In the industrial area, robots are an important part of the technological resources available to perform manipulation tasks in manufacturing, assembly, the transportation of dangerous waste, and a variety of applications. Specialized systems of computer vision have entered the market to solve problems that other technologies have been unable to address. This document analyzes a stereo vision system that is used to provide the center of mass of an object in three dimensions. This kind of application is mounted using two or more cameras that are aligned along the same axis and give the possibility to measure the depth of a point in the space. The stereoscopic system described, measures the position of an object using a combination between the 2D recognition, which implies the calculus of the coordinates of the center of mass and using moments, and the disparity that is found comparing two images: one of the right and one of the left. This converts the system into a 3D reality viewfinder, emulating the human eyes, which are capable of distinguishing depth with good precision.The proposed stereo vision system is integrated into a 5 degree of freedom pneumatic robot, which can be programmed using the GRAFCET method by means of commercial software. The cameras are mounted in the lateral plane of the robot to ensure that all the pieces in the robot's work area can be observed.For the implementation, an algorithm is developed for recognition and position measurement using open sources in C++. This ensures that the system can remain as open as possible once it is integrated with the robot. The validation of the work is accomplished by taking samples of the objects to be manipulated and generating robot's trajectories to see if the object can be manipulated by its end effector or not. The results show that is possible to manipulate pieces in a visually crowded space with acceptable precision. However, the precision reached does not allow the robot to perform tasks that require higher accuracy as the one is needed in manufacturing assembly process of little pieces or in welding applications. / En el área industrial los robots forman parte importante del recurso tecnológico disponible para tareas de manipulación en manufactura, ensamble, manejo de residuos peligrosos y aplicaciones varias. Los sistemas de visión computacional se han ingresado al mercado como soluciones a problemas que otros tipos de sensores y métodos no han podido solucionar. El presente trabajo analiza un sistema de visión estereoscópico aplicado a un robot. Este arreglo permite la medición de coordenadas del centro de un objeto en las tres dimensiones, de modo que, le da al robot la posibilidad de trabajar en el espacio y no solo en un plano. El sistema estereoscópico consiste en el uso de dos o más cámaras alineadas en alguno de sus ejes, mediante las cuales, es posible calcular la profundidad a la que se encuentran los objetos. En el presente, se mide la posición de un objeto haciendo una combinación entre el reconocimiento 2D y la medición de las coordenadas y de su centro calculadas usando momentos. En el sistema estereoscópico, se añade la medición de la última coordenada mediante el cálculo de la disparidad encontrada entre las imágenes de las cámaras inalámbricas izquierda y derecha, que convierte al sistema en un visor 3D de la realidad, emulando los ojos humanos capaces de distinguir profundidades con cierta precisión. El sistema de visión computacional propuesto es integrado a un robot neumático de 5 grados de libertad el cual puede ser programado desde la metodología GRAFCET mediante software de uso comercial. Las cámaras del sistema de visión están montadas en el plano lateral del robot de modo tal, que es posible visualizar las piezas que quedan dentro de su volumen de trabajo. En la implementación, se desarrolla un algoritmo de reconocimiento y medición de posición, haciendo uso de software libre en lenguaje C++. De modo que, en la integración con el robot, el sistema pueda ser lo más abierto posible. La validación del trabajo se logra tomando muestras de los objetos a ser manipulados y generando trayectorias para el robot, a fin de visualizar si la pieza pudo ser captada por su garra neumática o no. Los resultados muestran que es posible lograr la manipulación de piezas en un ambiente visualmente cargado y con una precisión aceptable. Sin embargo, se observa que la precisión no permite que el sistema pueda ser usado en aplicaciones donde se requiere precisión al nivel de los procesos de ensamblado de piezas pequeñas o de soldadura.

Submitted by Liliane Ferreira (ljuvencia30@gmail.com) on 2018-11-26T13:24:36Z No. of bitstreams: 2 Dissertação - Gabriel da Silva Vieira - 2018.pdf: 13740412 bytes, checksum: ddb7d4353e4f2d7650b087dd0d4bd796 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2018-11-26T13:43:18Z (GMT) No. of bitstreams: 2 Dissertação - Gabriel da Silva Vieira - 2018.pdf: 13740412 bytes, checksum: ddb7d4353e4f2d7650b087dd0d4bd796 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2018-11-26T13:43:18Z (GMT). No. of bitstreams: 2 Dissertação - Gabriel da Silva Vieira - 2018.pdf: 13740412 bytes, checksum: ddb7d4353e4f2d7650b087dd0d4bd796 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2018-10-05 / Outro / Disparity maps are key components of a stereo vision system. Autonomous navigation, 3D reconstruction, and mobility are examples of areas of research which use disparity maps as an important element. Although a lot of work has been done in the stereo vision field, it is not easy to build stereo systems with concepts such as reuse and extensible scope. In this study, we explore this gap and it presents a software architecture that can accommodate different stereo methods through a standard structure. Firstly, it introduces some scenarios that illustrate use cases of disparity maps and it shows a novel architecture that foments code reuse. A Disparity Computation Framework (DCF) is presented and we discuss how its components are structured. Then we developed a prototype which closely follows the proposal architecture and we prepared some test cases to be performed. Furthermore, we have implemented disparity methods for validation purposes and to evaluate our disparity refinement method. This refinement method, named as Segmented Consistency Check (SCC), was designed to increase the robustness of stereo matching algorithms. It consists of a segmentation process, statistical analysis of grouping areas and a support weighted function to find and to fill in unknown disparities. The experimental results show that the DCF can satisfy different scenarios on-demand. Besides, they show that SCC method is an efficient approach that can make some enhancements in disparity maps, as reducing the disparity error measure. / Mapas de disparidade são elementos cruciais em sistemas de visão estéreo. Navegação autônoma, reconstrução 3D e mobilidade são exemplos de área de pesquisa que utilizam mapas de disparidade como elementos-chave. Embora muitos trabalhos têm sido feitos na área de visão estéreo, ainda assim, não é trivial construir sistemas estéreos com aplicação de conceitos como reutilização e escopo extensível. Neste estudo, exploramos essa lacuna e apresentamos uma arquitetura de software capaz de acomodar diferentes métodos de visão estéreo através de uma estrutura bem definida. Inicialmente, cenários que ilustram usos de mapa de disparidade são introduzidos e uma arquitetura que fomenta reutilização de código é apresentada. Dessa forma, um Framework de Cálculo de Disparidade (FCD) é apresentado e seus componentes são discutidos a fim de especificar a sua estrutura. Em seguida, um protótipo que segue a arquitetura proposta é apresentado e alguns casos de teste são preparados e executados. Além disso, métodos de cálculo de disparidade foram implementados para propostas de validação e para avaliar o método de refinamento de disparidade proposto pelos autores. Esse método de refinamento, chamado de Checagem de Consistência de Segmento (CCS), foi projetado para aumentar a robustez de algoritmos de combinação estéreo. Trata-se de um método que utiliza um processo de segmentação preliminar, análise estatística de áreas definidas e função ponderada de suporte para encontrar e preencher disparidades marcadas como desconhecidas. Os resultados dos experimentos realizados apontam que o FCD pode satisfazer diferentes cenários sob demanda. Além disso, os resultados mostram que o método CCS é uma abordagem eficiente que pode trazer certos melhoramentos em mapas de disparidade, como reduzir a medida de erro no cálculo de correspondências estéreo.

Este trabalho aborda a utilização de tecnologias para a criação de ambientes virtuais baseados em imagens, com uma aplicação na praça central da cidade de Pelotas/RS. Possibilita que o usuário realize interativamente um passeio no entorno da praça com recursos que permitem avaliações arquitetônicas e urbanísticas por meio de simulações de troca de cor nos prédios, inserção de novas construções e análise do estado de conservação de imóveis, com vantagens sobre métodos tradicionais de análises em montagens fotográficas estáticas. Enfatiza a pesquisa de soluções para visualização interativa de ambientes, focado na identificação de fontes de informação e não na sua modelagem matemática. Para a apresentação do trabalho, além da seleção das cenas urbanas que seriam estudadas, foram consideradas técnicas para a modelagem dos elementos arquitetônicos de forma que se obtivesse a máxima preservação das características naturais (estado de conservação, cores e riqueza de detalhes), formas para a visualização destes dados de maneira integrada com dados bibliográficos (histórico, técnicas construtivas e localização) e também a utilização de objetos multimídia para o enriquecimento na apresentação de conteúdos. Na busca de soluções, foram investigadas as técnicas de modelagem fotogramétrica como forma de obtenção de objetos realísticos com a manutenção das características do objeto original em modelos geométricos simplificados. Foram feitos estudos sobre as formas de apresentação de ambientes virtuais navegáveis através de panoramas interativos e também foi estudada uma forma de aproximar a visualização dos conteúdos com a visão natural humana, através da estereoscopia. O trabalho culmina com a fusão de todas as tecnologias estudadas em uma aplicação denominada “Praça República Virtual – PRV” (para resgatar o antigo nome da atual Praça Coronel Pedro Osório), que funciona como um canteiro de provas na medida que abre um leque de opções para utilização em estudos na área de Arquitetura e Urbanismo. / This work approaches the uses of technologies for creation of virtual environments based on images, with an application to the central square of the city of Pelotas/RS. It makes possible to the user to accomplish an interactive walkthrough with resources that allows architectural and urban planning evaluations through simulations of color changes in the buildings, insertion of new constructions and analysis of the conservation condition of the buildings, with advantages if compared to traditional methods of analysis with static photographic assemblies. It emphasizes the research of solutions for interactive visualization of environments, focused in the identification of sources of information and not in mathematical modeling. Besides the selection of the urban scenes to be studied, it was considered techniques for modeling the architectural elements to obtain the maximal preservation of their natural characteristics (conservation state, colors and wealth of details), ways of visualization of nowadays conservation, but integrated with bibliographical dates (historical, constructive techniques and location). It also includes the uses of multimedia objects to the presentation of contents. In the search of solutions, techniques of photogrammetric modeling were investigated, looking for the construction of realistic objects and maintenance of the characteristics of the original object but using simplified geometric models. It was done a search about forms of presentation of navigable virtual environments through interactive panoramas and also using a prototype of stereoscopy. The work culminates with the coalition of all studied technologies in a prototype of the central square of Pelotas called “Praça República Virtual–PRV” (to rescue the old name of the current Square Cel. Pedro Osório). It works like a stonemason of proofs in the measure that opens various options of use in studies in the area of Architecture and Urban Planning.

Image based modeling using visual images has undergone major development during the earlier parts of the 21th century. In this thesis a system for automated uncalibrated scene reconstruction using infrared images is implemented and tested. An automated reconstruction system could serve to simplify thermal inspection or as a demonstration tool. Thermal images will in general have lower resolution, less contrast and less high frequency content as compared to visual images. These characteristics of infrared images further complicates feature extraction and matching, key steps in the reconstruction process. In order to remedy the complication preprocessing methods are suggested and tested as well. Infrared modeling will also impose additional demands on the reconstruction as it is of importance to maintain thermal accuracy of the images in the product. Three main results are obtained from this thesis. Firstly, it is possible to obtain camera calibration and pose as well as a sparse point cloud reconstruction from an infrared image sequence using the suggested implementation. Secondly, correlation of thermal measurements from the images used to reconstruct three dimensional coordinates is presented and analyzed. Lastly, from the preprocessing evaluation it is concluded that the tested methods are not suitable. The methods will increase computational cost while improvements in the model are not proportional. / Bildbaserad modellering med visuella bilder har genomgått en stor utveckling under de tidigare delarna av 2000-talet. Givet en sekvens bestående av vanliga tvådimensionella bilder på en scen från olika perspektiv så är målet att rekonstruera en tredimensionell modell. I denna avhandling implementeras och testas ett system för automatiserad okalibrerad scenrekonstruktion från infraröda bilder. Okalibrerad rekonstruktion refererar till det faktum att parametrar för kameran, såsom fokallängd och fokus, är okända och enbart bilder används som indata till systemet. Ett stort användingsområde för värmekameror är inspektion. Temperaturskillnader i en bild kan indikera till exempel dålig isolering eller hög friktion. Om ett automatiserat system kan skapa en tredimensionell modell av en scen så kan det bidra till att förenkla inspektion samt till att ge en bättre överblick. Värmebilder kommer generellt att ha lägre upplösning, mindre kontrast och mindre högfrekvensinnehåll jämfört med visuella bilder. Dessa egenskaper hos infraröda bilder komplicerar extraktion och matchning av punkter i bilderna vilket är viktiga steg i rekonstruktionen. För att åtgärda komplikationen förbehandlas bilderna innan rekonstruktionen, ett urval av metoder för förbehandling har testats. Rekonstruktion med värmebilder kommer också att ställa ytterligare krav på rekonstruktionen, detta eftersom det är viktigt att bibehålla termisk noggrannhet från bilderna i modellen. Tre huvudresultat erhålls från denna avhandling. För det första är det möjligt att beräkna kamerakalibrering och position såväl som en gles rekonstruktion från en infraröd bildsekvens, detta med implementationen som föreslås i denna avhandling. För det andra presenteras och analyseras korrelationen för temperaturmätningar i bilderna som används för rekonstruktionen. Slutligen så visar den testade förbehandlingen inte en förbättring av rekonstruktionen som är propotionerlig med den ökade beräkningskomplexiteten.

Les vagues courtes sont omniprésentes à la surface des océans, avec des longueurs de quelques dizaines de mètres au mètre typiquement. Connaitre leurs directions de propagation en mer est important à plusieurs titres, notamment pour la compréhension de la dynamique de l'état de mer, des échanges air-mer ou de la dérive de particules en surface. Ces distributions directionnelles sont étudiées ici au regard des progrès récents réalisés en techniques d'instrumentation. L'analyse du bruit sismo-acoustique enregistré en grandes profondeurs permet d'extraire un comportement quasi-universel qui dépend indirectement de cette distribution à travers ladite intégrale de recouvrement. Il est cohérent avec des observations directes du champ de vagues obtenues à partir de reconstructions tridimensionnelles de la surface de l'océan. Alors que la direction de propagation des vagues longues s'aligne avec celle du vent, les vagues courtes s'en détachent d'autant plus à mesure que leurs échelles diminuent (bimodalité).La comparaison de ces observations avec les prédictions d'un modèle numérique de vagues, basé sur l'environnement WAVEWATCH®III, permet de constater que ces modèles sont qualitativement valables mais encore quantitativement incorrects. Une des possibilités explorées pour corriger cet effet est la prise en compte de sources de vagues courtes à ±90° de la direction du vent, qui pourraient être associées au déferlement des vagues longues. Une telle source à elle seule n'explique pas les formes des distributions directionnelles observées. D'autres mécanismes pourraient intervenir que de futures investigations pourront tenter de clarifier. / Short surface gravity waves are ubiquitous at the ocean surface, with lengths from a few tens of meters to a meter typically.Knowing their propagation directions at sea is important in several respects, especially for the understanding of sea-state dynamics, airsea interactions and particles surface drift.Their directional distributions are here investigated in the light of the recent progress made in instrumentation techniques. The analysis of ocean bottom seismo-acoustic noise records allows for the extraction of a quasi-universal behavior which indirectly depends on this distribution through the socalled overlap integral. It is coherent with direct observations of the wave field obtained from tri-dimensional reconstructions of the ocean surface elevation field. While the propagation direction of long waves aligns with the wind direction, short waves progressively detach from it towards small scales (bimodality).Comparing those measurements with the predictions of a spectral numerical wave model, based on WAVEWATCH®III environment, allows to realize that they provide qualitatively correct but quantitatively incorrect predictions. One of the possibilities here explored to correct for it, is by accounting for the sources of energy at ±90° to the wind direction, which could be associated with the breaking of long waves. This source term on its own does not explain the shapes of the observed directional distributions. Other mechanisms could come into play that future investigations will help clarify.

Object tracking has become really important in the field of robotics in the last years. Frequently, the goal is to obtain the trajectory of the tracked target over time and space by acquiring and processing information from the sensors. In this thesis we are interested in tracking objects at a very short range. The primary application of our approach is targeting the domain of object tracking during grasp execution with a hand-in-eye sensor setup. To this end, a promising approach investigated in this work is based on the Leap Motion sensor, which is designed for tracking human hands. However, we are interested in tracking grasped objects thus we need to extend its functionality. The main goal of the thesis is to track the 3D position and orientation of an object from a set of simple primitives (cubes, cylinders, triangles) over a video sequence. That is the reason we have designed and developed two different approaches for tracking objects with the Leap Motion device as stereo vision system.

Dans le but d’améliorer le traitement des éventrations, cette thèse porte sur la biomécanique de la paroi abdominale. Plusieurs aspects de son comportement ont été étudiés: de la paroi globale aux constituants, de la paroi passive ex vivo sous chargement contrôlé à la paroi active in vivo sous chargement physiologique et enfin de la paroi saine des volontaires non-malades à la paroi lésée des patients en pré-opératoire. Un protocole a été développé pour évaluer la contribution des composants de la paroi abdominale humaine ex vivo à sa réponse mécanique globale. Les spécimens sont sollicités par pression après dissection successive des différents composants. L’analyse par stéréo-corrélation des déformations de la surface interne a montré que la gaine des rectus abdominis joue un rôle important dans la réponse de la paroi abdominale antérieure. Les examens in vivo ont permis de considérer la paroi abdominale in situ de 11 volontaires non-malades et pour la première fois de patients souffrant d’éventration (n=4) en pré-opératoire. Géométrie externe et interne, élasticité des muscles et raideurs locales ont été mesurées lors d’activités physiologiques. Les paramètres mécaniques mesurés sur les patients restent soit dans l’étendue de mesure des valeurs des volontaires non malades, soit sont plus faibles. Dans le futur, l’inclusion d’autres patients et des examens post-opératoires seront poursuivis. On disposera alors de données quantitatives de la paroi abdominale couvrant l’état sain, lésé et réparé. Des modèles numériques pourront être développés. Ils permettront d’estimer l’influence de paramètres mécaniques et géométriques sur le comportement de la paroi abdominale / This thesis focuses on the biomechanics of the abdominal wall in order to help improving the treatment of incisional hernias. Several aspects of its response werestudied: from global wall to components, from passive wall ex vivo subjected to controlled loading to active wall in vivo under physiological loading and finally from intact wall of healthy volunteers to incised wall of herniated patients before repair surgery. A protocol was developed to assess the contribution of the components of the human abdominal wall ex vivo to the global mechanical response. The specimens were loaded by air pressure after dissection of different components. The strain analysis of the internal surface by stereo-correlation highlighted the importance of the rectus abdominis sheath in the response of the anterior abdominal wall. The in vivo examinations considered the entire abdominal wall in situ of 11 healthy volunteers and for the first time herniated patients before surgery (n=4). External and internal geometry, muscle elasticity and local stiffness were measured during various physiological activities. Mechanical parameters measured on patients remain either in the range of values obtained with healthy volunteers or lower. In the future, the inclusion of other patients and post-operative examinations will be conducted. This will provide quantitative data for the healthy, incised and repaired abdominal wall and support the development of numerical models to estimate the influence of mechanical and geometrical parameters on the behavior of the abdominal wall

L’objectif de cette thèse de doctorat était de concevoir et développer un système permettant de caractériser les épandeurs et de prédire la répartition d’engrais au sol. Nous avons proposé deux approches basées respectivement sur l’imagerie 2D et 3D.Le système 2D a permis de déterminer les déplacements dans les images avec une très haute précision où 90% des estimations ont uniquement moins de 0,2 pixels d’erreur. Cependant cette précision n’était applicable que dans le cas d’un épandeur équipé de disques plats pour lequel la plupart des engrais est éjectée dans le plan horizontal parallèle au plan d’image de la camera. Par conséquent nous avons proposé un système d’imagerie 3D qui a permis de déterminer le mouvement 3D des engrais. Ainsi il peut être appliqué sur des épandeurs équipés de disque concave.Ce nouveau système peut : Caractériser les épandeurs dans un hall avec des conditions contrôlées ;Evaluer les effets de différents réglages des épandeurs ;Etudier le comportement des granulés et améliorer le modèle de vol balistique.Un tel système, moyennant quelques modifications, est envisagé à long terme sur un épandeur, permettant une gestion en temps réel de l’épandage et une rétroaction potentielle sur le fonctionnement de l’épandeur. [extrait du résumé] / The characterization of the fertilizer centrifugal spreading has become an important agriculture scientific issue in order to help farmers having a higher fertilization precision hence higher production efficiency. The ejected fertilizer grains are comparable to projectiles; hence, by using a ballistic flight model, predicting the spread pattern on the ground relies on an estimation of the trajectories and velocities of ejected grains. To estimate those parameters two approaches were proposed. First a two-steps zero mean normalized cross-correlation based algorithm for motion estimation was used to determine the displacement of the grains in the 2D images. The efficiency of this algorithm was evaluated by the mean of a grain images’ simulator. The results showed a high accuracy with an error of less than 0.2 pixels for 90% of the estimated velocities. However, the vertical ejection angle cannot be determined. This limits the use of the technique to spreaders equipped with flat disks where the trajectories of the grains will mostly be in a horizontal plane. This restriction was handled by the second approach. It is based on a 3D stereovision imaging system. A region based stereo matching algorithm with uniqueness and ordering constraints was introduced. It was validated using a grains’ stereo images simulator. 90% of the disparities were estimated with errors less than 2 pixels (around 1%). Moreover a 3D motion estimation algorithm was developed. It is based on an improvement of the previous 2D motion estimation algorithm combined with the estimated 3D coordinates. The efficiency of the whole system was approved via a comparison of its results and a real distribution obtained from a developed cylindrical collector.

Cette thèse s'inscrit dans le cadre du projet CPER Bramms, dont un des objectifs était de développer une méthode d'acquisition de la surface du buste féminin. Les travaux menés ont donc eu pour but la conception, le développement et la réalisation d'une machine de mesure tridimensionnelle adaptée aux objets vivants. Parmi le nombre important de méthodes de mesures tridimensionnelles existantes, l'attention a été portée sur la mise en correspondance par stéréovision ainsi que sur l'utilisation de lumière structurée. La mise en correspondance par stéréovision consiste à retrouver les pixels homologues dans deux images d'une même scène, prise de deux points de vue différents. Une des manières de réaliser la mise en correspondance est de faire appel à des mesures de corrélation. Les algorithmes utilisés se heurtent alors à certaines difficultés : les changements de luminosité, les bruits, les déformations, les occultations, les zones peu texturées et les larges zones homogènes. L'utilisation de lumière structurée a permis essentiellement d'ajouter de l'information dans les zones homogènes lors des travaux menés. En développant cette approche, une méthode de reconstruction originale basée sur l'exploitation d'un motif particulier projeté sur la surface a ainsi été conçue. Un appariement basé sur la comparaison de signatures de points particuliers du motif a été mis en place. Ce procédé permet une reconstruction éparse en une unique acquisition et simplifie l'étape de gestion du nuage de points pour en faire un maillage surfacique / This thesis is part of the CPER BRAMSS project, one of its objectives was to develop an surface's retrieval method applied to the female bust. Therefore the work has aimed at the design, development and implementation of a three-dimensional measuring machine adapted to living objects.Among the large number of existing methods of three-dimensional measurements, attention was paid to the stereo matching as well as the use of structured light. Matching in stereovision is to find homologous pixels in two images of the same scene, taken from two different points of view. One way to achieve the mapping is to use correlation measurements. The algorithms used come up against certain difficulties: the changing light, noises, distortions, occlusions, low textured areas and large homogeneous areas. The use of structured light allow essentially the adding of information in homogeneous areas in this work. Developing this approach, an original method of reconstruction based on the exploitation of a particular pattern projected on the surface has been designed. A matching based on a comparison of the signatures of specific points in the pattern was implemented. This method allows a single sparse reconstruction acquisition step and simplifies the handling of the point cloud when transforming it in a surface mesh

This thesis addresses a number of problems in computer vision, image processing, and geometry processing, and presents novel solutions to these problems. The overarching theme of the techniques presented here is a multi-scale approach, leveraging mathematical tools to represent images and surfaces at different scales, and methods that can be adapted from one type of domain (eg., the plane) to another (eg., the sphere). The main problem addressed in this thesis is known as stereo reconstruction: reconstructing the geometry of a scene or object from two or more images of that scene. We develop novel algorithms to do this, which work for both planar and spherical images. By developing a novel way to formulate the notion of disparity for spherical images, we are able effectively adapt our algorithms from planar to spherical images. Our stereo reconstruction algorithm is based on a novel application of distance transforms to multi-scale matching. We use matching information aggregated over multiple scales, and enforce consistency between these scales using distance transforms. We then show how multiple spherical disparity maps can be efficiently and robustly fused using visibility and other geometric constraints. We then show how the reconstructed point clouds can be used to synthesize a realistic sequence of novel views, images from points of view not captured in the input images, in real-time. Along the way to this result, we address some related problems. For example, multi-scale features can be detected in spherical images by convolving those images with a filterbank, generating an overcomplete spherical wavelet representation of the image from which the multiscale features can be extracted. Convolution of spherical images is much more efficient in the spherical harmonic domain than in the spatial domain. Thus, we develop a GPU implementation for fast spherical harmonic transforms and frequency domain convolutions of spherical images. This tool can also be used to detect multi-scale features on geometric surfaces. When we have a point cloud of a surface of a particular class of object, whether generated by stereo reconstruction or by some other modality, we can use statistics and machine learning to more robustly estimate the surface. If we have at our disposal a database of surfaces of a particular type of object, such as the human face, we can compute statistics over this database to constrain the possible shape a new surface of this type can take. We show how a statistical spherical wavelet shape prior can be used to efficiently and robustly reconstruct a face shape from noisy point cloud data, including stereo data.