Existing systems of scene reconstruction and theorethical basics necessary for scene reconstruction from images data are described in this work. System of scene reconstruction from video was designed and implemented. Its results were analyzed and possible future work was proposed. OpenCV, ArtToolKit and SIFT libraries which were used in this project are also described.

Dans un contexte industriel, la tomographie 3D par rayons X vise à imager virtuellement une pièce afin d'en contrôler l'intérieur. Le volume virtuel de la pièce est obtenu par un algorithme de reconstruction, prenant en entrées les projections de rayons X qui ont été envoyés à travers la pièce. Beaucoup d'incertitudes résident dans ces projections à cause de phénomènes non contrôlés tels que la diffusion et le durcissement de faisceau, causes d'artefacts dans les reconstructions conventionnelles par rétroprojection filtrée. Afin de compenser ces incertitudes, les méthodes de reconstruction dites itératives tentent de faire correspondre la reconstruction à un modèle a priori, ce qui, combiné à l'information apportée par les projections, permet d'améliorer la qualité de reconstruction. Dans ce contexte, cette thèse propose de nouvelles méthodes de reconstruction itératives pour le contrôle de pièces produites par le groupe SAFRAN. Compte tenu de nombreuses opérations de projection et de rétroprojection modélisant le processus d'acquisition, les méthodes de reconstruction itératives peuvent être accélérées grâce au calcul parallèle haute performance sur processeur graphique (GPU). Dans cette thèse, les implémentations sur GPU de plusieurs paires de projecteur-rétroprojecteur sont décrites. En particulier, une nouvelle implémentation pour la paire duale dite à empreinte séparable est proposée. Beaucoup de pièces produites par SAFRAN pouvant être vues comme des volumes constants par morceaux, un modèle a priori de Gauss-Markov-Potts est introduit, à partir duquel est déduit un algorithme de reconstruction et de segmentation conjointes. Cet algorithme repose sur une approche bayésienne permettant d'expliquer le rôle de chacun des paramètres. Le caractère polychromatique des rayons X par lequel s'expliquent la diffusion et le durcissement de faisceau est pris en compte par l'introduction d'un modèle direct séparant les incertitudes sur les projections. Allié à un modèle de Gauss-Markov-Potts sur le volume, il est montré expérimentalement que ce nouveau modèle direct apporte un gain en précision et en robustesse. Enfin, l'estimation des incertitudes sur la reconstruction est traitée via l'approche bayésienne variationnelle. Pour obtenir cette estimation en un temps de calcul raisonnable, il est montré qu'il est nécessaire d'utiliser une paire duale de projecteur-rétroprojecteur. / In industry, 3D X-ray Computed Tomography aims at virtually imaging a volume in order to inspect its interior. The virtual volume is obtained thanks to a reconstruction algorithm based on projections of X-rays sent through the industrial part to inspect. In order to compensate uncertainties in the projections such as scattering or beam-hardening, which are cause of many artifacts in conventional filtered backprojection methods, iterative reconstruction methods bring further information by enforcing a prior model on the volume to reconstruct, and actually enhance the reconstruction quality. In this context, this thesis proposes new iterative reconstruction methods for the inspection of aeronautical parts made by SAFRAN group. In order to alleviate the computational cost due to repeated projection and backprojection operations which model the acquisition process, iterative reconstruction methods can take benefit from the use of high-parallel computing on Graphical Processor Unit (GPU). In this thesis, the implementation on GPU of several pairs of projector and backprojector is detailed. In particular, a new GPU implementation of the matched Separable Footprint pair is proposed. Since many of SAFRAN's industrial parts are piecewise-constant volumes, a Gauss-Markov-Potts prior model is introduced, from which a joint reconstruction and segmentation algorithm is derived. This algorithm is based on a Bayesian approach which enables to explain the role of each parameter. The actual polychromacy of X-rays, which is responsible for scattering and beam-hardening, is taken into account by proposing an error-splitting forward model. Combined with Gauss-Markov-Potts prior on the volume, this new forward model is experimentally shown to bring more accuracy and robustness. At last, the estimation of the uncertainties on the reconstruction is investigated by variational Bayesian approach. In order to have a reasonable computation time, it is highlighted that the use of a matched pair of projector and backprojector is necessary.

<p>As buildings have almost come to a saturation point in most developed countries, the management and maintenance of existing buildings have become the major problem of the field. Building Information Modeling (BIM) is the underlying technology to solve this problem. It is a 3D semantic representation of building construction and facilities that contributes to not only the design phase but also the construction and maintenance phases, such as life-cycle management and building energy performance measurement. This study aims at the processes of creating as-built BIM models, which are constructed after the design phase. Point cloud, a set of points in 3D space, is an intermediate product of as-built BIM models that is often acquired by 3D laser scanning and photogrammetry. A raw point cloud typically requires further procedures, e.g. registration, segmentation, classification, etc. In terms of segmentation and classification, machine learning methodologies are trending due to the enhanced speed of computation. However, supervised machine learning methodologies require labelling the training point clouds in advance, which is time-consuming and often leads to inevitable errors. And due to the complexity and uncertainty of real-world environments, the attributes of one point vary from the attributes of others. These situations make it difficult to analyze how one single attribute contributes to the result of segmentation and classification. This study developed a method of producing point clouds from a fast-generating 3D virtual indoor environment using procedural modeling. This research focused on two attributes of simulated point clouds, point density and the level of random errors. According to Silverman (1986), point density is associated with the point features around each output raster cell. The number of points within a neighborhood divided the area of the neighborhood is the point density. However, in this study, there was a little different. The point density was defined as the number of points on a surface divided by the surface area. And the unit is points per square meters (pts/m²). This research compared the performances of a machine learning segmentation and classification algorithm on ten different point cloud datasets. The mean loss and accuracy of segmentation and classification were analyzed and evaluated to show how the point density and level of random errors affect the performance of the segmentation and classification models. Moreover, the real-world point cloud data were used as additional data to evaluate the applicability of produced models.</p>

De nos jours, les réseaux de capteurs multimédia sans fils sont prometteurs pour différentes applications et domaines, en particulier avec le développement de l’IoT et des capteurs de caméra efficaces et bon marché. La stéréo vision est également très importante pour des objectifs multiples comme la Cinématographie, les jeux, la Réalité Virtuelle, la Réalité Augmentée, etc. Cette thèse vise à développer un système de reconstruction de scène en 3D prouvant l’utilisation de cartes de disparités stéréoscopiques multi-angles dans le contexte des réseaux de capteurs multimedia. Notre travail peut être divisé en trois parties. La première se concentre sur l’étude de toutes les applications, composants, topologies, contraintes et limitations de ces réseaux. En plus, les méthodes de calcul de disparité de vision stéréoscopique afin de choisir la ou les meilleures méthodes pour réaliser une reconstruction en 3D sur le réseau à faible coût en termes de complexité et de consommation d’énergie. Dans la deuxième partie, nous expérimentons et simulons différents calculs de cartes de disparités sur quelques nœuds en changeant les scénarios (intérieur et extérieur), les distances de couverture, les angles, le nombre de nœuds et les algorithmes. Dans la troisième partie, nous proposons un modèle de réseau basé sur l’arbre pour calculer des cartes de disparités précises sur des nœuds de capteurs de caméra multicouches qui répond aux besoins du serveur pour faire une reconstruction de scène 3D de la scène ou de l’objet d’intérêt. Les résultats sont acceptables et assurent la preuve du concept d’utilisation des cartes de disparités dans le contexte des réseaux de capteurs multimédia. / Nowadays, the WMSNs are promising for different applications and fields, specially with the development of the IoT and cheap efficient camera sensors. The stereo vision is also very important for multiple purposes like Cinematography, games, Virtual Reality, Augmented Reality, etc. This thesis aim to develop a 3D scene reconstruction system that proves the concept of using multiple view stereo disparity maps in the context of WMSNs. Our work can be divided in three parts. The first one concentrates on studying all WMSNs applications, components, topologies, constraints and limitations. Adding to this stereo vision disparity map calculations methods in order to choose the best method(s) to make a 3d reconstruction on WMSNs with low cost in terms of complexity and power consumption. In the second part, we experiment and simulate different disparity map calculations on a couple of nodes by changing scenarios (indoor and outdoor), coverage distances, angles, number of nodes and algorithms. In the third part, we propose a tree-based network model to compute accurate disparity maps on multi-layer camera sensor nodes that meets the server needs to make a 3d scene reconstruction of the scene or object of interest. The results are acceptable and ensure the proof of the concept to use disparity maps in the context of WMSNs.

Three-dimensional information is often used in robotics and 3D-mapping. There exist several ways to obtain a three-dimensional map. However, the time of flight used in the laser scanners or the structured light utilized by Kinect-like sensors sometimes are not sufficient. In this thesis, we investigate two CNN based stereo matching methods for obtaining 3D-information from a grayscaled pair of rectified images.While the state-of-the-art stereo matching method utilize a Siamese architecture, in this project a two-channel and a two stream network are trained in an attempt to outperform the state-of-the-art. A set of experiments were performed to achieve optimal hyperparameters. By changing one parameter at the time, the networks with architectures mentioned above are trained. After a completed training the networks are evaluated with two criteria, the error rate, and the runtime.Due to time limitations, we were not able to find optimal learning parameters. However, by using settings from [17] we train a two-channel network that performed almost on the same level as the state-of-the-art. The error rate on the test data for our best architecture is 2.64% while the error rate for the state-of-the-art Siamese network is 2.62%. We were not able to achieve better performance than the state-of-the-art, but we believe that it is possible to reduce the error rate further. On the other hand, the state-of-the-art Siamese stereo matching network is more efficient and faster during the disparity estimation. Therefore, if the time efficiency is prioritized, the Siamese based network should be considered.

Tracking a moving object and reconstructing its trajectory can be done with a stereo camera system, since the two cameras enable depth vision. However, such a system would not work if one of the cameras fails to detect the object. If that happens, it would be beneficial if the system could still use the functioning camera to make an approximate trajectory reconstruction. In this study, I have investigated how past observations from a stereo system can be used to recreate trajectories when video from only one of the cameras is available. Several approaches have been implemented and tested, with varying results. The best method was found to be a nearest neighbors-search optimized by a Kalman filter. On a test set with 10000 golf shots, the algorithm was able to create estimations which on average differed around 3.5 meters from the correct trajectory, with better results for trajec-tories originating close to the camera. / Att spåra ett objekt i rörelse och rekonstruera dess bana kan göras med ett stereokamerasystem, eftersom de två kamerorna möjliggör djupseende. Ett sådant system skulle dock inte fungera om en av kamerorna misslyckas med att detektera objektet. Om det händer skulle det vara fördelaktigt om systemet ändå kunde använda den fungerande kameran för att göra en approximativ rekonstruktion av banan. I den här studien har jag undersökt hur tidigare observationer från ett stereosystem kan användas för att rekonstruera banor när video från enbart en av kamerorna är tillgänglig. Ett flertal metoder har implementerats och testats, med varierande resultat. Den bästa metoden visade sig vara en närmaste-grannar-sökning optimerad med ett Kalman-filter. På en testmängd bestående av 10000 golfslag kunde algoritmen skapa uppskattningar som i genomsnitt skiljde sig 3.5 meter från den korrekta banan, med bättre resultat för banor som startat nära kameran.

As the understanding of the workings of the biological world expands, biomimetic designs increasingly move into the focus of engineering research studies. For this thesis, two studiesinvolving leading edge vortex generation for lift production as observed in nature were explored intheir respective flow regimes. The first study focused on the steady state analysis of streamwise vortices generated byleading edge tubercles of an adult humpback whale flipper. A realistic scaled model of a humpbackflipper was fabricated based on the 3D reconstruction from a sequence of 18 images taken whilecircumscribing an excised flipper of a beached humpback whale. Two complementary modelswith smooth leading edges were transformed from this original digitized model and fabricatedfor testing to further understand the effect of the leading edge tubercles. Experimentally-obtainedforce and qualitative flow measurements were used to study the influence of the leading edgetubercles. The presence of leading edge tubercles are shown to decrease maximum lift coefficient(Cl ), but increase Cl production in the post-stall region. By evaluating a measure of hydrodynamicefficiency, humpback whale flipper geometry is shown to be more efficient in the pre-stall regionand less efficient in the post-stall region as compared to a comparable model with a smooth leadingedge. With respect to a humpback whale, if the decrease in efficiency during post-stall angles ofattack was only required during short periods of time (turning), then this decrease in efficiencymay not have a significant impact on the lift production and energy needs. For the pursuit ofbiomimetic designs, this decrease in efficiency could have potential significance and should beinvestigated further. Qualitative flow measurements further demonstrate that these force results aredue to a delay of separation resulting from the presence of tubercles.The second study investigated explored the effects of flapping frequency on the passive flowcontrol of a flapping wing with a sinusoidal leading edge profile. At a flapping frequency of f =0.05 Hz, an alternating streamwise vortical formation was observed for the sinusoidal leading edge,while a single pair of vortices were present for the straight leading edge. A sinusoidal leading edgecan be used to minimize spanwise flow by the generation of the observed alternating streamwisevortices. An increase in flapping frequency results in these streamwise vortices becoming stretchedin the path of the wing. The streamwise vortices are shown to minimize spanwise flow even afterbeing stretched. Once instabilities are formed at f ≥ 0:1 Hz due to velocity shearing generatedby the increase in cross-radial velocity, the alternating streamwise vortices begin to break downresulting in a increase of spanwise flow.

Modeling articulated objects made of rigid layered parts used to populate 3D scenes in video games or movie production is a complex and time-consuming task for digital artists. This work proposes a sketch-based approach to efficiently model 3D layered articulated objects, such as animals with rigid shells and armors, in annotating a single 2D photo manually, and eventually fabricate it from automatically computed 2D patterns. In considering symmetrical objects seen under a 3/4 view, and an- notating salient features such as extremities of the rigid articulated parts as a mix of circular and Bézier curve, this approach is able to retrieve depth information, hidden parts, and rotation-articulated structure. The resulting shape consists of a set of quadrangulated polygons that may be flattened in 2D. Details such as ears, tails, and legs were further models using dedicated annotations. The accuracy of the reconstruction has been validated on synthetic cylindrical examples, and its ro- bustness in reconstructing a 3D model of armor, armadillo, and shrimp. The latter was finally fabricated using paper. / Att modellera artikulerade objekt gjorda av styva delar lagda i lager som används till att fylla 3D-scener i datorspel och filmskapande är en komplex och tidsödande uppgift för digitala konstnärer. Den här undersökningen föreslår ett skiss-baserat tillvägagångssätt att effektivt modellera artikulerade 3D-objekt lagda i lager, såsom djur med styva skal och rustning, i att annotera ett 2D-foto manuellt, och eventuellt skapa det från automatiskt beräknade 2D-mönster. Hänsyn är tagen till symmetriska objekt sedda under en 3/4 vy, och annotera framträdande egenskapersåsom extremiteter av de styva artikulerade delarna som en blandning avcirkulära och Bézier-kurvor, kan det här tillvägagångssättet hämta information om djup, gömda delar och rotations-artikulerade strukturer. Den slutliga formen består av ett set av fyrsidiga polygoner som kan bli tillplattade i 2D. Detaljer såsom öron, svansar och ben där framtida modeller använder dedikerade annotationer. Noggrannheten av rekonstruktionen har blivit validerad på syntetiska cylindriska exempeloch dess robusthet i att rekonstruera en 3D-modell av en rustning, ett bältdjur och en räka. Den senare skapades slutligen med hjälp av papper.

<p>3D character modeling is a crucial process of asset creation in the entertainment industry, particularly for animation and games. A fully automated pipeline via sketch-based 3D modeling (SBM) is an emerging possibility, but development is stalled by unrefined outputs and a lack of character-centered tools. This thesis proposes an improved method for constructing 3D character models with minimal user input, using only two sketch inputs  i.e., a front and side unshaded sketch. The system implements a deep convolutional neural network (CNN), a type of deep learning algorithm extending from artificial intelligence (AI), to process the input sketch and generate multi-view depth, normal and confidence maps that offer more information about the 3D surface. These are then fused into a 3D point cloud, which is a type of object representation for 3D space. This point cloud is converted into a 3D mesh via an occupancy network, involving another CNN, for a more precise 3D representation. This reconstruction step contends with non-deep learning approaches such as  Poisson reconstruction. The proposed system is evaluated for character generation on standardized quantitative metrics (i.e., Chamfer Distance [CD], Earth Mover’s Distance [EMD], F-score and Intersection of Union [IoU]), and compared to the base framework trained on the same character sketch and model database. This implementation offers a  significant improvement in the accuracy of vertex positions for the reconstructed character models. </p>

<p>Accurate 3D landscape models of cities or mountains have wide applications in mission</p> <p>planning, navigation, geological studies, etc. Lidar scanning using drones can provide high</p> <p>accuracy 3D landscape models, but the data is more expensive to collect as the area of</p> <p>each scan is limited. Thanks to recent maturation of Very-High-Resolution (VHR) optical</p> <p>imaging on satellites, people nowadays have access to stereo images that are collected on a</p> <p>much larger area than Lidar scanning. My research addresses unique challenges in satellite</p> <p>stereo, including stereo rectification with pushbroom sensors, dense stereo matching using</p> <p>image pairs with varied appearance, e.g. sun angles and surface plantation, and rasterized</p> <p>digital surface model (DSM) generation. The key contributions include the Continuous 3D-</p> <p>Label Semi-Global Matching (CoSGM) and a large scale dataset for satellite stereo processing</p> <p>and DSM evaluation.</p>