Generation of photo-realistic 3D human face models is a hot topic in the area joining computer graphics and computer vision. Many different techniques are used for this purpose, but most of them are not feasible for home users. These techniques may use advanced hardware such as laser scanners, calibrated stereo cameras, or very sophisticated software that can be as expensive as advanced hardware. Face model generation by morphing an initial 3D model with uncalibrated camera photographs is studied in this thesis. Manually marked feature points on photographs are used to deform initial 3D face model. Initial photographs also are processed to form a single texture image covering deformed 3D face model.

The main aim of this thesis is to evaluate current situation and propose renovation of the wooden roof structure of the baroque Dominican church of the Holy Cross in Znojmo. Disrepair historic truss structure over the church is the main impetus for the creation of technical documentation. Truss structure assessment was based on sensory and instrumental methods. The technical documentation of the existing structures (including drawings) was created in the first part. In the next phase, the research evaluates damage of the timber parts of construction and determination of their causes.In the third stage, redevelopment arrangements of damaged parts of the construction are proposed. This proposal will serve as a basis for their restoration.A large part of the work consists of drawings, supplemented with a 3D model of the truss structure.

The thesis discusses the use of relatively new technologies laser scanning for speleology surveying. The impulse for the creation of this work are simple, in many cases inaccurate surveyings the caves, which are, since inception for a long time, used up to now. The work describes the process of data acquisition by terrestrial laser scanning, then their processing and outputs that can be present or work with them. It is also evaluated the appropriateness of using this method in speleosurveying and compared with the currently used methods.

Cette thèse est dédiée au développement de méthodes à base de graphes, permettant de traiter les problèmes fondamentaux de la vision par ordinateur tels que la segmentation, le suivi d’objets, l’appariement de formes et l’inférence de modèles 3D. La première contribution de cette thèse est une méthode unifiée reposant sur un champ de Markov aléatoire (MRF) d’ordre deux permettant de réaliser en une seule étape la segmentation et le suivi de plusieurs objets observés par une caméra unique, tout en les ordonnançant en fonction de leur distance à la caméra. Nous y parvenons au moyen d’un nouveau modèle stratifié (2.5D) dans lequel une représentation bas-niveau et une représentation haut-niveau sont combinées par le biais de contraintes locales. Afin d’introduire des connaissances de haut niveau a priori, telles que des a priori sur la forme des objets, nous étudions l’appariement non-rigide de surfaces 3D. La seconde contribution de cette thèse consiste en une formulation générique d’appariement de graphes qui met en jeu des potentiels d’ordre supérieur et qui est capable d’intégrer différentes mesures de similarités d’apparence, de similarités géométriques et des pénalisations sur les déformations des formes. En tant que la troisième contribution de cette thèse, nous considérons également des interactions d’ordre supérieur pour proposer un a priori de forme invariant par rapport à la pose des objets, et l’exploitons dans le cadre d’une nouvelle approche de segmentation d’images médicales 3D afin d’obtenir une méthode indépendante de la pose de l’objet d’intérêt et de l’initialisation du modèle de forme. La dernière contribution de cette thèse vise à surmonter l’influence de la pose de la caméra dans les problèmes de vision. Nous introduisons un paradigme unifié permettant d’inférer des modèles 3D à partir d’images 2D monoculaires. Ce paradigme détermine simultanément le modèle 3D optimal et les projections 2D correspondantes sans estimer explicitement le point de vue de la caméra, tout en gérant les mauvaises détections et les occlusions. / This thesis is devoted to the development of graph-based methods that address several of the most fundamental computer vision problems, such as segmentation, tracking, shape matching and 3D model inference. The first contribution of this thesis is a unified, single-shot optimization framework for simultaneous segmentation, depth ordering and multi-object tracking from monocular video sequences using a pairwise Markov Random Field (MRF). This is achieved through a novel 2.5D layered model where object-level and pixel-level representations are seamlessly combined through local constraints. Towards introducing high-level knowledge, such as shape priors, we then studied the problem of non-rigid 3D surface matching. The second contribution of this thesis consists of a higher-order graph matching formulation that encodes various measurements of geometric/appearance similarities and intrinsic deformation errors. As the third contribution of this thesis, higher-order interactions were further considered to build pose-invariant statistical shape priors and were exploited for the development of a novel approach for knowledge-based 3D segmentation in medical imaging which is invariant to the global pose and the initialization of the shape model. The last contribution of this thesis aimed to partially address the influence of camera pose in visual perception. To this end, we introduced a unified paradigm for 3D landmark model inference from monocular 2D images to simultaneously determine both the optimal 3D model and the corresponding 2D projections without explicit estimation of the camera viewpoint, which is also able to deal with misdetections/occlusions

In 1776, the City of Gävle was immersed in a blazing fire, almost the whole city burned down and buildings that managed to survived have either been demolished or replaced by another one. To provide an actual view of Gävle from 1800-century is difficult due to the three different fires. A three-dimensional visualization model presents the entire city between 1776-1815 as it might have appeared. Archival images and information was provided from Länsmusem Gävleborg, Fogden, City library of Gävle and the City Archive. The three-dimensional model of the entire city is presented in a QuickTime movie format for viewing.

The main purpose of this work is to reconstruct 3D model of an entire scene byusing two ordinary cameras. We develop a mobile phone application, based onstereo vision and image analysis algorithms, executed either locally or on a remotehost, to calculate the dietary intake using the current questionnaire and the mobilephone photographs. The information of segmented 3D models are used to calculatethe volume -and then the calories- of a person’s daily intake food. The method ischecked using different solid food samples, in different camera arrangements. Theresults shows that the method successfully reconstructs 3D model of different foodsample with high details.

This thesis deals with methods of edema measuring. In my work, I designed hardware and software solutions for a device reconstructing surface of the limb part. Purpose of my work is evaluating discussing possibilities of this device. For making 3D reconstruction of scene from 2D images I made reconstruction program. For acquisition of images a device controlled by Arduino platform was constructed, the whole device is realized in program language Matlab. In the end of the thesis is described, how to improve the device for using in real conditions.

The diploma thesis deals with modeling of the design of construction. The model will include technical, cost and cost information about the building. The model object is a family house. The thesis is composed of a theoretical part, which presents basic knowledge from the field of designing, budgeting, valuation and operation of building work. The practical part is designed by a building with all the requisites and with information.

The aim of the submitted semestral project is research of 3D scanning object methods. The 3D scans utilization and types of these scans have been mentioned in the first chapter. The scanners are grouped into two basic methods – contact and contactless. The second chapter is dedicated to 3D model measurement principles, which are described in detail in four sub-chapters. In the following chapter is described design with complete realization 3D scanner with the implementation of the application for its controlling. Last part of the thesis concerns the 3D model editing and method evaluating.

This diploma thesis deals with the design of a two-stroke engine for paragliding. First of all, the different types and designs of two-stroke engines are discussed. After the design of the crank mechanism, the forces in the engine are tested, followed by the strength control of selected components. In addition, the work includes design of individual engine components, propeller reducer and 3D models of components and motor unit.