral signature has to be preferably distinct and thus favours pure training pixels. The aim of this study was to evaluate the sensitivity of training data distribution along fractional and spectral gradients on the resulting mapping performance. We derived four continuous fields (tree, shrubherb, bare, water) from aerial photographs as response variables and processed corresponding spectral signatures from multitemporal Landsat 5 TM data as explanatory variables. Subsequent controlled experiments along fractional cover gradients were then based on generalised linear models. Resulting fractional and spectral distribution differed between single continuous fields, but could be satisfactorily trained and mapped. Pixels with fractional or without respective cover were much more critical than pure full cover pixels. Error distribution of continuous field models was non-uniform with respect to horizontal and vertical spatial distribution of target fields. We conclude that a sampling for continuous field training data should be based on extent and densities in the fractional and spectral, rather than the real spatial space. Consequently, adequate training plots are most probably not systematically distributed in the real spatial space, but cover the gradient and covariate structure of the fractional and spectral space well. (C) 2009 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.

Caracterização mineralógica de solos tropicais por sensoriamento remoto hiperespectral

Dados hiperespectrais coletados no Brasil pelo sensor AVIRIS (Airborne Visible/Infrared Imaging Spectrometer) foram utilizados para a caracterização espectral de uma típica cena agropastoril e para testar o uso da técnica Spectral Feature Fitting (SFF) na identificação de minerais argilosos na imagem. Utilizou-se um modelo linear de mistura espectral, usando como membros de referência a vegetação verde e seca, a água, e os solos Nitossolo Vermelho, Latossolo Vermelho e Neossolo Quartzarênico órtico. Na identificação dos minerais, foram selecionados espectros de referência da biblioteca espectral do JPL/NASA. Os espectros dos pixels e das referências foram normalizados pelo método do contínuo espectral, entre 2.100 e 2.330 nm, e depois comparados quanto à similaridade com o uso da técnica SFF. A caulinita predomina na cena, cuja identificação remota é dependente do tipo de solo e das proporções dos componentes da cena no interior do pixels. Os melhores resultados foram obtidos em solos de reflectância intermediária a alta e em pixels com valor de abundância da fração solo superior a 70%. Isto ocorreu devido, respectivamente, à menor quantidade de substâncias opacas nestes solos e à redução nos pixels dos efeitos espectrais da lignina-celulose. Estes fatores tendem a mascarar as bandas de absorção das argilas.