Dissertations / Theses on the topic 'Remote Sensing Data Fusion (RSDF)'

The growing Landsat data archive represents more than four decades of continuous Earth observation. Landsat's role in scientific analysis has increased dramatically in recent years as a result of the open-access policy of the U.S. Geological Survey (USGS). However, this rich data record suffers from relatively low temporal resolution due to the 16-day revisit period of each Landsat satellite. To estimate Landsat images at other points in time, researchers have proposed data-fusion approaches that combine existing Landsat data with images from other sensors, such as MODIS (Moderate Resolution Imaging Spectroradiometer) from the Terra and Aqua satellites. MODIS provides daily revisits, however, with a spatial resolution that is significantly lower than that of Landsat. Fusion of Landsat and MODIS is challenging because of differences in their spatial resolution, band designations, swath width, viewing angle and the noise level. Fusion is even more challenging for heterogeneous landscapes. In the first part of our work, the multiresolution analysis offered by the wavelet transform was explored as a suitable environment for Landsat and MODIS fusion. Our proposed Wavelet-based Spatiotemporal Adaptive Reflectance Fusion Model (WSTARFM) is the first model to merge Landsat and MODIS successfully. It handles the heterogeneity of the landscapes more effectively than the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) does. The system has been tested on simulated data and on actual data of two study areas in North Carolina. For a challenging heterogeneous study area near Greensboro, North Carolina, WSTARFM produced results with median R-squared values of 0.98 and 0.95 for the near-infrared band over deciduous forests and developed areas, respectively. Those results were obtained by withholding an actual Landsat image, and comparing it with a predicted version of the same image. These values represent an improvement over results obtained using the well-known STARFM technique. Similar improvements were obtained for the red band. For the second (homogeneous) study area, WSTARFM produced comparable prediction results to STARFM. In the second part of our work, Landsat-MODIS fusion has been explored from the temporal perspective. The fusion is performed on the Landsat and MODIS per-pixel time series. A new Multisensor Adaptive Time Series Fitting Model (MATSFM) is proposed. MATSFM is the first model to use mapped MODIS values to guide the fitting applied to the sparse Landsat time series. MATSFM produced results with median R-squared of 0.98 over the NDVI images of the first heterogeneous study area compared to 0.97 produced by STARFM. For the second study area, MATSFM also produced better prediction accuracy than STARFM.
Ph. D.

Throughout history floods have been part of the human experience. They are recurring phenomena that form a necessary and enduring feature of all river basin and lowland coastal systems. In an average year, they benefit millions of people who depend on them. In the more developed countries, major floods can be the largest cause of economic losses from natural disasters, and are also a major cause of disaster-related deaths in the less developed countries. Flood disaster mitigation research was conducted to determine how remotely sensed data can effectively be used to produce accurate flood plain maps (FPMs), and to identify/quantify the sources of error associated with such data. Differences were analyzed between flood maps produced by an automated remote sensing analysis tailored to the available satellite remote sensing datasets (rFPM), the 100-year flooded areas "predicted" by the Flood Insurance Rate Maps, and FPMs based on DEM and hydrological data (aFPM). Landuse/landcover was also examined to determine its influence on rFPM errors. These errors were identified and the results were integrated in a GIS to minimize landuse / landcover effects. Two substantial flood events were analyzed. These events were selected because of their similar characteristics (i.e., the existence of FIRM or Q3 data; flood data which included flood peaks, rating curves, and flood profiles; and DEM and remote sensing imagery.) Automatic feature extraction was determined to be an important component for successful flood analysis. A process network, in conjunction with domain specific information, was used to map raw remotely sensed data onto a representation that is more compatible with a GIS data model. From a practical point of view, rFPM provides a way to automatically match existing data models to the type of remote sensing data available for each event under investigation. Overall, results showed how remote sensing could contribute to the complex problem of flood management by providing an efficient way to revise the National Flood Insurance Program maps.

Lakes are vital components of the global biosphere, supporting complex ecosystems and playing important roles in the global biogeochemical cycle. However, they are vulnerable to the threat from climate change and their responses to climate forcing, eutrophication and other pressures, and their possibly confounding interactions, are not yet well understood. Monitoring lake health is therefore essential, in order to understand the changing patterns over space and time. Traditionally, in-situ data, which are collected directly from within lakes and analysed in laboratories, have been available for analysis. However, although these data are assumed to be accurate within measurement error, they are expensive to collect, so that few, if any, in-situ sampling locations are available for each lake, often with infrequent sampling at each location. On the other hand, remotely-sensed data, which are derived from reflectance measurements of the Earth's surface, obtained from satellites, have recently become widely available. These data have good spatial coverage of up to 300 metre resolution, covering entire lakes, often with a monthly-average time-scale, but they must firstly be calibrated with the in-situ data to ensure accuracy, before inferences are made. The data for this research were provided by the GloboLakes project (www.globolakes.ac.uk), which is a consortium research project that is investigating the state of lakes and their responses to environmental drivers on a global scale. The research primarily focusses on log(chlorophyll-a) data for Lake Balaton, in Hungary, and for the Great Lakes of North America. The key question of interest for this research is: ``How can data fusion be performed for in-situ and remotely-sensed lake water quality data, accounting for the spatiotemporal change of support between the point-location, point-time in-situ data and the grid-cell-scale, monthly-averaged remotely-sensed data, producing a fused dataset that takes accuracy from the in-situ data and spatial and temporal information from the remotely-sensed data?" In order to answer this question, this thesis presents the following work: An initial analysis of the data for Lake Balaton motivates the following work, by demonstrating the spatial and temporal patterns in the data, using mixed-effects models, generalised additive models, kriging and principal components analysis. Following the identification of statistical downscaling as an appropriate method for fusion of the data, statistical downscaling models are developed, specifically in the framework of Bayesian hierarchical models with spatially-varying coefficients, for the novel application to data for log(chlorophyll-a), producing fully calibrated maps of fused data across lake surfaces, with associated comprehensive uncertainty measures. Bivariate and multiple-lakes statistical downscaling models are developed and applied, motivated by the assumption that sharing information between variables and between lakes can improve the accuracy of model predictions. The statistically novel method of nonparametric statistical downscaling is developed, to account for both the spatial and temporal aspects of the change of support between the in-situ and remotely-sensed data. Using methodology from both functional data analysis and statistical downscaling, the model treats in-situ and remotely-sensed data at each location as observations of smooth functions over time, estimated using bases, with the basis coefficients related via a spatially-varying coefficient regression. This is computed within a Bayesian hierarchical model, enabling the calculation of comprehensive uncertainties. This thesis presents the background, motivation, model development and application of the novel method of nonparametric statistical downscaling, filling the gap in the literature of accounting for changing temporal support in statistical downscaling modelling. Results are presented throughout this thesis, to demonstrate the utility of the method for real lake water quality data.

Researchers now have unprecedented access to free Landsat data, enabling detailed monitoring of the Earth's land surface and vegetation.  There are gaps in the data, due in part to cloud cover. The gaps are aperiodic and localized, forcing any detailed multitemporal analysis based on Landsat data to compensate.   Harmonic regression approximates Landsat data for any point in time with minimal training images and reduced storage requirements.  In two study areas in North Carolina, USA, harmonic regression approaches were least as good at simulating missing data as STAR-FM for images from 2001.  Harmonic regression had an R^2"0.9 over three quarters of all pixels. It gave the highest R_Predicted^2 values on two thirds of the pixels.  Applying harmonic regression with the same number of harmonics to consecutive years yielded an improved fit, R^2"0.99 for most pixels.   We next demonstrate a change detection method based on exponentially weighted moving average (EWMA) charts of harmonic residuals. In the process, a data-driven cloud filter is created, enabling use of partially clouded data.  The approach is shown capable of detecting thins and subtle forest degradations in Alabama, USA, considerably finer than the Landsat spatial resolution in an on-the-fly fashion, with new images easily incorporated into the algorithm.  EWMA detection accurately showed the location, timing, and magnitude of 85% of known harvests in the study area, verified by aerial imagery.   We use harmonic regression to improve the precision of dynamic forest parameter estimates, generating a robust time series of vegetation index values.  These values are classified into strata maps in Alabama, USA, depicting regions of similar growth potential.  These maps are applied to Forest Service Forest Inventory and Analysis (FIA) plots, generating post-stratified estimates of static and dynamic forest parameters.  Improvements to efficiency for all parameters were such that a comparable random sample would require at least 20% more sampling units, with the improvement for the growth parameter requiring a 50% increase. These applications demonstrate the utility of harmonic regression for Landsat data.  They suggest further applications in environmental monitoring and improved estimation of landscape parameters, critical to improving large-scale models of ecosystems and climate effects.
Ph. D.

La humedad del suelo es la variable que regula los intercambios de agua, energía, y carbono entre la tierra y la atmósfera. Mediciones precisas de humedad son necesarias para una gestión sostenible de los recursos hídricos, para mejorar las predicciones meteorológicas y climáticas, y para la detección y monitorización de sequías e inundaciones. Esta tesis se centra en la medición de la humedad superficial de la Tierra desde el espacio, a escalas global y regional. Estudios teóricos y experimentales han demostrado que la teledetección pasiva de microondas en banda L es optima para la medición de humedad del suelo, debido a que la atmósfera es transparente a estas frecuencias, y a la relación directa de la emisividad del suelo con su contenido de agua. Sin embargo, el uso de la teledetección pasiva en banda L ha sido cuestionado en las últimas décadas, pues para conseguir la resolución temporal y espacial requeridas, un radiómetro convencional necesitaría una gran antena rotatoria, difícil de implementar en un satélite. Actualmente, hay tres principales propuestas para abordar este problema: (i) el uso de un radiómetro de apertura sintética, que es la solución implementada en la misión Soil Moisture and Ocean Salinity (SMOS) de la ESA, en órbita desde noviembre del 2009; (ii) el uso de un radiómetro ligero de grandes dimensiones y un rádar operando en banda L, que es la solución que ha adoptado la misión Soil Moisture Active Passive (SMAP) de la NASA, con lanzamiento previsto en 2014; (iii) el desarrollo de técnicas de desagregación de píxel que permitan mejorar la resolución espacial de las observaciones. La primera parte de la tesis se centra en el estudio del algoritmo de recuperación de humedad del suelo a partir de datos SMOS, que es esencial para obtener estimaciones de humedad con alta precisión. Se analizan diferentes configuraciones con datos simulados, considerando (i) la opción de añadir información a priori de los parámetros que dominan la emisión del suelo en banda L —humedad, rugosidad, temperatura del suelo, albedo y opacidad de la vegetación— con diferentes incertidumbres asociadas, y (ii) el uso de la polarización vertical y horizontal por separado, o del primer parámetro de Stokes. Se propone una configuración de recuperación de humedad óptima para SMOS. La resolución espacial de los radiómetros de SMOS y SMAP (40-50 km) es adecuada para aplicaciones globales, pero limita la aplicación de los datos en estudios regionales, donde se requiere una resolución de 1-10 km. La segunda parte de esta tesis contiene tres novedosas propuestas de mejora de resolución espacial de estos datos: • Se ha desarrollado un algoritmo basado en la deconvolución de los datos SMOS que permite mejorar la resolución espacial de las medidas. Los resultados de su aplicación a datos simulados y a datos obtenidos con un radiómetro aerotransportado muestran que es posible mejorar el producto de resolución espacial y resolución radiométrica de los datos. • Se presenta un algoritmo para mejorar la resolución espacial de las estimaciones de humedad de SMOS utilizando datos MODIS en el visible/infrarrojo. Los resultados de su aplicación a algunas de las primeras imágenes de SMOS indican que la variabilidad espacial de la humedad del suelo se puede capturar a 32, 16 y 8 km. • Un algoritmo basado en detección de cambios para combinar los datos del radiómetro y el rádar de SMAP en un producto de humedad a 10 km ha sido desarrollado y validado utilizando datos simulados y datos experimentales aerotransportados. Este trabajo se ha desarrollado en el marco de las actividades preparatorias de SMOS y SMAP, los dos primeros satélites dedicados a la monitorización de la variación temporal y espacial de la humedad de la Tierra. Los resultados presentados contribuyen a la obtención de estimaciones de humedad del suelo con la precisión y la resolución espacial necesarias para un mejor conocimiento del ciclo del agua y una mejor gestión de los recursos hídricos.
Soil moisture is a key state variable of the Earth's system; it is the main variable that links the Earth's water, energy and carbon cycles. Accurate observations of the Earth's changing soil moisture are needed to achieve sustainable land and water management, and to enhance weather and climate forecasting skill, flood prediction and drought monitoring. This Thesis focuses on measuring the Earth's surface soil moisture from space at global and regional scales. Theoretical and experimental studies have proven that L-band passive remote sensing is optimal for soil moisture sensing due to its all-weather capabilities and the direct relationship between soil emissivity and soil water content under most vegetation covers. However, achieving a temporal and spatial resolution that could satisfy land applications has been a challenge to passive microwave remote sensing in the last decades, since real aperture radiometers would need a large rotating antenna, which is difficult to implement on a spacecraft. Currently, there are three main approaches to solving this problem: (i) the use of an L-band synthetic aperture radiometer, which is the solution implemented in the ESA Soil Moisture and Ocean Salinity (SMOS) mission, launched in November 2009; (ii) the use of a large lightweight radiometer and a radar operating at L-band, which is the solution adopted by the NASA Soil Moisture Active Passive (SMAP) mission, scheduled for launch in 2014; (iii) the development of pixel disaggregation techniques that could enhance the spatial resolution of the radiometric observations. The first part of this work focuses on the analysis of the SMOS soil moisture inversion algorithm, which is crucial to retrieve accurate soil moisture estimations from SMOS measurements. Different retrieval configurations have been examined using simulated SMOS data, considering (i) the option of adding a priori information from parameters dominating the land emission at L-band —soil moisture, roughness, and temperature, vegetation albedo and opacity— with different associated uncertainties and (ii) the use of vertical and horizontal polarizations separately, or the first Stokes parameter. An optimal retrieval configuration for SMOS is suggested. The spatial resolution of SMOS and SMAP radiometers (~ 40-50 km) is adequate for global applications, but is a limiting factor to its application in regional studies, where a resolution of 1-10 km is needed. The second part of this Thesis contains three novel downscaling approaches for SMOS and SMAP: • A deconvolution scheme for the improvement of the spatial resolution of SMOS observations has been developed, and results of its application to simulated SMOS data and airborne field experimental data show that it is feasible to improve the product of the spatial resolution and the radiometric sensitivity of the observations by 49% over land pixels and by 30% over sea pixels. • A downscaling algorithm for improving the spatial resolution of SMOS-derived soil moisture estimates using higher resolution MODIS visible/infrared data is presented. Results of its application to some of the first SMOS images show the spatial variability of SMOS-derived soil moisture observations is effectively captured at the spatial resolutions of 32, 16, and 8 km. • A change detection approach for combining SMAP radar and radiometer observations into a 10 km soil moisture product has been developed and validated using SMAP-like observations and airborne field experimental data. This work has been developed within the preparatory activities of SMOS and SMAP, the two first-ever satellites dedicated to monitoring the temporal and spatial variation on the Earth's soil moisture. The results presented contribute to get the most out of these vital observations, that will further our understanding of the Earth's water cycle, and will lead to a better water resources management.

Multi-spectral imagery provides a robust and low-cost dataset for assessing wetland extent and quality over broad regions and is frequently used for wetland inventories. However in forested wetlands, hydrology is obscured by tree canopy making it difficult to detect with multi-spectral imagery alone. Because of this, classification of forested wetlands often includes greater errors than that of other wetlands types. Elevation and terrain derivatives have been shown to be useful for modelling wetland hydrology. But, few studies have addressed the use of LiDAR intensity data detecting hydrology in forested wetlands. Due the tendency of LiDAR signal to be attenuated by water, this research proposed the fusion of LiDAR intensity data with LiDAR elevation, terrain data, and aerial imagery, for the detection of forested wetland hydrology. We examined the utility of LiDAR intensity data and determined whether the fusion of Lidar derived data with multispectral imagery increased the accuracy of forested wetland classification compared with a classification performed with only multi-spectral image. Four classifications were performed: Classification A - All Imagery, Classification B - All LiDAR, Classification C - LiDAR without Intensity, and Classification D - Fusion of All Data. These classifications were performed using random forest and each resulted in a 3-foot resolution thematic raster of forested upland and forested wetland locations in Vermilion County, Illinois. The accuracies of these classifications were compared using Kappa Coefficient of Agreement. Importance statistics produced within the random forest classifier were evaluated in order to understand the contribution of individual datasets. Classification D, which used the fusion of LiDAR and multi-spectral imagery as input variables, had moderate to strong agreement between reference data and classification results. It was found that Classification A performed using all the LiDAR data and its derivatives (intensity, elevation, slope, aspect, curvatures, and Topographic Wetness Index) was the most accurate classification with Kappa: 78.04%, indicating moderate to strong agreement. However, Classification C, performed with LiDAR derivative without intensity data had less agreement than would be expected by chance, indicating that LiDAR contributed significantly to the accuracy of Classification B.

Because the earth's cryosphere influences global weather patterns and climate, the scientific community has had great interest in monitoring this important region. Microwave remote sensing has proven to be a useful tool in estimating sea and glacial ice surface characteristics with both scatterometers and radiometers exhibiting high sensitivity to important ice properties. This dissertation presents an array of studies focused on extracting key surface features from multisensor microwave data sets. First, several enhanced resolution image reconstruction issues are addressed. Among these are the optimization of the scatterometer image reconstruction (SIR) algorithm for NASA scatterometer (NSCAT) data, an analysis of Ku-band azimuthal modulation in Antarctica, and inter-sensor European Remote Sensing Satellite (ERS) calibration. Next, various methods for the removal of atmospheric distortions in image reconstruction of passive radiometer observations are considered. An automated algorithm is proposed which determines the spatial extent of sea ice in the Arctic and Antarctic regions from NSCAT data. A multisensor iterative sea ice statistical classification method which adapts to the temporally varying signatures of ice types is developed. The sea ice extent and classification algorithms are adopted for current SeaWinds scatterometer data sets. Finally, the automated inversion of large-scale forward electromagnetic scattering of models is considered and used to study the temporal evolution of the scattering properties of polar sea ice.

This dissertation investigated the practicality and expediency of applying remote sensing data fusion products to the analysis of dryland vegetation phenology. The objective of the first study was to verify the quality of the output products of the spatial and temporal adaptive reflectance fusion method (STARFM) over the dryland Arizona study site. Synthetic 30 m resolution images were generated from Landsat-5 Thematic Mapper (TM) data and a range of 500 m Moderate Resolution Imaging Spectroradiometer (MODIS) surface reflectance datasets and assessed via correlation analysis with temporally coincident Landsat-5 imagery. The accuracy of the results (0.61 < R2 < 0.94) justified subsequent use of STARFM data in this environment, particularly when the imagery were generated from Nadir Bi-directional Reflectance Factor (BRDF)-Adjusted Reflectance (NBAR) MODIS datasets. The primary objective of the second study was to assess whether synthetic Landsat data could contribute meaningful information to the phenological analyses of a range of dryland vegetation classes. Start-of-season (SOS) and date of peak greenness phenology metrics were calculated for each STARFM and MODIS pixel on the basis of enhanced vegetation index (EVI) and normalized difference vegetation index (NDVI) time series over a single growing season. The variability of each metric was calculated for all STARFM pixels within 500 m MODIS extents. Colorado Plateau Pinyon Juniper displayed high amounts of temporal and spatial variability that justified the use of STARFM data, while the benefit to the remaining classes depended on the specific vegetation index and phenology metric. The third study expanded the STARFM time series to five years (2005-2009) to examine the influence of site characteristics and climatic conditions on dryland ponderosa pine (Pinus ponderosa) forest phenological patterns. The results showed that elevation and slope controlled the variability of peak timing across years, with lower elevations and shallower slopes linked to higher levels of variability. During drought conditions, the number of site variables that controlled the timing and variability of vegetation peak increased.
Ph. D.

The European Water Framework Directive (Directive 2000/60/EC) is a mandatory agreement that guides the member states of the European Union in the field of water policy to fulfil the requirements for reaching the aim of the good ecological status of water bodies. In the last years several work ows and methods were developed to determine and evaluate the haracteristics and the status of the water bodies. Due to their area measurements remote sensing methods are a promising approach to constitute a substantial additional value. With increasing availability of optical and radar remote sensing data the development of new methods to extract information from both types of remote sensing data is still in progress. Since most limitations of these data sets do not agree the fusion of both data sets to gain data with higher spectral resolution features the potential to obtain additional information in contrast to the separate processing of the data. Based thereupon this study shall research the potential of multispectral and radar remote sensing data and the potential of their fusion for the assessment of the parameters of water body structure. Due to the medium spatial resolution of the freely available multispectral Sentinel-2 data sets especially the surroundings of the water bodies and their land use are part of this study. SAR data is provided by the Sentinel-1 satellite. Different image fusion methods are tested and the combined products of both data sets are evaluated afterwards. The evaluation of the single data sets and the fused data sets is performed by means of a maximum-likelihood classification and several statistical measurements. The results indicate that the combined use of different remote sensing data sets can have an added value.

Avec l'expansion des zones urbaines, la pollution de l'air et l'effet d'îlot de chaleur augmentent, entraînant des problèmes de santé pour les habitants et des changements climatiques mondiaux. Dans ce contexte, les arbres urbains sont une ressource précieuse pour améliorer la qualité de l'air et promouvoir les îlot de fraîcheur. D'autre part, les canopées sont soumises à des conditions spécifiques dans l'environnement urbain, causant la propagation de maladies et la diminution de l'espérance de vie parmi les arbres. Cette thèse explore le potentiel de la télédétection pour la cartographie automatique des arbres urbains, de la détection des couronnes d'arbres à l'estimation des espèces, une tâche préliminaire essentielle pour la conception des futures villes vertes, et pour une surveillance efficace de la végétation. Fondé sur des données hyperspectrales aéroportées, panchromatiques et un modèle numérique de surface, le premier objectif de cette thèse consiste à tirer parti de plusieurs sources de données pour améliorer les cartes d'arbres urbains existants, en testant différentes stratégies de fusion (fusion de caractéristiques et fusion de décision). La nature des résultats nous a conduit à optimiser la complémentarité des sources. En particulier, le deuxième objectif est d'étudier en profondeur la richesse des données hyperspectrales, en développant une approche d'ensemble classifier fondée sur des indices de végétation, où les "classifier" sont spécifiques aux espèces. Enfin, la première partie a mis en évidence l'intérêt de distinguer les arbres de rue des autres structures d'arbres urbains. Dans un cadre de Marked Point Process, le troisième objectif est de détecter les arbres en alignement urbain. Par le premier objectif, cette thèse démontre que les données hyperspectrales sont le principal moteur de la précision de la prédiction des espèces. La stratégie de fusion au niveau de décision est la plus appropriée pour améliorer la performance en comparaison des données hyperspectrales seules, mais de légères améliorations sont obtenues (quelques %) en raison de la faible complémentarité des caractéristiques texturales et structurelles en plus des caractéristiques spectrales. L'approche d'ensemble classifier développée dans la deuxième partie permet de classer les espèces d'arbres à partir de références au sol, avec des améliorations significatives par rapport à une approche standard de classification au niveau des caractéristiques. Chaque classifieur d'espèces extrait reflète les attributs spectraux discriminants de l'espèce et peut être relié à l'expertise des botanistes. Enfin, les arbres de rue peuvent être cartographiés grâce au terme d'interaction des MPP proposé qui modélise leurs caractéristiques contextuelles (alignement et hauteurs similaires). De nombreuses améliorations doivent être explorées comme la délimitation plus précise de la couronne de l'arbre, et plusieurs perspectives sont envisageables après cette thèse, parmi lesquelles le suivi de l'état de santé des arbres urbains
With the expansion of urban areas, air pollution and heat island effect are increasing, leading to state of health issues for the inhabitants and global climate changes. In this context, urban trees are a valuable resource for both improving air quality and promoting freshness islands. On the other hand, canopies are subject to specific conditions in the urban environment, causing the spread of diseases and life expectancy decreases among the trees. This thesis explores the potential of remote sensing for the automatic urban tree mapping, from the detection of the individual tree crowns to their species estimation, an essential preliminary task for designing the future green cities, and for an effective vegetation monitoring. Based on airborne hyperspectral, panchromatic and Digital Surface Model data, the first objective of this thesis consists in taking advantage of several data sources for improving the existing urban tree maps, by testing different fusion strategies (feature and decision level fusion). The nature of the results led us to optimize the complementarity of the sources. In particular, the second objective is to investigate deeply the richness of the hyperspectral data, by developing an ensemble classifiers approach based on vegetation indices, where the classifiers are species specific. Finally, the first part highlighted to interest of discriminating the street trees from the other structures of urban trees. In a Marked Point Process framework, the third objective is to detect trees in urban alignment. Through the first objective, this thesis demonstrates that the hyperspectral data are the main driver of the species prediction accuracy. The decision level fusion strategy is the most appropriate one for improving the performance in comparison the hyperspectral data alone, but slight improvements are obtained (a few percent) due to the low complementarity of textural and structural features in addition to the spectral ones. The ensemble classifiers approach developed in the second part allows the tree species to be classified from ground-based references, with significant improvements in comparison to a standard feature level classification approach. Each extracted species classifier reflects the discriminative spectral attributes of the species and can be related to the expertise of botanists. Finally, the street trees can be mapped thanks to the proposed MPP interaction term which models their contextual features (alignment and similar heights). Many improvements have to be explored such as the more accurate tree crown delineation, and several perspectives are conceivable after this thesis, among which the state of health monitoring of the urban trees

Water stored in snow is a critical contribution to the world’s available freshwater supply and is fundamental to the sustenance of natural ecosystems, agriculture and human societies. The importance of snow for the natural environment and for many socio-economic sectors in several mid‐ to high‐latitude mountain regions around the world, leads scientists to continuously develop new approaches to monitor and study snow and its properties. The need to develop new monitoring methods arises from the limitations of in situ measurements, which are pointwise, only possible in accessible and safe locations and do not allow for a continuous monitoring of the evolution of the snowpack and its characteristics. These limitations have been overcome by the increasingly used methods of remote monitoring with space-borne sensors that allow monitoring the wide spatial and temporal variability of the snowpack. Snow models, based on modeling the physical processes that occur in the snowpack, are an alternative to remote sensing for studying snow characteristics. However, from literature it is evident that both remote sensing and snow models suffer from limitations as well as have significant strengths that it would be worth jointly exploiting to achieve improved snow products. Accordingly, the main objective of this thesis is the development of novel methods for the estimation of snow parameters by exploiting the different properties of remote sensing and snow model data. In particular, the following specific novel contributions are presented in this thesis: i. A novel data fusion technique for improving the snow cover mapping. The proposed method is based on the exploitation of the snow cover maps derived from the AMUNDSEN snow model and the MODIS product together with their quality layer in a decision level fusion approach by mean of a machine learning technique, namely the Support Vector Machine (SVM). ii. A new approach has been developed for improving the snow water equivalent (SWE) product obtained from AMUNDSEN model simulations. The proposed method exploits some auxiliary information from optical remote sensing and from topographic characteristics of the study area in a new approach that differs from the classical data assimilation approaches and is based on the estimation of AMUNDSEN error with respect to the ground data through a k-NN algorithm. The new product has been validated with ground measurement data and by a comparison with MODIS snow cover maps. In a second step, the contribution of information derived from X-band SAR imagery acquired by COSMO-SkyMed constellation has been evaluated, by exploiting simulations from a theoretical model to enlarge the dataset.

Les acquisitions de télédétection ont des caractéristiques complémentaires en termes de résolution spatiale et temporelle et peuvent mesurer différents aspects de la couverture neigeuse (propriétés physiques de surface, type de neige, etc.). En combinant plusieurs acquisitions, il devrait être possible d'obtenir un suivi précis et continu de la neige. Cependant, cet objectif se heurte à la complexité du traitement des images satellites et à la confusion possible entre les différents matériaux observés. Plus particulièrement, l’accès à l’information fractionnelle, c’est-à-dire à la proportion de neige dans chaque pixel, nécessite de retrouver la proportion de l’ensemble des matériaux qui se trouvent dans celui-ci. Ces proportions sont accessibles via des méthodes d’inversions ou démélange spectral se basant sur la résolution spectrale des images obtenues. Le défi général est alors d’arriver à exploiter correctement les différentes informations de natures différentes qui nous sont apportées par les différentes acquisitions afin de produire des cartes d’enneigement précises. Les objectifs de la thèse sont alors au nombre de trois et peuvent se résumer par trois grandes interrogations qui permettent de traiter les différents points évoqués:- Quelles sont les limitations actuelles de l’état de l'art pour l’observation spatiale optique de la neige ?- Comment exploiter les séries temporelles pour s’adapter à la variabilité spectrale des matériaux ?- Est-il possible de généraliser la fusion de données pour une acquisition multimodale à partir de capteurs optiques ?Une étude complète des différents produits de neige issus du satellite MODIS est ainsi proposée, permettant l’identification des nombreuses limitations dont la principale est le haut taux d’erreurs lors de la reconstitution de la fraction (environ 30%). Parmi ces résultats sont notamment identifiés des problèmes liés aux méthodes de démélange face à la variabilité spectrale des matériaux. Face à ces limitations nous avons exploité les séries temporelles MODIS pour proposer une nouvelle approche d’estimation des endmembers, étape critique du démélange spectral. La faible évolution temporelle du milieu (hors neige) est alors utilisée pour contraindre l’estimation des endmembers non seulement sur l’image d’intérêt, mais également sur les images des jours précédents. L’efficacité de cette approche bien que démontrée ici reste sujette aux limitations de résolution spatiale intrinsèques au capteur. Des expérimentations sur la fusion de donnée, à même de pouvoir améliorer la qualité des images, ont par conséquent été réalisées. Devant les limitations de ces méthodes dans le cas des capteurs multispectraux utilisés, une nouvelle approche de fusion a été proposée. Via la formulation d’un nouveau modèle et sa résolution, la fusion entre des capteurs optiques de tous types peut être réalisée sans considération de recouvrement spectral. Les différentes expérimentations sur l’estimation de cartes de neige montrent un intérêt certain d’une meilleure résolution spatiale pour isoler les zones enneigées. Ce travail montre ainsi les nouvelles possibilités de développement pour l’observation de la neige, mais également les évolutions de l’utilisation combinée des images satellites pour l’observation de la Terre en général
Remote sensing acquisitions have complementary characteristics in terms of spatial and temporal resolution and can measure different aspects of snow cover (e.g., surface physical properties and snow type). By combining several acquisitions, it should be possible to obtain a precise and continuous monitoring of the snow. However, this task has to face the complexity of processing satellite images and the possible confusion between different materials observed. In particular, the estimation of fractional information, i.e., the amount of snow in each pixel, requires to know the proportion of the materials present in a scene. These proportions can be obtained performing spectral unmixing. The challenge is then to effectively exploit the information of different natures that are provided by the multiple acquisitions in order to produce accurate snow maps.Three main objectives are addressed by this thesis and can be summarized by the three following questions:- What are the current limitations of state-of-the-art techniques for the estimation of snow cover extent from optical observations?- How to exploit a time series for coping with the spectral variability of materials?- How can we take advantage of multimodal acquisitions from optical sensors for estimating snow cover maps?A complete study of the various snow products from the MODIS satellite is proposed. It allows the identification of numerous limitations, the main one being the high rate of errors during the estimation of the snow fraction (approximately 30%).The experimental analysis allowed to highlight the sensitivity of the spectral unmixing methods against the spectral variability of materials.Given these limitations, we have exploited the MODIS time series to propose a new endmembers estimation approach, addressing a critical step in spectral unmixing. The low temporal evolution of the medium (except snow) is then used to constrain the estimation of the endmembers not only on the image of interest, but also on images of the previous days. The effectiveness of this approach, although demonstrated here, remains limited by the spatial resolution of the sensor.Data fusion has been considered aiming at taking advantage of multiple acquisitions with different characteristics in term of resolution available on the same scene. Given the limitations of the actual methods in the case of multispectral sensors, a new fusion approach has been proposed. Through the formulation of a new model and its resolution, the fusion between optical sensors of all types can be achieved without consideration of their characteristics. The various experiments on the estimation of snow maps show a clear interest of a better spatial resolution to isolate the snow covered areas. The improvement in spectral resolution will improve future approaches based on spectral unmixing.This work explores the new possibilities of development for the observation of snow, but also for the combined use of the satellite images for the observation of the Earth in general

D’une part, les instruments permettant de mesurer les précipitations (pluviomètres, radars, etc.) effectuent des mesures de natures différentes et à différentes échelles. Leurs données sont difficilement comparables. D’autre part, les modèles décrivant l’évolution des précipitations sont eux complexes et difficiles à paramétrer et à valider. Dans cette thèse, nous utilisons l’assimilation de données afin de coupler des observations hétérogènes des précipitations et des modèles, pour étudier les précipitations et leur variabilité spatiotemporelle à différentes échelles (macrophysique, qui s’intéresse aux cellules de pluie, et microphysique, qui s’intéresse à la distribution en taille des gouttes – DSD – qui les composent). Tout d’abord, nous développons un algorithme permettant de restituer des cartes de précipitations à partir de mesures de l’atténuation causée par la pluie à des ondes provenant de satellites de télévision. Nos restitutions sont validées par rapport à des données radar et pluviomètres sur un cas d’étude dans le sud de la France. Ensuite, nous restituons, toujours par assimilation de données, des profils verticaux de DSD et de vents verticaux à partir de mesures de flux de gouttes au sol (par disdromètres) et de spectres Doppler en altitude (par radar). Nous utilisons ces restitutions sur 3 cas d’étude pour étudier les phénomènes physiques agissant sur les gouttes de pluie durant leur chute et pour évaluer la paramétrisation de ces phénomènes dans les modèles
On the one hand, the instruments designed to measure rainfall (rain gages, radars, etc.) perform measurements at different scales and of different natures. Their data are hard to compare. On the other hand, models simulating the evolution of rainfall are complex. It is not an easy task to parameterize and to validate them. In this thesis, we use data assimilation in order to couple heterogeneous observations of rainfall and models for studying rain and its spatiotemporal variability at different scales (macrophysical scale, which is interested in rain cells, as well as microphysical scale, which is interested in the drop size distribution – DSD). First, we develop an algorithm able to retrieve rain maps from measurements of attenuation of waves coming from TV satellites due to rainfall. Our retrievals are validated by comparison with radar and rain gages data for a case study in south of France. Second, we retrieve – again with data assimilation – vertical profiles of DSD and vertical winds from measurements of rain drop fluxes on the ground (using a disdrometer) and of Doppler spectra aloft (using a radar). We use these retrievals for 3 case studies to study the physical phenomena acting on rain drops during their fall and to evaluate the parameterization of these phenomena in models

Monitoring water quality on a near-real-time basis to address water resources management and public health concerns in coupled natural systems and the built environment is by no means an easy task. Furthermore, this emerging societal challenge will continue to grow, due to the ever-increasing anthropogenic impacts upon surface waters. For example, urban growth and agricultural operations have led to an influx of nutrients into surface waters stimulating harmful algal bloom formation, and stormwater runoff from urban areas contributes to the accumulation of total organic carbon (TOC) in surface waters. TOC in surface waters is a known precursor of disinfection byproducts in drinking water treatment, and microcystin is a potent hepatotoxin produced by the bacteria Microcystis, which can form expansive algal blooms in eutrophied lakes. Due to the ecological impacts and human health hazards posed by TOC and microcystin, it is imperative that municipal decision makers and water treatment plant operators are equipped with a rapid and economical means to track and measure these substances. Remote sensing is an emergent solution for monitoring and measuring changes to the earth's environment. This technology allows for large regions anywhere on the globe to be observed on a frequent basis. This study demonstrates the prototype of a near-real-time early warning system using Integrated Data Fusion and Mining (IDFM) techniques with the aid of both multispectral (Landsat and MODIS) and hyperspectral (MERIS) satellite sensors to determine spatiotemporal distributions of TOC and microcystin. Landsat satellite imageries have high spatial resolution, but such application suffers from a long overpass interval of 16 days. On the other hand, free coarse resolution sensors with daily revisit times, such as MODIS, are incapable of providing detailed water quality information because of low spatial resolution. This issue can be resolved by using data or sensor fusion techniques, an instrumental part of IDFM, in which the high spatial resolution of Landsat and the high temporal resolution of MODIS imageries are fused and analyzed by a suite of regression models to optimally produce synthetic images with both high spatial and temporal resolutions. The same techniques are applied to the hyperspectral sensor MERIS with the aid of the MODIS ocean color bands to generate fused images with enhanced spatial, temporal, and spectral properties. The performance of the data mining models derived using fused hyperspectral and fused multispectral data are quantified using four statistical indices. The second task compared traditional two-band models against more powerful data mining models for TOC and microcystin prediction. The use of IDFM is illustrated for monitoring microcystin concentrations in Lake Erie (large lake), and it is applied for TOC monitoring in Harsha Lake (small lake). Analysis confirmed that data mining methods excelled beyond two-band models at accurately estimating TOC and microcystin concentrations in lakes, and the more detailed spectral reflectance data offered by hyperspectral sensors produced a noticeable increase in accuracy for the retrieval of water quality parameters.
M.S.Env.E.
Masters
Civil, Environmental and, Construction Engineering
Engineering and Computer Science
Environmental Engineering

Durant dècades s'ha observat i monitoritzat sistemàticament la Terra i el seu entorn des de l'espai o a partir de plataformes aerotransportades. Paral·lelament, s'ha tractat d'extreure el màxim d'informació qualitativa i quantitativa de les observacions realitzades. Les tècniques de fusió de dades donen un "ventall de procediments que ens permeten aprofitar les dades heterogènies obtingudes per diferents mitjans i instruments i integrar-les de manera que el resultat final sigui qualitativament superior". En aquesta tesi s'han desenvolupat noves tècniques que es poden aplicar a l'anàlisi de dades multiespectrals que provenen de sensors remots, adreçades a aplicacions oceanogràfiques. Bàsicament s'han treballat dos aspectes: les tècniques d'enregistrament o alineament d'imatges; i la interpolació de dades esparses i multiescalars, focalitzant els resultats als camps vectorials bidimensionals.

En moltes aplicacions que utilitzen imatges derivades de satèl·lits és necessari mesclar o comparar imatges adquirides per diferents sensors, o bé comparar les dades d'un sòl sensor en diferents instants de temps, per exemple en: reconeixement, seguiment i classificació de patrons o en la monitorització mediambiental. Aquestes aplicacions necessiten una etapa prèvia d'enregistrament geomètric, que alinea els píxels d'una imatge, la imatge de treball, amb els píxels corresponents d'una altra imatge, la imatge de referència, de manera que estiguin referides a uns mateixos punts. En aquest treball es proposa una aproximació automàtica a l'enregistrament geomètric d'imatges amb els contorns de les imatges; a partir d'un mètode robust, vàlid per a imatges mutimodals, que a més poden estar afectades de distorsions, rotacions i de, fins i tot, oclusions severes. En síntesi, s'obté una correspondència punt a punt de la imatge de treball amb el mapa de referència, fent servir tècniques de processament multiresolució. El mètode fa servir les mesures de correlació creuada de les transformades wavelet de les seqüències que codifiquen els contorns de la línia de costa. Un cop s'estableix la correspondència punt a punt, es calculen els coeficients de la transformació global i finalment es poden aplicar a la imatge de treball per a enregistrar-la respecte la referència.

A la tesi també es prova de resoldre la interpolació d'un camp vectorial espars mostrejat irregularment. Es proposa un algorisme que permet aproximar els valors intermitjos entre les mostres irregulars si es disposa de valors esparsos a escales de menys resolució. El procediment és òptim si tenim un model que caracteritzi l'esquema multiresolució de descomposició i reconstrucció del conjunt de dades. Es basa en la transformada wavelet discreta diàdica i en la seva inversa, realitzades a partir d'uns bancs de filtres d'anàlisi i síntesi. Encara que el problema està mal condicionat i té infinites solucions, la nostra aproximació, que primer treballarem amb senyals d'una dimensió, dóna una estratègia senzilla per a interpolar els valors d'un camp vectorial bidimensional, utilitzant tota la informació disponible a diferents resolucions. Aquest mètode de reconstrucció es pot utilitzar com a extensió de qualsevol interpolació inicial. També pot ser un mètode adequat si es disposa d'un conjunt de mesures esparses de diferents instruments que prenen dades d'una mateixa escena a diferents resolucions, sense cap restricció en les característiques de la distribució de mesures. Inicialment cal un model dels filtres d'anàlisi que generen les dades multiresolució i els filtres de síntesi corresponents, però aquest requeriment es pot relaxar parcialment, i és suficient tenir una aproximació raonable a la part passa baixes dels filtres. Els resultats de la tesi es podrien implementar fàcilment en el flux de processament d'una estació receptora de satèl·lits, i així es contribuiria a la millora d'aplicacions que utilitzessin tècniques de fusió de dades per a monitoritzar paràmetres mediambientals.
During the last decades a systematic survey of the Earth environment has been set up from many spatial and airborne platforms. At present, there is a continuous effort to extract and combine the maximum of quantitative information from these different data sets, often rather heterogeneous. Data fusion can be defined as "a set of means and tools for the alliance of data originating from different sources with the aims of a greater quality result". In this thesis we have developed new techniques and schemes that can be applied on multispectral data obtained from remote sensors, with particular interest in oceanographic applications. They are based on image and signal processing. We have worked mainly on two topics: image registration techniques or image alignment; and data interpolation of multiscale and sparse data sets, with focus on two dimensional vector fields.

In many applications using satellite images, and specifically in those related to oceanographic studies, it is necessary to merge or compare multiple images of the same scene acquired from different captors or from one captor but at different times. Typical applications include pattern classification, recognition and tracking, multisensor data fusion and environmental monitoring. Image registration is the process of aligning the remotely sensed images to the same ground truth and transforming them into a known geographic projection (map coordinates). This step is crucial to correctly merge complementary information from multisensor data. The proposed approach to automatic image registration is a robust method, valid for multimodal images affected by distortions, rotations and, to a reasonably extend, with severe data occlusion. We derived a point to point matching of one image to a georeferenced map applying multiresolution signal processing techniques. The method is based on the contours of images: it uses a maximum cross correlation measure on the biorthogonal undecimated discrete wavelet transforms of the codified coastline contours sequences. Once this point to point correspondence is established, the coefficients of a global transform could be calculated and finally applied on the working image to register it to the georeferenced map.

The second topic of this thesis focus on the interpolation of sparse irregularly-sampled vector fields when these sparse data belong to different resolutions. It is proposed a new algorithm to iteratively approximate the intermediate values between irregularly sampled data when a set of sparse values at coarser scales is known. The procedure is optimal if there is a characterized model for the multiresolution decomposition / reconstruction scheme of the dataset. The scheme is based on a fast dyadic wavelet transform and on its inversion using a filter bank analysis/synthesis implementation for the wavelet transform model. Although the problem is ill-posed, and there are infinite solutions, our approach, firstly worked for one dimension signals, gives an easy strategy to interpolate the values of a vector field using all the information available at different scales. This reconstruction method could be used as an extension on any initial interpolation. It can also be suitable in cases where there are sparse measures from different instruments that are sensing the same scene simultaneously at several resolutions, without any restriction to the characteristics of the data distribution. Initially a filter model for the generation of multiresolution data and their synthesis counterpart is the main requisite but; this assumption can be partially relaxed with the only requirement of a reasonable approximation to the low pass counterpart. The thesis results can be easily implemented on the process stream of any satellite receiving station and therefore constitute a first contribution to potential applications on data fusion of environmental monitoring.

Zhang, Hankui.
Thesis (Ph.D.)--Chinese University of Hong Kong, 2013.
Includes bibliographical references (leaves 99-118).
Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Abstract also in Chinese.

Satellite remote sensing is supported by the extraction of data/information from satellite images or aircraft, through multispectral images, that allows their remote analysis and classification. Analyzing those images with data fusion tools and techniques, seem a suitable approach for the identification and classification of land cover. This land cover classification is possible because the fusion/merging techniques can aggregate various sources of heterogeneous information to generate value-added products that facilitate features classification and analysis. This work proposes to apply a data fusion algorithm, denoted FIF (Fuzzy Information Fusion), which combines computational intelligence techniques with multicriteria concepts and techniques to automatically distinguish Eucalyptus trees, in satellite images To assess the proposed approach, a Portuguese region, which includes planted Eucalyptus, will be used. This region is chosen because it includes a significant number of eucalyptus, and, currently, it is hard to automatically distinguish them from other types of trees (through satellite images), which turns this study into an interesting experiment of using data fusion techniques to differentiate types of trees. Further, the proposed approach is tested and validated with several fusion/aggregation operators to verify its versatility. Overall, the results of the study demonstrate the potential of this approach for automatic classification of land types.
A deteção remota de imagens de satélite é baseada na extração de dados / informações de imagens de satélite ou aeronaves, através de imagens multiespectrais, que permitem a sua análise e classificação. Quando estas imagens são analisadas com ferramentas e técnicas de fusão de dados, torna-se num método muito útil para a identificação e classificação de diferentes tipos de ocupação de solo. Esta classificação é possível porque as técnicas de fusão podem processar várias fontes de informações heterogéneas, procedendo depois à sua agregação, para gerar produtos de valor agregado que facilitam a classificação e análise de diferentes entidades - neste caso a deteção de eucaliptos. Esta dissertação propõe a utilização de um algoritmo, denominado FIF (Fuzzy Information Fusion), que combina técnicas de inteligência computacional com conceitos e técnicas multicritério. Para avaliar o trabalho proposto, será utilizada uma região portuguesa, que inclui uma vasta área de eucaliptos. Esta região foi escolhida porque inclui um número significativo de eucaliptos e, atualmente, é difícil diferenciá-los automaticamente de outros tipos de árvores (através de imagens de satélite), o que torna este estudo numa experiência interessante relativamente ao uso de técnicas de fusão de dados para diferenciar tipos de árvores. Além disso, o trabalho desenvolvido será testado com vários operadores de fusão/agregação para verificar sua versatilidade. No geral, os resultados do estudo demonstram o potencial desta abordagem para a classificação automática de diversos tipos de ocupação de solo (e.g. água, árvores, estradas etc).

In this study, the performances of the optical sensors and instruments carried on both ground-based and airborne platforms were evaluated for monitoring crop growing status, detecting the vegetation response to aerial applied herbicides, and identifying crop nitrogen status. Geostatistical analysis on remotely sensed data was conducted to investigate spatial structure of crop canopy normalized difference vegetation index and multispectral imagery. A computerized crop monitoring system was developed that combined sensors and instruments that measured crop structure and spectral data with a global positioning system. The integrated crop monitoring system was able to collect real-time, multi-source, multi-form, and crop related data simultaneously as the tractor-mounted system moved through the field. This study firstly used remotely sensed data to evaluate glyphosate efficacy on weeds applied with conventional and emerging aerial spray nozzles. A weedy field was In this study, the performances of the optical sensors and instruments carried on both ground-based and airborne platforms were evaluated for monitoring crop growing status, detecting the vegetation response to aerial applied herbicides, and identifying crop nitrogen status. Geostatistical analysis on remotely sensed data was conducted to investigate spatial structure of crop canopy normalized difference vegetation index and multispectral imagery. A computerized crop monitoring system was developed that combined sensors and instruments that measured crop structure and spectral data with a global positioning system. The integrated crop monitoring system was able to collect real-time, multi-source, multi-form, and crop related data simultaneously as the tractor-mounted system moved through the field. This study firstly used remotely sensed data to evaluate glyphosate efficacy on weeds applied with conventional and emerging aerial spray nozzles. A weedy field was set up in three blocks and four aerial spray technology treatments were tested. Spectral reflectance measurements were taken using ground-based sensors from all the plots at 1, 8, and 17 days after treatment. The results indicated that the differences among the treatments could be detected with spectral data. This study could provide applicators with guidance equipment configurations that can result in herbicide savings and optimized applications in other crops. The main focus of this research was to apply sensor fusion technology to ground-based and airborne imagery data. Experimental plots cropped with cotton and soybean plants were set up with different nitrogen application rates. The multispectral imagery was acquired by an airborne imaging system over crop field; at the same period, leaf chlorophyll content and spectral reflectance measurements were gathered with chlorophyll meter and spectroradiometer at canopy level on the ground, respectively. Statistical analyses were applied on the data from individual sensor for discrimination with respect to the nitrogen treatment levels. Multisensor data fusion was performed at data level. The results showed that the data fusion of airborne imagery with ground-based data were capable of improving the performance of remote sensing data on detection of crop nitrogen status. The method may be extended to other types of data, and data fusion can be performed at feature or decision level.

Michael M. Daniel, Alan S. Willsky.
Cover title.
Includes bibliographical references (p. 15).
Supported by the Advanced Research Projects Agency. F49620-93-1-0604 Supported by the Office of Naval Research. N00014-91-J-1004 Supported by the National Science Foundation. 9316624-DMS

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.

为了监测以及分析全球或者局部范围内发生的气候变化、生态系统动态以及人类活动，遥感是不可或缺的重要工具。在过去的二十年间，随着众多应用领域对遥感数据需求的增长以及太空技术的发展，卫星传感器发射的数目一直在增加。然而，由于硬件技术和经济方面的制约，卫星传感器获取遥感数据时不得不在空间分辨率和其他数据属性之间进行平衡，包括时间分辨率、光谱分辨率、扫描宽度等。为了使得卫星数据同时兼备高空间分辨率和高时间分辨率或者高空间分辨率和高光谱分辨率，一种经济有效的方法是利用数据融合处理技术将多源遥感数据进行融合，从而提高可用遥感数据的应用潜力。在本论文中，我们提出利用稀疏表示理论来探索空间分辨率和时间分辨率的融合以及空间分辨率和光谱分辨率的融合。
以Landsat ETM+（空间分辨率为30米，时间分辨率为16天）和MODIS（空间分辨率为250米~1千米，重访周期为1天）的反射率融合为例，我们提出两种时空融合方法将Landsat图像的精细空间细节和MODIS图像的每天重访周期进行结合。这两种传感器捕获的反射率值在相应的波段具有可比性，受这一事实启发，我们提出在已知的Landsat-MODIS图像对上将它们的空间信息建立对应关系，然后在预测日期将Landsat图像从相应的MODIS图像中预测出来。为了有效地从先验图像中学习空间细节信息，我们基于稀疏表示理论对Landsat和MODIS图像分别建立一个冗余字典来提取它们的基本表示基元。在两对先验Landsat-MODIS图像场景下，我们通过从先验图像对中学习一个高-低分辨率字典对，在ETM+和MODIS的差图像间建立对应关系。在第二个融合场景下，即只有一对先验Landsat-MODIS图像对，我们通过一个图像降质模型直接连接ETM+和MODIS数据；在融合阶段，结合高通调制MODIS图像在一个两层融合框架下被提高分辨率从而得到融合图像。值得注意的是，本论文提出的时空融合方法对于物候变化和地物类型变化形成了一个统一的融合框架。
基于本文提出的时空融合模型，我们提出对中国深圳的土地利用/覆盖变化进行监测。为了达到合理的城市规划和可持续发展，深圳作为一个快速发展的城市面临着检测快速变化的问题。然而，这一地区的多云多雨天气使得获得高质量的遥感图像的周期比卫星的正常重访周期更长。时空融合方法可以处理这一问题，其通过提高具有低空间分辨率而频繁时间覆盖图像的空间分辨率来实现检测快速变化。通过选定两组分别具有年纪变化和月份变化的Landsat-MODIS数据，我们将本文提出的时空融合方法应用于检测多类变化的任务。
随后，基于字典对学习和稀疏非负矩阵分解，我们对于遥感多光谱和高光谱图像提出一种新的空谱融合方法。通过将高光谱图像 (具有低空间分辨率和高光谱分辨率，简称为LSHS)的光谱信息和多光谱图像（具有高空间分辨率和低光谱分辨率，简称为HSLS）的空间信息进行结合，本方法旨在产生同时具有高空间和高光谱分辨率的融合数据。对于高光谱数据，其每个像素可以表示成少数端元的线性组合，受这一现象启发，本方法首先充分利用LSHS数据中的丰富光谱信息提取LSHS和HSLS图像的光谱基元。由于这些光谱基元可以分别对应地表示LSHS和HSLS图像的每个像素光谱，我们将这两类数据的基元形成一个字典对。接着，我们将HSLS图像关于其对应的字典进行稀疏表示求得其表示系数，从而对LSHS图像进行空间解混。结合LSHS数据的光谱基元和HSLS数据的表示系数，我们可以最终得到具有LSHS数据的光谱分辨率和HSLS数据的空间分辨率的融合图像。
Remote sensing provides good measurements for monitoring and further analyzing the climate change, dynamics of ecosystem, and human activities in global or regional scales. Over the past two decades, the number of launched satellite sensors has been increasing with the development of aerospace technologies and the growing requirements on remote sensing data in a vast amount of application fields. However, a key technological challenge confronting these sensors is that they tradeoff between spatial resolution and other properties, including temporal resolution, spectral resolution, swath width, etc., due to the limitations of hardware technology and budget constraints. To increase the spatial resolution of data with other good properties, one possible cost-effective solution is to explore data integration methods that can fuse multi-resolution data from multiple sensors, thereby enhancing the application capabilities of available remote sensing data. In this thesis, we propose to fuse the spatial resolution with temporal resolution and spectral resolution, respectively, based on sparse representation theory.
Taking the study case of Landsat ETM+ (with spatial resolution of 30m and temporal resolution of 16 days) and MODIS (with spatial resolution of 250m ~ 1km and daily temporal resolution) reflectance, we propose two spatial-temporal fusion methods to combine the fine spatial information of Landsat image and the daily temporal resolution of MODIS image. Motivated by that the images from these two sensors are comparable on corresponding bands, we propose to link their spatial information on available Landsat- MODIS image pair (captured on prior date) and then predict the Landsat image from the MODIS counterpart on prediction date. To well-learn the spatial details from the prior images, we use a redundant dictionary to extract the basic representation atoms for both Landsat and MODIS images based on sparse representation. Under the scenario of two prior Landsat-MODIS image pairs, we build the corresponding relationship between the difference images of MODIS and ETM+ by training a low- and high-resolution dictionary pair from the given prior image pairs. In the second scenario, i.e., only one Landsat- MODIS image pair being available, we directly correlate MODIS and ETM+ data through an image degradation model. Then, the fusion stage is achieved by super-resolving the MODIS image combining the high-pass modulation in a two-layer fusion framework. Remarkably, the proposed spatial-temporal fusion methods form a unified framework for blending remote sensing images with phenology change or land-cover-type change.
Based on the proposed spatial-temporal fusion models, we propose to monitor the land use/land cover changes in Shenzhen, China. As a fast-growing city, Shenzhen faces the problem of detecting the rapid changes for both rational city planning and sustainable development. However, the cloudy and rainy weather in region Shenzhen located makes the capturing circle of high-quality satellite images longer than their normal revisit periods. Spatial-temporal fusion methods are capable to tackle this problem by improving the spatial resolution of images with coarse spatial resolution but frequent temporal coverage, thereby making the detection of rapid changes possible. On two Landsat-MODIS datasets with annual and monthly changes, respectively, we apply the proposed spatial-temporal fusion methods to the task of multiple change detection.
Afterward, we propose a novel spatial and spectral fusion method for satellite multispectral and hyperspectral (or high-spectral) images based on dictionary-pair learning and sparse non-negative matrix factorization. By combining the spectral information from hyperspectral image, which is characterized by low spatial resolution but high spectral resolution and abbreviated as LSHS, and the spatial information from multispectral image, which is featured by high spatial resolution but low spectral resolution and abbreviated as HSLS, this method aims to generate the fused data with both high spatial and high spectral resolutions. Motivated by the observation that each hyperspectral pixel can be represented by a linear combination of a few endmembers, this method first extracts the spectral bases of LSHS and HSLS images by making full use of the rich spectral information in LSHS data. The spectral bases of these two categories data then formulate a dictionary-pair due to their correspondence in representing each pixel spectra of LSHS data and HSLS data, respectively. Subsequently, the LSHS image is spatially unmixed by representing the HSLS image with respect to the corresponding learned dictionary to derive its representation coefficients. Combining the spectral bases of LSHS data and the representation coefficients of HSLS data, we finally derive the fused data characterized by the spectral resolution of LSHS data and the spatial resolution of HSLS data.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Song, Huihui.
Thesis (Ph.D.) Chinese University of Hong Kong, 2014.
Includes bibliographical references (leaves 103-110).
Abstracts also in Chinese.

Lors de ces travaux, nous nous sommes intéressés au problème de la classification supervisée d'images satellitaires de
zones urbaines. Les données traitées sont des images optiques à très hautes résolutions spatiales: données panchromatiques à très haute résolution spatiale (IKONOS, QUICKBIRD, simulations PLEIADES) et des images hyperspectrales (DAIS, ROSIS).
Deux stratégies ont été proposées.
La première stratégie consiste en une phase d'extraction de caractéristiques spatiales et spectrales suivie d'une phase de classification. Ces caractéristiques sont extraites par filtrages morphologiques : ouvertures et fermetures géodésiques et filtrages surfaciques auto-complémentaires. La classification est réalisée avec les machines à vecteurs supports (SVM)
non linéaires. Nous proposons la définition d'un noyau spatio-spectral utilisant de manière conjointe l'information spatiale
et l'information spectrale extraites lors de la première phase.\\
La seconde stratégie consiste en une phase de fusion de données pre- ou post-classification. Lors de la fusion postclassification,
divers classifieurs sont appliqués, éventuellement sur plusieurs données issues d'une même scène (image panchromat
ique, image multi-spectrale). Pour chaque pixel, l'appartenance à chaque classe est estimée à l'aide des classifieurs. Un schém
a de fusion adaptatif permettant d'utiliser l'information sur la fiabilité locale de chaque classifieur, mais aussi l'information globale disponible a priori sur les performances de chaque algorithme pour les différentes classes, est proposé
.
Les différents résultats sont fusionnés à l'aide d'opérateurs flous.
Les méthodes ont été validées sur des images réelles. Des
améliorations significatives sont obtenues par rapport aux méthodes publiées dans la litterature.

土地利用/覆盖变化是地球上最重要的景观之一，同全球环境变化高度相关。通过对全球变化的整体模拟以及综合评价研究，可以了解全球气候变化运行机制以及人地关系。同时，全球尺度的土地利用/覆盖变化及其驱动机制研究，将揭示人类在全球气候变化机制中所起的作用，使人类更好地适应全球环境的变化。目前全球尺度的土地利用/覆盖研究大多是基于现有的五种欧洲或美国开发的全球地表覆盖产品，这些产品在一定程度上满足了全球变化研究的基本要求。但是，仍然存在一些不足之处，如统一的分类系统，精度低，产品之间的不一致以及低时效性等，使得这些产品并不适合全球环境变化的对比研究，也不能满足建立更高的精度和更可靠的全球气候变化模型的要求。因此，开发高分辨率，实时的地表覆盖产品，已成为当前全球变化研究的紧迫需要。
目前，遥感影像已广泛被用于制作全球地表覆盖产品，但由于传感器的技术要求和资金预算的限制，影像的空间和时间分辨率不能满足更高精度和可靠的全球变化研究需要。鉴于此，迫切需要我们研究和开发更加先进的卫星影像处理方法和地表覆盖产品的生产技术，为全球变化研究提供高精度和高可靠性的地表覆盖产品。
因此，为了提供更多的时间和更高空间分辨率的卫星影像以及地表覆盖产品，以更好地开展全球变化研究。本文主要从技术层面上，研究利用多源遥感影像的优点，生成高分辨率和多时相的卫星合成影像，并在此基础上发展了卫星数据融合理论和方法。本文研究中，传统的光谱空间数据融合理论将被回顾和充分讨论，考虑到卫星影像的多时相特征，传统的数据融合理论在时间维度得到扩展，本文将提出新的时空数据融合方法，并应用于植被监测和土地利用制图。
通过对融合理论及相关方法的系统学习，本文对各种融合方法进行了系统的回顾与总结，比如基于HIS变换图像融合方法 ，基于小波变换的图像融合方法，时空自适应反射融合模型（STARFM）等，并从遥感应用的角度，提出各种方法的优缺点。结合本文的研究目标，以下为本论文的主要研究内容。
(1)数据融合相关理论将得到系统的研究和总结，包括各种融合模型及其应用，如基于IHS变换，PCA变换，或者小波分析的数据融合方法，等等。同时，结合具体应用归纳并总结了这些方法的优缺点。
(2)由于传统数据融合方法依赖于空间及光谱信息，很难处理多源影像数据所蕴含的时空变化信息。因此，本文中，传统数据融合理论和方法在考虑到时间信息后得到改善和扩展。本文通过结合高空间分辨率Landsat数据和高时间分辨率MODIS数据为例，提出两种不同的时空数据融合方法。实验结果也表明，他们适合于处理多时空数据集成, 并能够满足全球变化研究对高质量数据的需要。
(3)时空数据融合建模中的主要问题有两个，第一个问题是不同数据源之间具有不一致性，如不同卫星数据具有不同的地表反射率以及不同的数据可靠性。第二个是地表覆盖的季节性或者土地利用变化规则在空间和时间的维度具有不确定性，尤其是在复杂地区。考虑这些问题，本文在基于时间和空间自适应反射融合模型（STARFM）的基础上，提出一种新的改进模型，结果表明，它将比原有模型更为有效和更为准确的生成高分辨率合成影像数据。
(4)混合像元问题是处理卫星数据中的一个常见问题。对于多源卫星数据来说，一个低分辨率图像像素区域将包含多个高分辨率图像像素。因此，不同数据源所获得的遥感数据将会因为混合像元问题从而影响到地表反射率数据在空间尺度上的差异，并影响到最终的融合精度。为了解决时空多源数据融合中的混合像元问题，本文将提出一种改进的基于附加条件的混合像元解缠的时空数据融合方法，实验结果表明它是适合植被监测应用，特别是具有先验土地覆盖图的地区。
(5)在时空数据融合方法产生的一系列高分辨率合成影像的基础上，时空马尔可夫随机场分类方法被提出并用于研制生产高分辨率土地覆盖产品，该方法利用影像的时空上下文信息。这种方法提供了新的策略去制作土地覆盖产品 ，在缺乏高分辨率影像的地区。实验结果表明，它的精度是可以接受的，可以为缺乏高分辨率数据地区提供高品质的土地覆盖产品。
Land use/cover change is one of the most important landscapes on the earth and it is highly related to global environmental change, based on which an overall simulation and comprehensive evaluation of global change research can be achieved for understanding the global change mechanism and the linkages between the human and natural environments. Moreover, study of global-scale land use/cover change and its driving mechanism will reveal the human role in global change mechanisms and processes for human adaptation to global environmental change. Most of the current global-scale land use/cover research is based on the existing five land cover products that have been developed by Europe and the US, and these indeed meet the basic requirements for the global change research to some extent. However, certain shortcomings still exist, such as their unified classification system, low accuracy, poor inconsistency, weak timeliness, etc., so, it is impossible to take the comparative global environmental change research as a basis for building more highly accurate and more reliable global change models, and it is urgent and necessary to develop a high-resolution, and up-to-date land cover product for global change research.
Currently, remote sensing imagery has been widely used for generating global land cover products, but due to certain physical and budget limitations related to the sensors, their spatial and temporal resolution are too low to attain more accurate and more reliable global change research. In this situation, there is an urgent need to study and develop a more advanced satellite image processing method and land cover producing techniques to generate higher resolution images and land cover products for global change research.
Accordingly, in order to provide more multi-temporal, high-resolution images and land cover products for global change research, this research mainly focuses on the technical level, of using both advantages of satellite images from different sources to generate high-resolution, multi-temporal images and develop satellite data fusion theory and methods. In this research, the traditional data fusion theory will be fully discussed and an improved scheme will be produced, taking into consideration the temporal information from satellite images at different times. Consequently, the spatial and temporal data fusion method will be proposed and applied to the monitoring of vegetation growth and land cover mapping.
Through conducting a comprehensive study of the related theories and methods related to data fusion, various methods are systematically reviewed and summarized, such as HIS transformation image fusion, Wavelet transform image fusion, the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM), etc. The advantages and disadvantages of these methods are highlighted according to their specific applications in the field of remote sensing. Based on my research target, the following are the main contents of this thesis:
(1) Data fusion theory will be systematically studied and summarized, including various fusion models and specific applications, such as IHS transformation, PCA transformation, Wavelet analysis based data fusion, etc. Furthermore, their advantages and disadvantages are pointed out in relation to specific applications.
(2) As traditional data fusion methods rely on spatial information and it is hard to deal with multi-source data fusion with temporal variation, therefore, the traditional data fusion theory and methods will be improved by a consideration of temporal information. Accordingly, some spatial and temporal data fusion methods will be proposed, in which both high-resolution & low-temporary imagery and low-resolution & high-temporary imagery are incorporated. Our experiments also show that they are suitable for dealing with multi-temporal data integration and generating high-resolution, multi-temporal images for global change research.
(3) There are two main issues related to spatial and temporal data fusion theory. The first is that there are inconsistencies in different images, such as the different levels of land surface reflectance and different degrees of reliability of multi-source satellite data. The second is the rule of phonological variation/land cover variation in both the spatial and temporal dimensions, particularly in areas with heterogeneous landscapes. When considering these issues, an improved STARFM (spatial and temporal adaptive reflectance fusion model) is proposed, based on the original model, and the preliminary results show that it is more efficient and accurate in generating high-resolution land surface imagery than its predecessor.
(4) Mixed pixels is a common issue in relation to satellite data processing, as one pixel in a coarse resolution image will constitute several pixels in a high-resolution image of the same size, so different levels of land surface reflectance will be acquired from multi-source satellite data because of the mixed pixel effect on the coarse resolution data, and the final accuracy of the fused result will be affected if these data are subjected to data fusion. In order to solve the mixed pixel issue in multi-source data fusion, an improved spatial and temporal data fusion approach, based on the constraint unmixing technique, was developed in this thesis. The experimental results show that it is well-suited to the phenological monitoring task when a prior land cover map is available.
(5) Based on the high-resolution reflectance images generated from spatial and temporal fusion, a spatial and temporal classification method based on the spatial and temporal Markov random field was developed to produce a high-resolution land cover product, in which both spatial and temporal contextual information are included within the classification scheme. This method provides a new strategy for generating high-resolution land cover products in the area without high-resolution images at a certain time, and the experimental results show that it is acceptable and suitable for generating high quality land cover products in areas for which there is a lack of high-resolution data.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Detailed summary in vernacular field only.
Xu, Yong.
Thesis (Ph.D.)--Chinese University of Hong Kong, 2012.
Includes bibliographical references (leaves 151-158).
Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Abstract also in Chinese.
ABSTRACT --- p.II
Acknowledgement --- p.VII
Contents --- p.VIII
List of Figures --- p.X
List of Tables --- p.XII
Abbreviations --- p.XIV
Chapter CHAPTER 1 --- Introduction --- p.1
Chapter 1.1 --- Background --- p.1
Chapter 1.2 --- Research objectives and significance --- p.5
Chapter 1.3 --- Research issues --- p.11
Chapter 1.4 --- Research framework and methodology --- p.13
Chapter 1.5 --- Organization of thesis --- p.16
Chapter CHAPTER 2 --- Review of the Existing Image Fusion Methods --- p.19
Chapter 2.1 --- Overview --- p.19
Chapter 2.2 --- The multi-source image fusion method --- p.24
Chapter 2.3 --- The multi-temporal, multi-source image fusion method --- p.29
Chapter 2.4 --- Details of STARFM --- p.35
Chapter 2.5 --- Accuracy of the assessment of the image fusion method --- p.41
Chapter 2.6 --- Summary and discussion --- p.44
Chapter CHAPTER 3 --- An Improved Spatial and Temporal Adaptive Reflectance Data Fusion Model --- p.47
Chapter 3.1 --- Introduction --- p.48
Chapter 3.2 --- Theoretical basis of the spatial and temporal reflectance data fusion model --- p.49
Chapter 3.3 --- An improved spatial and temporal reflectance data fusion model --- p.57
Chapter 3.4 --- Experiments with simulated data --- p.60
Chapter 3.5 --- Experiments with actual data from the BOREAS and PANYU study areas --- p.67
Chapter 3.6 --- Summary and discussion --- p.76
Chapter CHAPTER 4 --- Spatial and Temporal Data Fusion Method Using the Constrained Unmixing Approach --- p.78
Chapter 4.1 --- Introduction --- p.78
Chapter 4.2 --- Methodology --- p.80
Chapter 4.3 --- Experiments with simulated data --- p.86
Chapter 4.4 --- Experiments with actual data --- p.90
Chapter 4.5 --- Applications for NDVI and Land Surface Reflectance Monitoring --- p.96
Chapter 4.6 --- Summary and conclusions --- p.105
Chapter CHAPTER 5 --- Spatial and Temporal Classification of Synthetic Satellite Imagery: Land Cover Mapping and Accuracy Validation --- p.107
Chapter 5.1 --- Introduction --- p.107
Chapter 5.2 --- Study sites and data sources --- p.109
Chapter 5.3 --- Methodology --- p.113
Chapter 5.4 --- Synthetic Data Generation at the HARV and PANYU Study Areas --- p.119
Chapter 5.5 --- Land Cover Mapping with Synthetic Data --- p.133
Chapter 5.6 --- Summary and discussion --- p.142
Chapter CHAPTER 6 --- Summary and Conclusions --- p.144
Chapter 6.1 --- Summary --- p.144
Chapter 6.2 --- Contributions --- p.147
Chapter 6.3 --- Recommendations for further research --- p.149
REFERENCES --- p.151

Land surface albedo describes the proportion of incident solar radiant flux that is reflected from the Earth's surface and therefore is a crucial parameter in modeling and monitoring attempts to capture the current climate, hydrological, and biogeochemical cycles and predict future scenarios. Due to the temporal variability and spatial heterogeneity of land surface albedo, remote sensing offers the only realistic method of monitoring albedo on a global scale. While the distribution of bright, highly reflective surfaces (clouds, snow, deserts) govern the vast majority of the fluctuation, variations in the intrinsic surface albedo due to natural and human disturbances such as urban development, fire, pests, harvesting, grazing, flooding, and erosion, as well as the natural seasonal rhythm of vegetation phenology, play a significant role as well. The development of times series of global snow-free and cloud-free albedo from remotely sensed observations over the past decade and a half offers a unique opportunity to monitor and assess the impact of these alterations to the Earth's land surface. By utilizing multiple satellite records from the MODerate-resolution Imaging Spectroradiometer (MODIS), the Multi-angle Imaging Spectroradiometer (MISR) and the Visible Infrared Imaging Radiometer Suite (VIIRS) instruments, and developing innovative spectral conversion coefficients and temporal gap-filling strategies, it has been possible to utilize the strengths of the various sensors to improve the spatial and temporal coverage of global land surface albedo retrievals. The availability of these products is particularly important in tropical regions where cloud cover obscures the forest for significant periods. In the Amazon, field ecologists have noted that some areas of the forest ecosystem respond rapidly with foliage growth at the beginning of the dry season, when sunlight can finally penetrate fully to the surface and have suggested this phenomenon can continue until reductions in water availability (particularly in times of drought) impact the growth cycle. While it has been difficult to capture this variability from individual optical satellite sensors, the temporally gap-filled albedo products developed during this research are used in a case study to monitor the Amazon during the dry season and identify the extent of these regions of foliage growth.

Building information extraction and reconstruction from satellite images is an essential task for many applications related to 3D city modeling, planning, disaster management, navigation, and decision-making. Building information can be obtained and interpreted from several data, like terrestrial measurements, airplane surveys, and space-borne imagery. However, the latter acquisition method outperforms the others in terms of cost and worldwide coverage: Space-borne platforms can provide imagery of remote places, which are inaccessible to other missions, at any time. Because the manual interpretation of high-resolution satellite image is tedious and time consuming, its automatic analysis continues to be an intense field of research. At times however, it is difficult to understand complex scenes with dense placement of buildings, where parts of buildings may be occluded by vegetation or other surrounding constructions, making their extraction or reconstruction even more difficult. Incorporation of several data sources representing different modalities may facilitate the problem. The goal of this dissertation is to integrate multiple high-resolution remote sensing data sources for automatic satellite imagery interpretation with emphasis on building information extraction and refinement, which challenges are addressed in the following: Building footprint extraction from Very High-Resolution (VHR) satellite images is an important but highly challenging task, due to the large diversity of building appearances and relatively low spatial resolution of satellite data compared to airborne data. Many algorithms are built on spectral-based or appearance-based criteria from single or fused data sources, to perform the building footprint extraction. The input features for these algorithms are usually manually extracted, which limits their accuracy. Based on the advantages of recently developed Fully Convolutional Networks (FCNs), i.e., the automatic extraction of relevant features and dense classification of images, an end-to-end framework is proposed which effectively combines the spectral and height information from red, green, and blue (RGB), pan-chromatic (PAN), and normalized Digital Surface Model (nDSM) image data and automatically generates a full resolution binary building mask. The proposed architecture consists of three parallel networks merged at a late stage, which helps in propagating fine detailed information from earlier layers to higher levels, in order to produce an output with high-quality building outlines. The performance of the model is examined on new unseen data to demonstrate its generalization capacity. The availability of detailed Digital Surface Models (DSMs) generated by dense matching and representing the elevation surface of the Earth can improve the analysis and interpretation of complex urban scenarios. The generation of DSMs from VHR optical stereo satellite imagery leads to high-resolution DSMs which often suffer from mismatches, missing values, or blunders, resulting in coarse building shape representation. To overcome these problems, a methodology based on conditional Generative Adversarial Network (cGAN) is developed for generating a good-quality Level of Detail (LoD) 2 like DSM with enhanced 3D object shapes directly from the low-quality photogrammetric half-meter resolution satellite DSM input. Various deep learning applications benefit from multi-task learning with multiple regression and classification objectives by taking advantage of the similarities between individual tasks. Therefore, an observation of such influences for important remote sensing applications such as realistic elevation model generation and roof type classification from stereo half-meter resolution satellite DSMs, is demonstrated in this work. Recently published deep learning architectures for both tasks are investigated and a new end-to-end cGAN-based network is developed, which combines different models that provide the best results for their individual tasks. To benefit from information provided by multiple data sources, a different cGAN-based work-flow is proposed where the generative part consists of two encoders and a common decoder which blends the intensity and height information within one network for the DSM refinement task. The inputs to the introduced network are single-channel photogrammetric DSMs with continuous values and pan-chromatic half-meter resolution satellite images. Information fusion from different modalities helps in propagating fine details, completes inaccurate or missing 3D information about building forms, and improves the building boundaries, making them more rectilinear. Lastly, additional comparison between the proposed methodologies for DSM enhancements is made to discuss and verify the most beneficial work-flow and applicability of the resulting DSMs for different remote sensing approaches.

Indiana University-Purdue University Indianapolis (IUPUI)
With the advances in embedded technology and the omnipresence of smartphones, tracking systems do not need to be confined to a specific tracking environment. By introducing mobile devices into a tracking system, we can leverage their mobility and the availability of multiple sensors such as camera, Wi-Fi, Bluetooth and Inertial sensors. This thesis proposes to improve the existing tracking systems, enhanced Distributed Tracking System (e-DTS 2.0) [19] and enhanced Distributed Object Tracking System (eDOTS)[26], in the form of e-DTS 3.0 and provides an empirical analysis of these improvements. The enhancements proposed are to introduce Android-based mobile devices into the tracking system, to use multiple sensors on the mobile devices such as the camera, the Wi-Fi and Bluetooth sensors and inertial sensors and to utilize possible resources that may be available in the environment to make the tracking opportunistic. This thesis empirically validates the proposed enhancements through the experiments carried out on a prototype of e-DTS 3.0.