Advanced Kernel Methods For Remote Sensing Image Classification

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

MODELING OF SOIL LOAD-BEARING CAPACITY AS A FUNCTION OF SOIL MECHANICAL RESISTANCE TO PENETRATION

Estimation of soil load-bearing capacity from mathematical models that relate preconsolidation pressure (σp) to mechanical resistance to penetration (PR) and gravimetric soil water content (U) is important for defining strategies to prevent compaction of agricultural soils. Our objective was therefore to model the σp and compression index (CI) according to the PR (with an impact penetrometer in the field and a static penetrometer inserted at a constant rate in the laboratory) and U in a Rhodic Eutrudox. The experiment consisted of six treatments: no-tillage system (NT); NT with chiseling; and NT with additional compaction by combine traffic (passing 4, 8, 10, and 20 times). Soil bulk density, total porosity, PR (in field and laboratory measurements), U, σp, and CI values were determined in the 5.5-10.5 cm and 13.5-18.5 cm layers. Preconsolidation pressure (σp) and CI were modeled according to PR in different U. The σp increased and the CI decreased linearly with increases in the PR values. The correlations between σp and PR and PR and CI are influenced by U. From these correlations, the soil load-bearing capacity and compaction susceptibility can be estimated by PR readings evaluated in different U.

Surface Complexation Modeling in Variable Charge Soils: Charge Characterization by Potentiometric Titration

ABSTRACT Intrinsic equilibrium constants of 17 representative Brazilian Oxisols were estimated from potentiometric titration measuring the adsorption of H+ and OH− on amphoteric surfaces in suspensions of varying ionic strength. Equilibrium constants were fitted to two surface complexation models: diffuse layer and constant capacitance. The former was fitted by calculating total site concentration from curve fitting estimates and pH-extrapolation of the intrinsic equilibrium constants to the PZNPC (hand calculation), considering one and two reactive sites, and by the FITEQL software. The latter was fitted only by FITEQL, with one reactive site. Soil chemical and physical properties were correlated to the intrinsic equilibrium constants. Both surface complexation models satisfactorily fit our experimental data, but for results at low ionic strength, optimization did not converge in FITEQL. Data were incorporated in Visual MINTEQ and they provide a modeling system that can predict protonation-dissociation reactions in the soil surface under changing environmental conditions.

Surface Complexation Modeling in Variable Charge Soils: Prediction of Cadmium Adsorption

ABSTRACT Intrinsic equilibrium constants for 22 representative Brazilian Oxisols were estimated from a cadmium adsorption experiment. Equilibrium constants were fitted to two surface complexation models: diffuse layer and constant capacitance. Intrinsic equilibrium constants were optimized by FITEQL and by hand calculation using Visual MINTEQ in sweep mode, and Excel spreadsheets. Data from both models were incorporated into Visual MINTEQ. Constants estimated by FITEQL and incorporated in Visual MINTEQ software failed to predict observed data accurately. However, FITEQL raw output data rendered good results when predicted values were directly compared with observed values, instead of incorporating the estimated constants into Visual MINTEQ. Intrinsic equilibrium constants optimized by hand calculation and incorporated in Visual MINTEQ reliably predicted Cd adsorption reactions on soil surfaces under changing environmental conditions.

ZHARP: three-dimensional motion tracking from a single image plane.

Three-dimensional imaging and quantification of myocardial function are essential steps in the evaluation of cardiac disease. We propose a tagged magnetic resonance imaging methodology called zHARP that encodes and automatically tracks myocardial displacement in three dimensions. Unlike other motion encoding techniques, zHARP encodes both in-plane and through-plane motion in a single image plane without affecting the acquisition speed. Postprocessing unravels this encoding in order to directly track the 3-D displacement of every point within the image plane throughout an entire image sequence. Experimental results include a phantom validation experiment, which compares zHARP to phase contrast imaging, and an in vivo study of a normal human volunteer. Results demonstrate that the simultaneous extraction of in-plane and through-plane displacements from tagged images is feasible.

High-throughput SELEX SAGE method for quantitative modeling of transcription-factor binding sites.

The ability to determine the location and relative strength of all transcription-factor binding sites in a genome is important both for a comprehensive understanding of gene regulation and for effective promoter engineering in biotechnological applications. Here we present a bioinformatically driven experimental method to accurately define the DNA-binding sequence specificity of transcription factors. A generalized profile was used as a predictive quantitative model for binding sites, and its parameters were estimated from in vitro-selected ligands using standard hidden Markov model training algorithms. Computer simulations showed that several thousand low- to medium-affinity sequences are required to generate a profile of desired accuracy. To produce data on this scale, we applied high-throughput genomics methods to the biochemical problem addressed here. A method combining systematic evolution of ligands by exponential enrichment (SELEX) and serial analysis of gene expression (SAGE) protocols was coupled to an automated quality-controlled sequence extraction procedure based on Phred quality scores. This allowed the sequencing of a database of more than 10,000 potential DNA ligands for the CTF/NFI transcription factor. The resulting binding-site model defines the sequence specificity of this protein with a high degree of accuracy not achieved earlier and thereby makes it possible to identify previously unknown regulatory sequences in genomic DNA. A covariance analysis of the selected sites revealed non-independent base preferences at different nucleotide positions, providing insight into the binding mechanism.

Growth rate of fractal copper electrodeposits: Potential and concentration effects

Experiments are reported on fractal copper electrodeposits. An electrochemical cell was designed in order to obtain a potentiostatic control on the quasi-two-dimensional electrodeposition process. The aim was focused on the analysis of the growth rate of the electrodeposited phase, in particular its dependence on the electrode potential and electrolyte concentration.

Classification of urban multi-angular image sequences by aligning their manifolds

When dealing with multi-angular image sequences, problems of reflectance changes due either to illumination and acquisition geometry, or to interactions with the atmosphere, naturally arise. These phenomena interplay with the scene and lead to a modification of the measured radiance: for example, according to the angle of acquisition, tall objects may be seen from top or from the side and different light scatterings may affect the surfaces. This results in shifts in the acquired radiance, that make the problem of multi-angular classification harder and might lead to catastrophic results, since surfaces with the same reflectance return significantly different signals. In this paper, rather than performing atmospheric or bi-directional reflection distribution function (BRDF) correction, a non-linear manifold learning approach is used to align data structures. This method maximizes the similarity between the different acquisitions by deforming their manifold, thus enhancing the transferability of classification models among the images of the sequence.