Thesis (M.S.)--Indiana University, 2009. / Department of Earth Sciences, Indiana University-Purdue University Indianapolis (IUPUI). Advisor(s): Jeffrey Wilson, Lenore Tedesco, Lin Li. Includes vita. Includes bibliographical references (leaves 92-95).

Thesis (Msc Food Sc (Food Science))--University of Stellenbosch, 2009. / The use of near infrared (NIR) hyperspectral imaging and hyperspectral image analysis for distinguishing between whole maize kernels of varying degrees of hardness and fungal infected and non-infected kernels have been investigated. Near infrared hyperspectral images of whole maize kernels of varying degrees of hardness were acquired using a Spectral Dimensions MatrixNIR camera with a spectral range of 960-1662 nm as well as a sisuChema SWIR (short wave infrared) hyperspectral pushbroom imaging system with a spectral range of 1000-2498 nm. Exploratory principal component analysis (PCA) on absorbance images was used to remove background, bad pixels and shading. On the cleaned images, PCA could be used effectively to find histological classes including glassy (hard) and floury (soft) endosperm. PCA illustrated a distinct difference between floury and glassy endosperm along principal component (PC) three. Interpreting the PC loading line plots important absorbance peaks responsible for the variation were 1215, 1395 and 1450 nm, associated with starch and moisture for both MatrixNIR images (12 and 24 kernels). The loading line plots for the sisuChema (24 kernels) illustrated peaks of importance at the aforementioned wavelengths as well as 1695, 1900 and 1940 nm, also associated with starch and moisture. Partial least squares-discriminant analysis (PLS-DA) was applied as a means to predict whether the different endosperm types observed, were glassy or floury. For the MatrixNIR image (12 kernels), the PLS-DA model exhibited a classification rate of up to 99% for the discrimination of both floury and glassy endosperm. The PLS-DA model for the second MatrixNIR image (24 kernels) yielded a classification rate of 82% for the discrimination of glassy and 73% for floury endosperm. The sisuChema image (24 kernels) yielded a classification rate of 95% for the discrimination of floury and 92% for glassy endosperm. The fungal infected and sound whole maize kernels were imaged using the same instruments. Background, bad pixels and shading were removed by applying PCA on absorbance images. On the cleaned images, PCA could be used effectively to find the infected regions, pedicle as well as non-infected regions. A distinct difference between infected and sound kernels was illustrated along PC1. Interpreting the PC loading line plots showed important absorbance peaks responsible for the variation and predominantly associated with starch and moisture: 1215, 1450, 1480, 1690, 1940 and 2136 nm for both MatrixNIR images (15 and 21 kernels). The MatrixNIR image (15 kernels) exhibited a PLS-DA classification rate of up to 96.1% for the discrimination of infected kernels and the sisuChema had a classification rate of 99% for the same region of interest. The The iv sisuChema image (21-kernels) had a classification rate for infected kernels of 97.6% without pre-processing, 97.7% with multiplicative scatter correction (MSC) and 97.4% with standard normal variate (SNV). Near infrared hyperspectral imaging is a promising technique, capable of distinguishing between maize kernels of varying hardness and between fungal infected and sound kernels. While there are still limitations with hardware and software, these results provide the platform which would greatly assist with the determination of maize kernel hardness in breeding programmes without having to destroy the kernel. Further, NIR hyperspectral imaging could serve as an objective, rapid tool for identification of fungal infected kernels.

Les méthodes standard de pansharpening visent à fusionner une image panchromatique avec une image multispectrale afin de générer une image possédant la haute résolution spatiale de la première et la haute résolution spectrale de la dernière. Durant la dernière décennie, beaucoup de méthodes de pansharpening utilisant des images multispectrales furent créées. Avec la disponibilité croissante d’images hyperspectrales, ces méthodes s’étendent maintenant au pansharpening hyperspectral, c’est-à-dire à la fusion d’une image panchromatique possédant une très bonne résolution spatiale avec une image hyperspectrale possédant une résolution spatiale plus faible. Toutefois les méthodes de pansharpening hyperspectrale issues de l’état de l’art ignorent souvent le problème des pixels mixtes. Le but de ses méthodes est de préserver l’information spectrale tout en améliorant l’information spatiale. Dans cette thèse, dans une première partie, nous présentons et analysons les méthodes de l’état de l’art afin de les analyser pour connaitre leurs performances et leurs limitations. Dans une seconde partie, nous présentons une approche qui s’occupe du cas des pixels mixtes en intégrant une étape pré-fusion pour les démélanger. Cette méthode améliore les résultats en ajoutant de l’information spectrale qui n’est pas présente dans l’image hyperspectrale à cause des pixels mixtes. Les performances de notre méthode sont évaluées sur différents jeux de données possédant des résolutions spatiales et spectrales différentes correspondant à des environnements différents. Notre méthode sera évaluée en comparaison avec les méthodes de l’état de l’art à une échelle globale et locale. / Standard pansharpening aims at fusing a panchromatic image with a multispectral image in order to synthesize an image with the high spatial resolution of the former and the spectral resolution of the latter. In the last decade many pansharpening algorithms have been presented in the literature using multispectral data. With the increasing availability of hyperspectral systems, these methods are now extending to hyperspectral pansharpening, i.e. the fusion of a panchromatic image with a high spatial resolution and a hyperspectral image with a coarser spatial resolution. However, state of the art hyperspectral pansharpening methods usually do not consider the problem of the mixed pixels. Their goal is solely to preserve the spectral information while adding spatial information. In this thesis, in a first part, we present the state-of-the-art methods and analysed them to identified there performances and limitations. In a second part, we present an approach to actually deal with mixed pixels as a pre-processing step before performing the fusion. This improves the result by adding missing spectral information that is not directly available in the hyperspectral image because of the mixed pixels. The performances of our proposed approach are assessed on different real data sets, with different spectral and spatial resolutions and corresponding to different contexts. They are compared qualitatively and quantitatively with state of the art methods, both at a global and a local scale.

O objetivo do presente trabalho foi avaliar o uso potencial dos dados hiperespectrais do sensor orbital Hyperion/Earth Observing One (EO-1) e dos modelos de mistura espectral MESMA (Multiple Endmember Spectral Mixture Analysis) e SMA (Spectral Mixture Analysis) para discriminação de classes de cobertura da Planície Costeira do Rio Grande do Sul. O modelo MESMA difere do SMA por permitir que o número e o tipo de Membros de Referência (MRs), assim como sua abundância, variem pixel a pixel. A abordagem metodológica utilizada envolveu as seguintes etapas: (a) préprocessamento dos dados Hyperion e conversão dos valores de radiância para imagens atmosfericamente corrigidas de reflectância de superfície; (b) uso seqüencial das técnicas Minimum Noise Fraction (MNF), Pixel Purity Index (PPI) e Visualizador n- Dimensional, no intervalo de 454 a 2334 nm, para seleção inicial de um grupo de pixels candidatos a MRs (primeira biblioteca espectral) e de um outro grupo para fins de validação dos modelos; (c) uso do aplicativo VIPER (Visualization and Image Processing for Environmental Research) Tools para refinamento da primeira biblioteca espectral e seleção final dos MRs, utilizando as métricas EAR (Endmember Average RMSE), MASA (Minimum Average Spectral Angle) e CoB (Count Based Endmember Selection); (d) geração dos modelos MESMA e SMA com o VIPER Tools; e (e) comparação dos resultados dos modelos com base nas imagens-fração e nos valores de erro médio quadrático (RMSE). Os resultados obtidos mostraram que: (1) o uso seqüencial das técnicas MNF, PPI e Visualizador n-Dimensional pode constituir uma etapa inicial para identificar pixels candidatos a MRs, cuja seleção final pode ser feita com as métricas EAR, MASA e CoB. Usadas de forma combinada, essas métricas minimizam possíveis efeitos da baixa relação sinal-ruído do Hyperion; (2) os MRs selecionados representaram os principais componentes de cena como “água” (com clorofila, límpida e com sedimentos em suspensão), “vegetação verde” (pinus, eucalipto e gramíneas) e “solo” (dunas e campo seco); (3) Por utilizar número e tipo variáveis de MRs, o modelo MESMA produziu melhores resultados que o SMA. Quando aplicado sobre a imagem, sobre a amostra de validação e quando comparado com o SMA, o modelo MESMA de 4 componentes (Solo = dunas e campo Seco; vegetação verde = pinus, eucalipto e gramíneas; água = com Sedimentos em suspensão, sem Sedimentos e com clorofila; sombra) descreveu adequadamente a diversidade dos componentes de cena, incluindo materiais dentro de uma mesma classe (p.ex. pinus e eucalipto). O MESMA produziu menores valores de RMSE e uma maior quantidade de pixels modelados na cena (85% contra 55%) do que o SMA; (4) o VIPER mostrou-se uma ferramenta bastante eficaz para seleção dos MRs e geração dos modelos. Os resultados, como um todo, demonstraram o potencial da aplicação dos modelos MESMA com dados hiperespectrais do sensor Hyperion/EO-1, mesmo considerando a baixa relação sinal/ruído do instrumento, especialmente no infravermelho de ondas curtas (SWIR). / The objective of this work was to evaluate the potential use of the Hyperion/Earth Observing One (EO-1) hyperspectral data and of the MESMA (Multiple Endmember Spectral Mixture Analysis) and SMA (Spectral Mixture Analysis) mixture models to discriminate land covers in the Rio Grande do Sul state, South Brazil. MESMA differs from SMA because it may use a variable number and type of endmembers in each pixel. The methodology involved: (a) pre-processing of Hyperion data and conversion of radiance values into atmospherically corrected surface reflectance images; (b) sequential use of the Minimum Noise Fraction (MNF), Pixel Purity Index (PPI) and n- Dimensional Visualizer techniques, in the 454-2334 nm range, for initial selection of a general group of candidate endmembers (first spectral library) and of another group of pixels used for model validation; (c) use of VIPER (Visualization and Image Processing for Environmental Research) Tools algorithm for final selection of endmembers from the first spectral library and from the use of the metrics EAR (Endmember Average RMSE), MASA (Minimum Average Spectral Angle) and CoB (Count Based Endmember Selection); (d) use of VIPER tools to obtain MESMA and SMA models; and (e) comparison of modeling results based on the inspection of fraction images and root mean square error (RMSE) values. Results showed that: (1) the sequential use of the MNF, PPI and n-D Visualizer techniques may comprise an initial step to identify candidate endmembers. Final selection was performed using a combination of EAR, MASA and CoB to minimize possible effects of low signalnoise ratio (SNR) of Hyperion; (2) the selected endmembers represented major scene components such as water (with chlorophyll, clear or bearing in suspended sediments), green vegetation (pinus, eucalyptus and grasslands) and soil (dunes and dry grasslands); (3) By using a variable number and type of endmembers, MESMA produced better results than SMA. When applied over the image, the validation dataset and compared with SMA, the four-endmember MESMA model (soil = dunes and dry grasslands; green vegetation = pinus, eucalyptus and grasslands; water = with chlorophyll, clear and with suspended sediments; shadow) described adequately the diversity of the scene components, including materials within the same class (e.g., pinus and eucalyptus). MESMA produced lower RMSE values and greater number of modeled pixels (85% versus 55%) than SMA; (5) the VIPER tools seems to be an interesting approach for endmember selection and spectral mixture model generation. Results, as a whole, demonstrated the potential use of the MESMA with Hyperion/EO-1 hyperspectral data, even considering the low SNR of the instrument, especially in the shortwave infrared (SWIR).

Le démélange spectral est un des sujets majeurs de l’analyse d’images hyperspectrales. Ce problème consiste à identifier les composants macroscopiques présents dans une image hyperspectrale et à quantifier les proportions (ou abondances) de ces matériaux dans tous les pixels de l’image. La plupart des algorithmes de démélange suppose un modèle de mélange linéaire qui est souvent considéré comme une approximation au premier ordre du mélange réel. Cependant, le modèle linéaire peut ne pas être adapté pour certaines images associées par exemple à des scènes engendrant des trajets multiples (forêts, zones urbaines) et des modèles non-linéaires plus complexes doivent alors être utilisés pour analyser de telles images. Le but de cette thèse est d’étudier de nouveaux modèles de mélange non-linéaires et de proposer des algorithmes associés pour l’analyse d’images hyperspectrales. Dans un premier temps, un modèle paramétrique post-non-linéaire est étudié et des algorithmes d’estimation basés sur ce modèle sont proposés. Les connaissances a priori disponibles sur les signatures spectrales des composants purs, sur les abondances et les paramètres de la non-linéarité sont exploitées à l’aide d’une approche bayesienne. Le second modèle étudié dans cette thèse est basé sur l’approximation de la variété non-linéaire contenant les données observées à l’aide de processus gaussiens. L’algorithme de démélange associé permet d’estimer la relation non-linéaire entre les abondances des matériaux et les pixels observés sans introduire explicitement les signatures spectrales des composants dans le modèle de mélange. Ces signatures spectrales sont estimées dans un second temps par prédiction à base de processus gaussiens. La prise en compte d’effets non-linéaires dans les images hyperspectrales nécessite souvent des stratégies de démélange plus complexes que celles basées sur un modèle linéaire. Comme le modèle linéaire est souvent suffisant pour approcher la plupart des mélanges réels, il est intéressant de pouvoir détecter les pixels ou les régions de l’image où ce modèle linéaire est approprié. On pourra alors, après cette détection, appliquer les algorithmes de démélange non-linéaires aux pixels nécessitant réellement l’utilisation de modèles de mélange non-linéaires. La dernière partie de ce manuscrit se concentre sur l’étude de détecteurs de non-linéarités basés sur des modèles linéaires et non-linéaires pour l’analyse d’images hyperspectrales. Les méthodes de démélange non-linéaires proposées permettent d’améliorer la caractérisation des images hyperspectrales par rapport au méthodes basées sur un modèle linéaire. Cette amélioration se traduit en particulier par une meilleure erreur de reconstruction des données. De plus, ces méthodes permettent de meilleures estimations des signatures spectrales et des abondances quand les pixels résultent de mélanges non-linéaires. Les résultats de simulations effectuées sur des données synthétiques et réelles montrent l’intérêt d’utiliser des méthodes de détection de non-linéarités pour l’analyse d’images hyperspectrales. En particulier, ces détecteurs peuvent permettre d’identifier des composants très peu représentés et de localiser des régions où les effets non-linéaires sont non-négligeables (ombres, reliefs,...). Enfin, la considération de corrélations spatiales dans les images hyperspectrales peut améliorer les performances des algorithmes de démélange non-linéaires et des détecteurs de non-linéarités. / Spectral unmixing is one the major issues arising when analyzing hyperspectral images. It consists of identifying the macroscopic materials present in a hyperspectral image and quantifying the proportions of these materials in the image pixels. Most unmixing techniques rely on a linear mixing model which is often considered as a first approximation of the actual mixtures. However, the linear model can be inaccurate for some specific images (for instance images of scenes involving multiple reflections) and more complex nonlinear models must then be considered to analyze such images. The aim of this thesis is to study new nonlinear mixing models and to propose associated algorithms to analyze hyperspectral images. First, a ost-nonlinear model is investigated and efficient unmixing algorithms based on this model are proposed. The prior knowledge about the components present in the observed image, their proportions and the nonlinearity parameters is considered using Bayesian inference. The second model considered in this work is based on the approximation of the nonlinear manifold which contains the observed pixels using Gaussian processes. The proposed algorithm estimates the relation between the observations and the unknown material proportions without explicit dependency on the material spectral signatures, which are estimated subsequentially. Considering nonlinear effects in hyperspectral images usually requires more complex unmixing strategies than those assuming linear mixtures. Since the linear mixing model is often sufficient to approximate accurately most actual mixtures, it is interesting to detect pixels or regions where the linear model is accurate. This nonlinearity detection can be applied as a pre-processing step and nonlinear unmixing strategies can then be applied only to pixels requiring the use of nonlinear models. The last part of this thesis focuses on new nonlinearity detectors based on linear and nonlinear models to identify pixels or regions where nonlinear effects occur in hyperspectral images. The proposed nonlinear unmixing algorithms improve the characterization of hyperspectral images compared to methods based on a linear model. These methods allow the reconstruction errors to be reduced. Moreover, these methods provide better spectral signature and abundance estimates when the observed pixels result from nonlinear mixtures. The simulation results conducted on synthetic and real images illustrate the advantage of using nonlinearity detectors for hyperspectral image analysis. In particular, the proposed detectors can identify components which are present in few pixels (and hardly distinguishable) and locate areas where significant nonlinear effects occur (shadow, relief, ...). Moreover, it is shown that considering spatial correlation in hyperspectral images can improve the performance of nonlinear unmixing and nonlinearity detection algorithms.

Nessa dissertação é investigada e testada uma metodologia para otimizar os parâmetros do kernel do classificador Support Vector Machines (SVM). Experimentos são realizados utilizando dados de imagens em alta dimensão. Imagens em alta dimensão abrem novas possibilidades para a classificação de imagens de sensoriamento remoto que capturam cenas naturais. É sabido que classes que são espectralmente muito similares, i.e, classes que possuem vetores de média muito próximos podem não obstante serem separadas com alto grau de acurácia em espaço de alta dimensão, desde que a matriz de covariância apresente diferenças significativas. O uso de dados de imagens em alta dimensão pode apresentar, no entanto, alguns desafios metodológicos quando aplicado um classificador paramétrico como o classificador de Máxima Verossimilhança Gaussiana. Conforme aumenta a dimensionalidade dos dados, o número de parâmetros a serem estimados a partir de um número geralmente limitado de amostras de treinamento também aumenta. Esse fato pode ocasionar estimativas pouco confiáveis, que por sua vez resultam em baixa acurácia na imagem classificada. Existem diversos abordagens propostas na literatura para minimizar esse problema. Os classificadores não paramétricos podem ser uma boa alternativa para mitigar esse problema. O SVM atualmente tem sido investigado na classificação de dados de imagens em alta-dimensão com número limitado de amostras de treinamento. Para que o classificador SVM seja utilizado com sucesso é necessário escolher uma função de kernel adequada, bem como os parâmetros dessa função. O kernel RBF tem sido frequentemente mencionado na literatura por obter bons resultados na classificação de imagens de sensoriamento remoto. Neste caso, dois parâmetro devem ser escolhidos para o classificador SVM: (1) O parâmetro de margem (C) que determina um ponto de equilíbrio razoável entre a maximização da margem e a minimização do erro de classificação, e (2) o parâmetro que controla o raio do kernel RBF. Estes dois parâmetros podem ser vistos como definindo um espaço de busca. O problema nesse caso consiste em procurar o ponto ótimo que maximize a acurácia do classificador SVM. O método de Busca em Grade é baseado na exploração exaustiva deste espaço de busca. Esse método é proibitivo do ponto de vista do tempo de processamento, sendo utilizado apenas com propósitos comparativos. Na prática os métodos heurísticos são a abordagem mais utilizada, proporcionado níveis aceitáveis de acurácia e tempo de processamento. Na literatura diversos métodos heurísticos são aplicados ao problema de classificação de forma global, i.e, os valores selecionados são aplicados durante todo processo de classificação. Esse processo, no entanto, não considera a diversidade das classes presentes nos dados. Nessa dissertação investigamos a aplicação da heurística Simulated Annealing (Recozimento Simulado) para um problema de múltiplas classes usando o classificador SVM estruturado como uma arvore binária. Seguindo essa abordagem, os parâmetros são estimados em cada nó da arvore binária, resultado em uma melhora na acurácia e tempo razoável de processamento. Experimentos são realizados utilizando dados de uma imagem hiperespectral disponível, cobrindo uma área de teste com controle terrestre bastante confiável. / In this dissertation we investigate and test a methodology to optimize the kernel parameters in a Support Vector Machines classifier. Experiments were carried out using remote sensing high-dimensional image data. High dimensional image data opens new possibilities in the classification of remote sensing image data covering natural scenes. It is well known that classes that are spectrally very similar, i.e., classes that show very similar mean vectors can notwithstanding be separated with an high degree of accuracy in high dimensional spaces, provided that their covariance matrices differ significantly. The use of high-dimensional image data may present, however, some drawbacks when applied in parametric classifiers such as the Gaussian Maximum Likelihood classifier. As the data dimensionality increases, so does the number of parameters to be estimated from a generally limited number of training samples. This fact results in unreliable estimates for the parameters, which in turn results in low accuracy in the classified image. There are several approaches proposed in the literature to minimize this problem. Non-parametric classifiers may provide a sensible way to overcome this problem. Support Vector Machines (SVM) have been more recently investigated in the classification of high-dimensional image data with a limited number of training samples. To achieve this end, a proper kernel function has to be implemented in the SVM classifier and the respective parameters selected properly. The RBF kernel has been frequently mentioned in the literature as providing good results in the classification of remotely sensed data. In this case, two parameters must be chosen in the SVM classification: (1) the margin parameter (C) that determines the trade-off between the maximization of the margin in the SVM and minimization of the classification error, and (2) the parameter that controls the radius in the RBF kernel. These two parameters can be seen as defining a search space, The problem here consists in finding an optimal point that maximizes the accuracy in the SVM classifier. The Grid Search approach is based on an exhaustive exploration in the search space. This approach results prohibitively time consuming and is used only for comparative purposes. In practice heuristic methods are the most commonly used approaches, providing acceptable levels of accuracy and computing time. In the literature several heuristic methods are applied to the classification problem in a global fashion, i.e., the selected values are applied to the entire classification process. This procedure, however, does not take into consideration the diversity of the classes present in the data. In this dissertation we investigate the application of Simulated Annealing to a multiclass problem using the SVM classifier structured as a binary tree. Following this proposed approach, the parameters are estimated at every level of the binary tree, resulting in better accuracy and a reasonable computing time. Experiments are done using a set of hyperspectral image data, covering a test area with very reliable ground control available.

O objetivo do presente trabalho foi avaliar o uso potencial dos dados hiperespectrais do sensor orbital Hyperion/Earth Observing One (EO-1) e dos modelos de mistura espectral MESMA (Multiple Endmember Spectral Mixture Analysis) e SMA (Spectral Mixture Analysis) para discriminação de classes de cobertura da Planície Costeira do Rio Grande do Sul. O modelo MESMA difere do SMA por permitir que o número e o tipo de Membros de Referência (MRs), assim como sua abundância, variem pixel a pixel. A abordagem metodológica utilizada envolveu as seguintes etapas: (a) préprocessamento dos dados Hyperion e conversão dos valores de radiância para imagens atmosfericamente corrigidas de reflectância de superfície; (b) uso seqüencial das técnicas Minimum Noise Fraction (MNF), Pixel Purity Index (PPI) e Visualizador n- Dimensional, no intervalo de 454 a 2334 nm, para seleção inicial de um grupo de pixels candidatos a MRs (primeira biblioteca espectral) e de um outro grupo para fins de validação dos modelos; (c) uso do aplicativo VIPER (Visualization and Image Processing for Environmental Research) Tools para refinamento da primeira biblioteca espectral e seleção final dos MRs, utilizando as métricas EAR (Endmember Average RMSE), MASA (Minimum Average Spectral Angle) e CoB (Count Based Endmember Selection); (d) geração dos modelos MESMA e SMA com o VIPER Tools; e (e) comparação dos resultados dos modelos com base nas imagens-fração e nos valores de erro médio quadrático (RMSE). Os resultados obtidos mostraram que: (1) o uso seqüencial das técnicas MNF, PPI e Visualizador n-Dimensional pode constituir uma etapa inicial para identificar pixels candidatos a MRs, cuja seleção final pode ser feita com as métricas EAR, MASA e CoB. Usadas de forma combinada, essas métricas minimizam possíveis efeitos da baixa relação sinal-ruído do Hyperion; (2) os MRs selecionados representaram os principais componentes de cena como “água” (com clorofila, límpida e com sedimentos em suspensão), “vegetação verde” (pinus, eucalipto e gramíneas) e “solo” (dunas e campo seco); (3) Por utilizar número e tipo variáveis de MRs, o modelo MESMA produziu melhores resultados que o SMA. Quando aplicado sobre a imagem, sobre a amostra de validação e quando comparado com o SMA, o modelo MESMA de 4 componentes (Solo = dunas e campo Seco; vegetação verde = pinus, eucalipto e gramíneas; água = com Sedimentos em suspensão, sem Sedimentos e com clorofila; sombra) descreveu adequadamente a diversidade dos componentes de cena, incluindo materiais dentro de uma mesma classe (p.ex. pinus e eucalipto). O MESMA produziu menores valores de RMSE e uma maior quantidade de pixels modelados na cena (85% contra 55%) do que o SMA; (4) o VIPER mostrou-se uma ferramenta bastante eficaz para seleção dos MRs e geração dos modelos. Os resultados, como um todo, demonstraram o potencial da aplicação dos modelos MESMA com dados hiperespectrais do sensor Hyperion/EO-1, mesmo considerando a baixa relação sinal/ruído do instrumento, especialmente no infravermelho de ondas curtas (SWIR). / The objective of this work was to evaluate the potential use of the Hyperion/Earth Observing One (EO-1) hyperspectral data and of the MESMA (Multiple Endmember Spectral Mixture Analysis) and SMA (Spectral Mixture Analysis) mixture models to discriminate land covers in the Rio Grande do Sul state, South Brazil. MESMA differs from SMA because it may use a variable number and type of endmembers in each pixel. The methodology involved: (a) pre-processing of Hyperion data and conversion of radiance values into atmospherically corrected surface reflectance images; (b) sequential use of the Minimum Noise Fraction (MNF), Pixel Purity Index (PPI) and n- Dimensional Visualizer techniques, in the 454-2334 nm range, for initial selection of a general group of candidate endmembers (first spectral library) and of another group of pixels used for model validation; (c) use of VIPER (Visualization and Image Processing for Environmental Research) Tools algorithm for final selection of endmembers from the first spectral library and from the use of the metrics EAR (Endmember Average RMSE), MASA (Minimum Average Spectral Angle) and CoB (Count Based Endmember Selection); (d) use of VIPER tools to obtain MESMA and SMA models; and (e) comparison of modeling results based on the inspection of fraction images and root mean square error (RMSE) values. Results showed that: (1) the sequential use of the MNF, PPI and n-D Visualizer techniques may comprise an initial step to identify candidate endmembers. Final selection was performed using a combination of EAR, MASA and CoB to minimize possible effects of low signalnoise ratio (SNR) of Hyperion; (2) the selected endmembers represented major scene components such as water (with chlorophyll, clear or bearing in suspended sediments), green vegetation (pinus, eucalyptus and grasslands) and soil (dunes and dry grasslands); (3) By using a variable number and type of endmembers, MESMA produced better results than SMA. When applied over the image, the validation dataset and compared with SMA, the four-endmember MESMA model (soil = dunes and dry grasslands; green vegetation = pinus, eucalyptus and grasslands; water = with chlorophyll, clear and with suspended sediments; shadow) described adequately the diversity of the scene components, including materials within the same class (e.g., pinus and eucalyptus). MESMA produced lower RMSE values and greater number of modeled pixels (85% versus 55%) than SMA; (5) the VIPER tools seems to be an interesting approach for endmember selection and spectral mixture model generation. Results, as a whole, demonstrated the potential use of the MESMA with Hyperion/EO-1 hyperspectral data, even considering the low SNR of the instrument, especially in the shortwave infrared (SWIR).

Submitted by GABRIELA TAKAHASHI MIYOSHI null (takahashi.gabi@gmail.com) on 2016-03-24T18:48:17Z No. of bitstreams: 1 MIYOSHI_GT_DISSERTACAO.pdf: 6445481 bytes, checksum: 7e46eb0d4d485bf0b3f7498d99fe9d65 (MD5) / Approved for entry into archive by Ana Paula Grisoto (grisotoana@reitoria.unesp.br) on 2016-03-24T20:29:25Z (GMT) No. of bitstreams: 1 miyoshi_gt_me_prud.pdf: 6445481 bytes, checksum: 7e46eb0d4d485bf0b3f7498d99fe9d65 (MD5) / Made available in DSpace on 2016-03-24T20:29:25Z (GMT). No. of bitstreams: 1 miyoshi_gt_me_prud.pdf: 6445481 bytes, checksum: 7e46eb0d4d485bf0b3f7498d99fe9d65 (MD5) Previous issue date: 2016-02-29 / Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) / Florestas têm importante papel na manutenção da biodiversidade, retenção de carbono e regulação do regime hidrológico, além de garantir proteção ao solo e às fontes d’água. Podem ser classificadas em diferentes estádios de desenvolvimento, caracterizados pela presença de espécies secundárias e clímax. Atualmente, no Brasil, as florestas estão reduzidas em fragmentos espalhados em diversas regiões do país sendo seu monitoramento necessário para realização de planos de manejo. Uma das formas de realizar o monitoramento florestal é utilizando o Sensoriamento Remoto hiperespectral, que fornece informação espectral detalhada dos alvos as quais são úteis para a discriminação das espécies de vegetação que compõem o remanescente florestal. Sensores hiperespectrais acoplados a VANTs (Veículos Aéreos Não Tripulados) possibilitam a aquisição de dados para posterior delimitação das copas das espécies de vegetação. A Mata Atlântica, bioma rico em biodiversidade, está distribuída de norte a sul do Brasil, sendo classificada conforme a localização e características de cada formação florestal, dentre elas a Mata Atlântica de Interior. O objetivo desse trabalho é a caracterização espectral de espécies de vegetação em nível foliar e de copa para contribuir com informações que possam ser utilizadas para o monitoramento florestal. Foram adquiridas imagens hiperespectrais com câmara baseada no Interferômetro de Fabry-Perot acoplada em VANT. As imagens foram adquiridas na gleba Ponte Branca, pertencente à Estação Ecológica Mico-Leão-Preto. O processamento das imagens considerou 5 diferentes correções que permitiram mostrar a importância da geometria de aquisição das imagens e do ajustamento radiométrico em bloco. Copas de 12 espécies de vegetação foram delimitadas manualmente no mosaico de imagens gerado e nelas foram medidos valores de Fator de Reflectância Hemisférico Cônico. A caracterização espectral em nível foliar de 16 espécies de vegetação foi realizada em laboratório utilizando espectrorradiômetro. Por meio da análise de agrupamento, verificou-se a similaridade entre as respostas espectrais de tais espécies, tanto em nível de copa como foliar. Para minimizar a similaridade entre tais respostas, foram aplicados e normalizados 7 índices de vegetação. Por fim, utilizando os índices que apresentaram menor correlação entre si, uma nova análise de agrupamento foi realizada onde se verificou que a similaridade entre as espécies foi atenuada. / Forests have an important role to support biodiversity, carbon stocks and water regime. In addition, provide fundamental protection to soil and water resources. Pioneers and climax species characterize successional stages of forest. In Brazil, forests are reduced to fragments spread out over the country, being their monitoring necessary to perform management plans. Hyperspectral Remote Sensing provides detailed spectral information about targets and is feasible to discriminate trees species. Hyperspectral sensor attached to UAVs (Unmanned Aerial Vehicles) makes possible the delineation of trees canopies. The Atlantic Forest, biome rich in biodiversity, is distributed from north to south in Brazil, being classified according to the different locations and characteristics, such as the Interior Atlantic Forest. The main objective of this project is spectral characterization of tree species in leaf and canopy level to contribute with forest monitoring. Hyperspectral images acquired with camera based on Fabry-Perot Interferometer coupled to an UAV were acquired. The interest area, Ponte Branca, belongs to the ecological station called Estação Ecológica Mico-Leão-Preto in the western region of São Paulo State. Imaging process where realized with 5 different corrections showing the importance of geometry during image acquisition and radiometric block adjustment. Trees canopies from 12 species were manually delimited in the images mosaic and Hemispherical Conical Reflectance Factor were obtained. Leaf spectral characterization was realized in laboratory using spectrorradiometer. Clustering analyses were applied to verify similarity between spectral responses of species, in canopy and leaf level. 7 vegetation indexes were applied and normalized in order to reduce the similarity between the spectral responses. Lastly, a new clustering analyses was realized using the less correlated normalized indexes, concluding that the similarity between species was reduced. / CNPq: 130871/2014-1

The aim of this thesis is to study and evaluate the application of hyperspectral image analysis as a non-destructive analysis method for historical mortars. This method was applied on 35 sampled mortars in varying sizes and type from the inner walls of the fortified medieval city Carcassonne. By using near infrared spectroscopy and classifying the complex multivariate data by applying the SIMCA method (Soft Independent Modelling of Class Analogies) it is possible to conduct an in depth analysis of the samples. This can then further our understanding about the construction phases as well as construction techniques used as indicated through the chemometric analysis that can identify and group the mortars in accordance to raw material and transformation process. From this could four distinct groups be found in the PCA models, two Roman periods and two high medieval periods, allowing to study Carcassonne prior to and after its enclosure. A find from the first Roman period indicates on a bathhouse or public building existing prior to the construction of the defensive wall, leading to the hypothesis that maybe more parts of the inner wall might contain older structures like this. The application of hyperspectral image analysis on historical mortars has proven itself a useful tool and simple method for studying mortars. / Målet med denna uppsats var att studera och evaluera applikationen av hyperspektral bildanalys som en icke-destruktiv analysmetod på historiskt murbruk. Instrumentet applicerades på 35 murbruksprover i varierande storlek och typ tagna från de inre murarna av den befästa medeltida staden Carcassonne. Med nära infraröd spektroskopi och klassificering av den multivariata genom SIMCA metoden (Soft Independent Modelling of Class Analogies) var det möjligt att göra en djupgående analys av proverna. Detta tillvägagångssätt kan då främja vår förståelse om stadens konstruktionsfaser och konstruktionstekniker som indikeras genom den chemometriska analysen som kan identifiera murbruket utefter råmaterial samt hur murbruket tillverkats. Från dessa metoder kunde fyra distinkta grupper finnas i PCA modellerna, två romerska perioder och två högmedeltida perioder, vilket öppnade för tolkning både innan och efter stadsmurarna rests. Ett fynd från den första romerska perioden indikerar på förekomsten av ett badhus eller publik byggnad vars väggar sedan återanvänts vid konstruktionen av den inre stadsmuren. Detta fynd leder till hypotesen att potentiellt andra delar av den inre stadsmuren kan innehålla väggar från äldre byggnader som denna. Applikationen av hyperspektral bildanalys på historiskt murbruk har påvisat sig ett användbart verktyg och simpel metod för att studera murbruk.

Nessa dissertação é investigada e testada uma metodologia para otimizar os parâmetros do kernel do classificador Support Vector Machines (SVM). Experimentos são realizados utilizando dados de imagens em alta dimensão. Imagens em alta dimensão abrem novas possibilidades para a classificação de imagens de sensoriamento remoto que capturam cenas naturais. É sabido que classes que são espectralmente muito similares, i.e, classes que possuem vetores de média muito próximos podem não obstante serem separadas com alto grau de acurácia em espaço de alta dimensão, desde que a matriz de covariância apresente diferenças significativas. O uso de dados de imagens em alta dimensão pode apresentar, no entanto, alguns desafios metodológicos quando aplicado um classificador paramétrico como o classificador de Máxima Verossimilhança Gaussiana. Conforme aumenta a dimensionalidade dos dados, o número de parâmetros a serem estimados a partir de um número geralmente limitado de amostras de treinamento também aumenta. Esse fato pode ocasionar estimativas pouco confiáveis, que por sua vez resultam em baixa acurácia na imagem classificada. Existem diversos abordagens propostas na literatura para minimizar esse problema. Os classificadores não paramétricos podem ser uma boa alternativa para mitigar esse problema. O SVM atualmente tem sido investigado na classificação de dados de imagens em alta-dimensão com número limitado de amostras de treinamento. Para que o classificador SVM seja utilizado com sucesso é necessário escolher uma função de kernel adequada, bem como os parâmetros dessa função. O kernel RBF tem sido frequentemente mencionado na literatura por obter bons resultados na classificação de imagens de sensoriamento remoto. Neste caso, dois parâmetro devem ser escolhidos para o classificador SVM: (1) O parâmetro de margem (C) que determina um ponto de equilíbrio razoável entre a maximização da margem e a minimização do erro de classificação, e (2) o parâmetro que controla o raio do kernel RBF. Estes dois parâmetros podem ser vistos como definindo um espaço de busca. O problema nesse caso consiste em procurar o ponto ótimo que maximize a acurácia do classificador SVM. O método de Busca em Grade é baseado na exploração exaustiva deste espaço de busca. Esse método é proibitivo do ponto de vista do tempo de processamento, sendo utilizado apenas com propósitos comparativos. Na prática os métodos heurísticos são a abordagem mais utilizada, proporcionado níveis aceitáveis de acurácia e tempo de processamento. Na literatura diversos métodos heurísticos são aplicados ao problema de classificação de forma global, i.e, os valores selecionados são aplicados durante todo processo de classificação. Esse processo, no entanto, não considera a diversidade das classes presentes nos dados. Nessa dissertação investigamos a aplicação da heurística Simulated Annealing (Recozimento Simulado) para um problema de múltiplas classes usando o classificador SVM estruturado como uma arvore binária. Seguindo essa abordagem, os parâmetros são estimados em cada nó da arvore binária, resultado em uma melhora na acurácia e tempo razoável de processamento. Experimentos são realizados utilizando dados de uma imagem hiperespectral disponível, cobrindo uma área de teste com controle terrestre bastante confiável. / In this dissertation we investigate and test a methodology to optimize the kernel parameters in a Support Vector Machines classifier. Experiments were carried out using remote sensing high-dimensional image data. High dimensional image data opens new possibilities in the classification of remote sensing image data covering natural scenes. It is well known that classes that are spectrally very similar, i.e., classes that show very similar mean vectors can notwithstanding be separated with an high degree of accuracy in high dimensional spaces, provided that their covariance matrices differ significantly. The use of high-dimensional image data may present, however, some drawbacks when applied in parametric classifiers such as the Gaussian Maximum Likelihood classifier. As the data dimensionality increases, so does the number of parameters to be estimated from a generally limited number of training samples. This fact results in unreliable estimates for the parameters, which in turn results in low accuracy in the classified image. There are several approaches proposed in the literature to minimize this problem. Non-parametric classifiers may provide a sensible way to overcome this problem. Support Vector Machines (SVM) have been more recently investigated in the classification of high-dimensional image data with a limited number of training samples. To achieve this end, a proper kernel function has to be implemented in the SVM classifier and the respective parameters selected properly. The RBF kernel has been frequently mentioned in the literature as providing good results in the classification of remotely sensed data. In this case, two parameters must be chosen in the SVM classification: (1) the margin parameter (C) that determines the trade-off between the maximization of the margin in the SVM and minimization of the classification error, and (2) the parameter that controls the radius in the RBF kernel. These two parameters can be seen as defining a search space, The problem here consists in finding an optimal point that maximizes the accuracy in the SVM classifier. The Grid Search approach is based on an exhaustive exploration in the search space. This approach results prohibitively time consuming and is used only for comparative purposes. In practice heuristic methods are the most commonly used approaches, providing acceptable levels of accuracy and computing time. In the literature several heuristic methods are applied to the classification problem in a global fashion, i.e., the selected values are applied to the entire classification process. This procedure, however, does not take into consideration the diversity of the classes present in the data. In this dissertation we investigate the application of Simulated Annealing to a multiclass problem using the SVM classifier structured as a binary tree. Following this proposed approach, the parameters are estimated at every level of the binary tree, resulting in better accuracy and a reasonable computing time. Experiments are done using a set of hyperspectral image data, covering a test area with very reliable ground control available.