No description available.

In this paper, a method for determining ground plane features in a sequence of images captured by a mobile camera is presented. The hardware of the mobile system consists of a monocular camera that is mounted on an inertial measurement unit (IMU). An image processing procedure is proposed, first to extract image features and match them across consecutive image frames, and second to detect the ground plane features using a two-step algorithm. In the first step, the planar homography of the ground plane is constructed using an IMU-camera motion estimation approach. The obtained homography constraints are used to detect the most likely ground features in the sequence of images. To reject the remaining outliers, as the second step, a new plane normal vector computation approach is proposed. To obtain the normal vector of the ground plane, only three pairs of corresponding features are used for a general camera transformation. The normal-based computation approach generalizes the existing methods that are developed for specific camera transformations. Experimental results on real data validate the reliability of the proposed method. / <p>QC 20121107</p>

Cette thèse traite de la reconstruction d'hypersurfaces au sein de champs de normales en dimension quelconque et trouve des applications dans l’analyse des empreintes digitales (lignes dermiques), des images satellites météorologiques (lieux de turbulence) et astrophysiques (bras de galaxies) ainsi que dans l’analyse stratigraphique des images sismiques (horizons). Les méthodes développées s’appuient sur la minimisation d’une équation aux dérivées partielles non linéaire reliant une hypersurface au pendage déduit d’un champ de normales. Elles prennent en compte des contraintes diverses telles que des points de passages, des frontières, des bornes et des discontinuités. La contribution principale de la thèse réside dans l’introduction d’un changement d’espace du pendage qui permet de reconstruire aussi bien des hypersurfaces exprimées sous des formes implicites dans les repères de définition des champs de normales que des horizons sismiques de manière rapide et interactive. Deux schémas de reconstruction d’horizons sismiques unidimensionnels présentant une discontinuité d’amplitude et de lieu inconnus sont également proposés. / This thesis deals with the reconstruction of hypersurfaces from a finite-dimensional normal vector field. Application scopes can be found in the analysis of fingerprints (epidermal ridges), meteorological images (eddies and cyclones), astrophysical images (galaxy arms) and in the stratigraphic analysis of seismic images (horizons). The hypersurfaces are obtained by solving a non-linear partial derivative equation relied on the local dip deduced from a normal vector field. Several constraints such as boundaries, bounds, points belonging to the hypersurface or discontinuities can be considered.The major contribution of this thesis consists in a local dip transformation which allows to reconstruct implicit hypersurfaces as well as seismic horizons by a fast and interactive method. Two schemes dedicated to the reconstruction of discontinuous one-dimensional seismic horizons are also proposed when the discontinuity location and jump are unknown.

In this thesis, the expression variation problem in two-dimensional (2D) and three-dimensional (3D) face recognition is tackled. While discriminant analysis (DA) methods are effective solutions for recognizing expression-variant 2D face images, they are not directly applicable when only a single sample image per subject is available. This problem is addressed in this thesis by introducing expression subspaces which can be used for synthesizing new expression images from subjects with only one sample image. It is proposed that by augmenting a generic training set with the gallery and their synthesized new expression images, and then training DA methods using this new set, the face recognition performance can be significantly improved. An important advantage of the proposed method is its simplicity; the expression of an image is transformed simply by projecting it into another subspace. The above proposed solution can also be used in general pattern recognition applications. The above method can also be used in 3D face recognition where expression variation is a more serious issue. However, DA methods cannot be readily applied to 3D faces because of the lack of a proper alignment method for 3D faces. To solve this issue, a method is proposed for sampling the points of the face that correspond to the same facial features across all faces, denoted as the closest-normal points (CNPs). It is shown that the performance of the linear discriminant analysis (LDA) method, applied to such an aligned representation of 3D faces, is significantly better than the performance of the state-of-the-art methods which, rely on one-by-one registration of the probe faces to every gallery face. Furthermore, as an important finding, it is shown that the surface normal vectors of the face provide a higher level of discriminatory information rather than the coordinates of the points. In addition, the expression subspace approach is used for the recognition of 3D faces from single sample. By constructing expression subspaces from the surface normal vectors at the CNPs, the surface normal vectors of a 3D face with single sample can be synthesized under other expressions. As a result, by improving the estimation of the within-class scatter matrix using the synthesized samples, a significant improvement in the recognition performance is achieved.

In this thesis, the expression variation problem in two-dimensional (2D) and three-dimensional (3D) face recognition is tackled. While discriminant analysis (DA) methods are effective solutions for recognizing expression-variant 2D face images, they are not directly applicable when only a single sample image per subject is available. This problem is addressed in this thesis by introducing expression subspaces which can be used for synthesizing new expression images from subjects with only one sample image. It is proposed that by augmenting a generic training set with the gallery and their synthesized new expression images, and then training DA methods using this new set, the face recognition performance can be significantly improved. An important advantage of the proposed method is its simplicity; the expression of an image is transformed simply by projecting it into another subspace. The above proposed solution can also be used in general pattern recognition applications. The above method can also be used in 3D face recognition where expression variation is a more serious issue. However, DA methods cannot be readily applied to 3D faces because of the lack of a proper alignment method for 3D faces. To solve this issue, a method is proposed for sampling the points of the face that correspond to the same facial features across all faces, denoted as the closest-normal points (CNPs). It is shown that the performance of the linear discriminant analysis (LDA) method, applied to such an aligned representation of 3D faces, is significantly better than the performance of the state-of-the-art methods which, rely on one-by-one registration of the probe faces to every gallery face. Furthermore, as an important finding, it is shown that the surface normal vectors of the face provide a higher level of discriminatory information rather than the coordinates of the points. In addition, the expression subspace approach is used for the recognition of 3D faces from single sample. By constructing expression subspaces from the surface normal vectors at the CNPs, the surface normal vectors of a 3D face with single sample can be synthesized under other expressions. As a result, by improving the estimation of the within-class scatter matrix using the synthesized samples, a significant improvement in the recognition performance is achieved.